Academic papers and research lineage

Mastering Atari, Go, chess and shogi by planning with a learned model

Abstract Constructing agents with planning capabilities has long been one of the main challenges in the pursuit of artificial intelligence. Tree-based planning methods have enjoyed huge success in challenging domains, such as chess1 and Go2, where a perfect simulator is available. However, in real-world problems, the dynamics governing the environment are often complex and unknown. Here we present the MuZero algorithm, which, by combining a tree-based search with a learned model, achieves superhuman performance in a range of challenging and visually complex domains, without any knowledge of their underlying dynamics. The MuZero algorithm learns an iterable model that produces predictions relevant to planning: the action-selection policy, the value function and the reward. When evaluated on 57 different Atari games3—the canonical video game environment for testing artificial intelligence techniques, in which model-based planning approaches have historically struggled4—the MuZero algorithm achieved state-of-the-art performance. When evaluated on Go, chess and shogi—canonical environments for high-performance planning—the MuZero algorithm matched, without any knowledge of the game dynamics, the superhuman performance of the AlphaZero algorithm5 that was supplied with the rules of the game.

Julian Schrittwieser · Ioannis Antonoglou · Thomas Hubert · Karen Simonyan · Laurent Sifre · Simon Schmitt · Arthur Guez · Edward Lockhart · Demis Hassabis · Thore Graepel · Timothy Lillicrap · David Silver

A Human-Sensitive Controller: Adapting to Human Musculoskeletal Disorder-Related Constraints via Reinforcement Learning

arXiv:2504.10102v2 Announce Type: replace Abstract: Work-Related Musculoskeletal Disorders continue to be a major challenge in industrial environments, leading to reduced workforce participation, increased healthcare costs, and long-term disability. This study introduces a human-sensitive robotic system aimed at reintegrating individuals with a history of musculoskeletal disorders into standard job roles, while simultaneously optimizing ergonomic conditions for the broader workforce. This research leverages reinforcement learning (RL) to develop a human-aware control strategy for collaborativ…

Where to Touch, How to Contact: Hierarchical RL-MPC Framework for Geometry-Aware Long-Horizon Dexterous Manipulation

arXiv:2601.10930v3 Announce Type: replace Abstract: A key challenge in contact-rich dexterous manipulation is the need to jointly reason over global geometry and nonsmooth contact dynamics. End-to-end policies bypass this complexity, but often require large amounts of data and transfer poorly from simulation to reality. We address the limitations with a simple insight: dexterous manipulation is inherently hierarchical--at a high level, a robot decides where to touch (geometry); at a low level it determines how to move the object through contact dynamics. Building on this insight, we propose a…

CRAFT: Coaching Reinforcement Learning Autonomously using Foundation Models for Multi-Robot Coordination Tasks

arXiv:2509.14380v3 Announce Type: replace Abstract: Multi-Agent Reinforcement Learning (MARL) provides a powerful framework for learning coordination in multi-agent systems. However, applying MARL to robotics remains challenging due to their high-dimensional continuous joint action spaces, complex reward design, and non-stationarity from concurrently learning agents. On the other hand, humans often learn complex coordination with the help of coaches, who guide learning through carefully designed curricula and detailed feedback. Building on the reasoning capabilities of foundation models, we a…

From Pixels to Shelf: An Integrated Robotic System for Autonomous Supermarket Stocking with a Mobile Manipulator

arXiv:2509.11740v2 Announce Type: replace Abstract: Autonomous stocking in retail environments, particularly supermarkets, presents challenges due to dynamic human interactions, constrained spaces, and diverse product geometries. This paper introduces an efficient modular robotic system for autonomous shelf stocking, integrating commercially available hardware with a scalable algorithmic architecture. A major contribution of this work is the system integration of off-the-shelf hardware and ROS2-based perception, planning, and control into a single deployable platform for retail environments.…

Test-Time Trajectory Optimization for Autonomous Driving

arXiv:2606.07170v1 Announce Type: new Abstract: End-to-end planners for autonomous driving typically generate a set of candidate trajectories, score each one, and return the highest-scoring candidate. However, the scorer is applied only after the proposals are generated and cannot influence the set of trajectories: a weak set of candidates limits planning performance regardless of the scorer's quality. We instead treat the scorer as a learned trajectory-level reward function and search for trajectories that maximize it. Our method, TOAD, runs the Cross-Entropy Method at test time, warm-starte…

CAPE: Contrastive Action-conditioned Parallel Encoding for Embodied Planning

arXiv:2606.07304v1 Announce Type: new Abstract: Embodied agents need to predict the future consequences of candidate actions in order to plan effectively before execution. Existing visual dynamics models learn by reconstructing future visual states or rolling out dense latent representations, which spreads learning capacity across visually salient but planning-irrelevant content rather than the action-conditioned changes that drive manipulation outcomes. We propose CAPE, a Contrastive Action-conditioned Parallel Encoding framework that learns visual dynamics by distinguishing the future outco…

A Causal Probabilistic Framework for Perception-Informed Closed-Loop Simulation of Autonomous Driving

arXiv:2606.07186v1 Announce Type: new Abstract: Software-in-the-loop (SIL) simulation is a cornerstone for the validation of modern automotive safety functions. However, many current frameworks utilize ideal sensing, which bypasses the functional insufficiencies of perception algorithms, leading to over-optimistic safety assessments. This paper proposes a perception-informed SIL testing methodology that bridges the gap between ground-truth simulation and real-world perception behavior. We present a framework for incorporating causal probabilistic models into standardized, scenario-based simul…

Physiologically Constrained Musculoskeletal Neural Network for Multi-DoF Joint Kinematics Estimation from Partially Observed sEMG

arXiv:2606.07476v1 Announce Type: cross Abstract: This paper investigates multi-degrees of freedom (DoF) joint kinematics estimation under partially observed surface electromyography (sEMG), where only a subset of task-relevant muscles can be measured due to anatomical inaccessibility or sensor constraints. A novel musculoskeletal neural network (MSK-NN) is proposed to estimate multi-DoF joint angles while simultaneously inferring activations for both measured and unmeasured muscles. MSK-NN consists of a CNN-based muscle activation estimator and an embedded MSK forward dynamics module, formin…

Dreaming when Necessary: Advancing World Action Models with Adaptive Multi-Modal Reasoning

arXiv:2606.07089v1 Announce Type: new Abstract: World Action Models (WAMs) offer a promising approach to embodied intelligence, yet existing methods rely heavily on video prediction as action priors and lack adaptive multimodal reasoning, limiting their effectiveness on long-horizon, complex tasks. We observe that WAMs require different multimodal reasoning modes under different execution contexts: textual reasoning is essential during task transitions to guide high-level action prediction, while visual reasoning is critical during fine-grained manipulation for precise control. Motivated by t…

Predictive Style Matching: Natural and Robust Humanoid Locomotion

arXiv:2606.07083v1 Announce Type: new Abstract: Reinforcement learning has become the prevailing approach to humanoid locomotion control: policies transfer reliably from simulation to hardware and recover gracefully from disturbances. Motion quality, however, still lags behind: task-only rewards often converge to stiff, asymmetric gaits, while motion imitation methods improve appearance but become more sensitive to external disturbances because reference signals can oppose the transient poses needed to regain balance. We propose Predictive Style Matching, in which an offline predictor maps th…

LIMMT: Less is More for Motion Tracking

arXiv:2606.06953v1 Announce Type: new Abstract: We argue that high-quality motion data can steer tracking policies toward better optimization trajectories early in training. In this work, we introduce LIMMT (Less Is More for Motion Tracking). To our knowledge, this is the first data-centric study for physics-based humanoid motion tracking. We go beyond simply removing low-quality and erroneous clips, but define motion data quality through three dimensions: physics feasibility, diversity, and complexity. We show that even training with under 3% of AMASS yields better tracking performance than…

T-GMP: Terrain-conditioned Generative Motion Priors for Versatile and Natural Humanoid Locomotion

arXiv:2606.06944v1 Announce Type: new Abstract: Achieving both anthropomorphic naturalness and robust terrain traversal remains a fundamental challenge in humanoid locomotion. Existing Reinforcement Learning (RL) approaches typically rely on fixed motion priors, limiting their adaptability to varying environments. We propose Terrain-conditioned Generative Motion Priors (T-GMP), a module that captures a terrain-conditioned latent motion manifold from a few expert state-terrain demonstrations using a Conditional Variational Autoencoder (CVAE). The learned priors enable smooth style transitions,…

Robots Need More than VLA and World Models

arXiv:2606.06556v1 Announce Type: new Abstract: Generalist robot intelligence is often framed as a policy-scaling problem: collect more robot demonstrations, train larger Vision-Language-Action (VLA) models, and expect broader generalisation. In this position paper, we argue that this framing is incomplete. The central bottleneck is not only policy learning, but the absence of mechanisms that convert the world's abundant unstructured behavioural data into grounded robot supervision. Human motion, internet video, simulation rollouts, and interactive demonstrations contain rich information abou…

PhyRoGen: Synthetic Generation of Physical Robot Manipulation Puzzles Using Procedural Content Generation

arXiv:2606.06569v1 Announce Type: new Abstract: Robot manipulation of physical puzzles is important for automatic assembly and disassembly tasks. However, to enable robots to solve physical puzzles, manipulation skills need to be learned, which requires large training datasets, the generation of which is often time consuming and tedious. To overcome this problem, we propose the Physical Robot Manipulation Puzzle Generation framework (PhyRoGen), which leverages procedural content generation (PCG) for automated generation of synthetic datasets of manipulation puzzles. PhyRoGen is a general-purp…

Optimal Control Approach for Non-prehensile Ball Juggling Using a 7-DoF Manipulator

arXiv:2606.06704v1 Announce Type: new Abstract: Non-prehensile object manipulation skills are important for real-world robot interactions, enabling highly dynamic tasks such as balancing a glass on a tray or the controlled sliding of items on a table. Among such tasks, those characterised by high-speed manipulation requirements and general sensitivity of the resulting hybrid dynamics are particularly hard to accomplish. Within these, juggling can be seen as a highly challenging maneuver to be solved. The key to robotic juggling is achieving dynamic stabilisation of an underactuated object. Si…

Mission-Level Runtime Assurance Framework for Autonomous Driving

arXiv:2606.06996v1 Announce Type: new Abstract: This paper studies runtime safety for autonomous driving when high-level driving commands become faulty or unreliable. Unlike conventional runtime-safety approaches that mainly focus on immediate vehicle safety, the proposed framework evaluates both driving safety and whether the vehicle can still successfully complete its mission before a command is executed. The framework extends highway-env with mission-level fault scenarios such as skipping required checkpoints, entering restricted areas, and generating future routes that can no longer compl…

IDDMBSE: Integrating Data-Driven and Model-Based Systems Engineering for Trusted Autonomous Cyber-Physical Systems

arXiv:2606.06727v1 Announce Type: new Abstract: Autonomous cyber-physical systems (CPS) sit at the intersection of Model-Based Systems Engineering (MBSE) and data-driven Machine Learning and Artificial Intelligence (ML/AI), yet no integrated Systems Engineering (SE) methodology natively spans both. We address this gap with IDDMBSE, an Integrated Data-Driven and Model-Based Systems Engineering methodology that extends the rigorous MBSE V-process with a data-driven loop at every step, anchored in SysML, the autonomy stack, and a hybrid model-based plus data-driven trade-off architecture. We ins…

STRIPS-WM: Learning Grounded Propositional STRIPS-style World Models from Images

arXiv:2606.06832v1 Announce Type: new Abstract: Robots performing long-horizon visual manipulation observe high-dimensional images, but successful plans depend on action-relevant facts: what can be done now and what changes afterward. A useful planning representation should discard irrelevant visual details while preserving action applicability and effects. Classical task planners exploit this structure through symbolic operators with preconditions and effects, but obtaining such representations from raw visual experience remains challenging. We study a visual task-planning setting in which a…

Predicting Dynamic Map States from Limited Field-of-View Sensor Data

arXiv:2602.12360v2 Announce Type: replace Abstract: When autonomous systems are deployed in real-world scenarios, sensors are often subject to limited field-of-view (FOV) constraints, either naturally through system design, or through unexpected occlusions or sensor failures. In conditions where a large FOV is unavailable, it is important to be able to infer information about the environment and predict the state of nearby surroundings based on available data to maintain safe and accurate operation. In this work, we explore the effectiveness of deep learning for dynamic map state prediction b…

How AI is reshaping discovery in maths and physics

Summary extraction is still pending for this item.

AI is taking on antibiotic resistance — here’s how

Summary extraction is still pending for this item.

Federated orthogonal learning for detection of liver lesions from multi-phase contrast-enhanced CT images

Summary extraction is still pending for this item.

Gene dependency-informed inference of response to targeted cancer therapies

Summary extraction is still pending for this item.

Chromatix: a differentiable, GPU-accelerated wave-optics library

Summary extraction is still pending for this item.

A scalable approach to investigating sequence-to-function predictions from personal genomes

Summary extraction is still pending for this item.

PriSrv+: Privacy and Usability-Enhanced Wireless Service Discovery with Fast and Expressive Matchmaking Encryption

arXiv:2606.05902v1 Announce Type: new Abstract: Service discovery is a fundamental process in wireless networks, enabling devices to find and communicate with services dynamically, and is critical for the seamless operation of modern systems like 5G and IoT. This paper introduces PriSrv+, an advanced privacy and usability-enhanced service discovery protocol for modern wireless networks and resource-constrained environments. PriSrv+ builds upon PriSrv (NDSS'24), by addressing critical limitations in expressiveness, privacy, scalability, and efficiency, while maintaining compatibility with wide…

An ERP Study on Recursive Locative Processing in Mandarin-Speaking Children with Autism

arXiv:2606.05620v1 Announce Type: new Abstract: Recursion enables the generation of hierarchical linguistic structures but imposes substantial processing demands during real-time comprehension. While difficulties with complex syntax have been reported in autism spectrum disorder (ASD), the temporal dynamics of recursive processing remain poorly understood. This study used event-related potentials (ERPs) to examine how Mandarin-speaking children with ASD process two-level recursive locative constructions. Twenty-four children (12 ASD, 12 typically developing, TD) participated in a cross-modal…

Forgive or forget: Understanding the context of hate in audio retrieval systems

arXiv:2606.05857v1 Announce Type: new Abstract: Handling toxic retrieval in text-to-audio systems is challenging due to contextual dependencies. Existing strategies (e.g., rephrasing, summarization) risk altering intent or omitting details. We propose a post hoc causal debiasing framework with a sentiment-controlled mediator to preserve semantic relevance while suppressing harmful speech. Our approach is model-agnostic and integrates seamlessly with existing retrieval pipelines. We introduce two variants: Forgive, which re-ranks and filters toxic audio via logit adjustment, and Forget, which…

The Generator-Eraser Paradox: Community Guidelines for Responsible LLM-Assisted Dialect Resource Creation

arXiv:2606.06004v1 Announce Type: new Abstract: Dialect resources occupy a unique position at the intersection of scientific description, cultural preservation, and computational infrastructure. Large language models offer powerful capabilities for accelerating dialect resource development through retrieval-grounded drafting, corpus navigation, metadata enrichment, and annotation workflow support. However, the same systems pose substantial risks: they can contribute to dialect erasure by privileging prestige varieties, homogenizing orthography, and enabling synthetic feedback loops that reduc…

ReverseEOL: Improving Training-free Text Embeddings via Text Reversal in Decoder-only LLMs

arXiv:2606.05858v1 Announce Type: new Abstract: Recent advances in Large Language Models (LLMs) have opened new avenues for generating training-free text embeddings. However, the causal attention in decoder-only LLMs prevents earlier tokens from attending to future context, leading to biased contextualized representations. In this work, we propose Reverse prompting with Explicit One-word Limitation (ReverseEOL), a simple yet effective method for enhancing the representational capability of frozen LLMs. ReverseEOL augments the standard forward embedding with an additional reversed embedding de…

M2S-AVSR: Modality-aware Multi-view Self-supervised Representation for Robust Audio-Visual Speech Recognition

arXiv:2606.05763v1 Announce Type: new Abstract: Audio-Visual Speech Recognition (AVSR) enhances speech recognition robustness by leveraging visual cues, while real-world scenarios remain challenging due to viewpoint variation, audio distortion, and visual occlusion, which degrade modality quality and increase audio-visual asynchrony. In this paper, we propose a novel Modality-aware Multi-view Self-supervised representation framework for robust Audio-Visual Speech Recognition (M2S-AVSR). First, we introduce a multi-view representation learning encoder to learn view-invariant visual speech repr…

Using Large Language Models to Support High Volume Application Review for an Undergraduate Research Program

arXiv:2606.05564v1 Announce Type: new Abstract: Undergraduate research programs such as the Summer Undergraduate Research Fellowship (SURF) at Purdue University receive thousands of applications every year, requiring significant time and effort for program staff to evaluate each submission consistently and within tight timelines. This work-in-progress paper describes the development and initial deployment of a large language model (LLM)-based tool to assist in the evaluation of approximately 1,200 student Statements of Purpose (SoPs) for the SURF 2026 cycle at Purdue University. The workflow…

Multi-Granularity Reasoning for Natural Language Inference

arXiv:2606.05181v1 Announce Type: new Abstract: Natural Language Inference (NLI) is a fundamental task in natural language understanding that requires determining the logical relationship between a premise and a hypothesis. Despite the remarkable success of transformer-based pre-trained models, most existing approaches primarily rely on the final-layer token representations, which are often insufficient for capturing the complex and hierarchical semantic interactions required for effective reasoning. In particular, fine-grained lexical cues, phrasal compositions, and higher-level contextual s…

PlanBench-V: A Spatial Planning Map Benchmark for Vision-Language Models

arXiv:2606.05744v1 Announce Type: new Abstract: Spatial planning maps are central to territorial governance, translating planning objectives, regulations, and spatial strategies into visual forms for decision-making, public communication, and institutional coordination. Their interpretation, however, requires fine-grained visual perception, spatial reasoning, and policy-informed professional judgment, creating major challenges for both human learners and AI systems. With the rapid progress of Vision-Language Models (VLMs), their use in urban planning analysis is gaining attention, yet existin…

AdaPLD: Adaptive Retrieval and Reuse for Efficient Model-Free Speculative Decoding

arXiv:2606.05742v1 Announce Type: new Abstract: Speculative decoding accelerates generation by verifying multiple drafted tokens in a single target-model forward pass, reducing sequential decoding iterations. Model-free variants avoid auxiliary draft models by reusing text and model states already available during generation, but their speedup depends on the reliability of the constructed drafts. We identify two limitations of existing reuse-based methods: lexically anchored retrieval has limited recall under surface-form variation, and deterministic span copying can be brittle when the retri…

RAG Security and Privacy: Formalizing the Threat Model and Attack Surface

arXiv:2509.20324v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) is an emerging approach in natural language processing that combines large language models (LLMs) with external document retrieval to produce more accurate and grounded responses. While RAG has shown strong potential in reducing hallucinations and improving factual consistency, it also introduces new privacy and security challenges that differ from those faced by traditional LLMs. Existing research has demonstrated that LLMs can leak sensitive information through training data memorization or adversarial…

An Ultra-Low-Bitrate Neural Speech Codec with Plain-to-Pseudo Synergistic Vector Quantization

arXiv:2606.05876v1 Announce Type: new Abstract: Most neural speech codecs use residual vector quantization (RVQ), in which later VQs contribute less but consume the same bitrate, leading to inefficiency. We propose P2PSynCodec, an ultra-low-bitrate neural speech codec with a plain-to-pseudo synergistic vector quantizer (P2PSVQ). P2PSVQ consists of one plain VQ and multiple pseudo VQs. The plain VQ produces basic tokens by quantization, while the pseudo VQs generate auxiliary tokens by neural prediction and incur zero transmitted bitrate. Thus, speech is decoded from the plain-VQ tokens togeth…

Scaffold, Not Vocabulary? A Controlled, Two-Tier, Pre-Registered Study of a Popperian Code-Generation Skill

arXiv:2606.06454v1 Announce Type: cross Abstract: Large language models increasingly write, review, and judge code, and a fast-growing practice equips them with prompt 'skills' that ask the model to reason like a scientist. A prominent example tells the model to act as a Popperian falsificationist, and such skills are reported to improve generated code. But these gains are almost always read off an LLM-as-a-judge, an instrument with documented positional, self-preference, and stylistic biases. We ask: if it appears to help, is the gain from the skill's Popperian content, or from the structure…

High-Dimensional Theory of LoRA Fine-Tuning in a Solvable Attention Model

arXiv:2606.05899v1 Announce Type: new Abstract: We develop a high-dimensional statistical theory of low-rank adaptation (LoRA) in attention models, capturing the interplay between pre-training and fine-tuning. We introduce a solvable framework in which a single-head attention layer is first pre-trained on a data-abundant task and subsequently adapted via a rank-one LoRA update on limited data. In the high-dimensional limit, both stages admit a sharp asymptotic characterization in terms of a finite set of order parameters, yielding explicit predictions for test errors and representation alignm…

Nonreversible Gauge Fields in Fokker--Planck Dynamics: Supersymmetric Hamiltonians and Learned Finite Forces

arXiv:2606.06412v1 Announce Type: cross Abstract: We formulate stationary-density-preserving nonreversible perturbations of Fokker--Planck dynamics as gauge fields that deform relaxation spectra while leaving the invariant state fixed. When detailed balance holds, a similarity transformation maps the reversible Fokker--Planck operator to a Witten-Laplacian-type supersymmetric Hamiltonian; nonreversible gauges then appear as non-Hermitian perturbations that preserve the zero mode but modify the excited spectrum. This operator viewpoint gives a common language for relaxation gaps, circulating p…

Bootstrapping Semantic Layer from Execution for Text-to-SQL

arXiv:2606.05634v1 Announce Type: new Abstract: Real-world text-to-SQL is often under-specified until user phrases are grounded in how the database stores values. Prior work attempts to address this by requiring a semantic layer to specify groundings in advance, but such specifications are often incomplete, especially in expert domains where domain-specific conventions are under-documented. As this leaves multiple grounding hypotheses open for the same SQL part, we introduce GATE (Grouding After Test from Execution), which bootstraps missing groundings from execution feedback. GATE keeps grou…

Enhancing Audio Captioning with Auxiliary AudioSet Semantics

arXiv:2606.05717v1 Announce Type: new Abstract: Automatic Audio Captioning (AAC) seeks to generate natural language descriptions of complex acoustic scenes, bridging auditory perception and language understanding. However, word-selection indeterminacy and increasing reliance on large-scale sequence-to-sequence or LLM-based models limit practical deployment. We propose a resource-efficient AAC framework that explicitly grounds caption generation in auxiliary AudioSet semantics. Frame-level acoustic representations extracted using a ConvNeXt encoder are augmented with top-$K$ predicted AudioSet…

A Motivational Architecture for Conversational AGI

arXiv:2606.05411v1 Announce Type: cross Abstract: Motivational architectures in cognitive AI have largely been designed for physical agents regulating bodily needs. Conversational agents operate in a different regime: their sensorimotor loop is linguistic, their environment is a user's evolving mental state, and their consequential actions are speech acts, tool invocations, and strategic silences. This paper proposes a conversational reinterpretation of the OpenPsi motivational lineage, coupled to MetaMo's higher-level motivational scaffold, for agents built on a modular execution substrate.…

What's in a Name? Morphological Shortcuts by LLMs in Pharmacology

arXiv:2606.05616v1 Announce Type: new Abstract: The morphological form of a word can often give cues to its meaning, but purely relying on these mappings can lead to overgeneralization in high-stakes domains. In the medical domain, for instance, LLMs can confidently reason about fictitious drugs from their affixes alone (e.g., wugcillin) and generate plausible-looking clinical content. We present a behavioral and mechanistic study of LLM "affix heuristics" in pharmacology. Using fictitious drug names built from real affixes, we show that affix signals alone elicit class-level pharmacological…

Interpreting Style Representations via Style-Eliciting Prompts

arXiv:2606.05716v1 Announce Type: new Abstract: Style representation learning is a powerful tool for authorship analysis and modeling writing style, yet the latent nature of learned representations makes them difficult to interpret. Recent work has attempted to explain these representations by generating natural language descriptions with large language models (LLMs) conditioned on input text. However, such descriptions are often prone to the LLM's biases and hallucinations, and they lack an explicit objective and practical utility. In this work, we propose a novel framework for interpreting…

Anomaly Detection for Electro-Hydrostatic Actuators using LSTM Autoencoder

arXiv:2606.05274v1 Announce Type: new Abstract: Electro-Hydrostatic Actuators (EHAs) are widely used in aerospace and industrial systems, where timely detection of sensor anomalies is essential to ensure safe and reliable operation. However, the large volume and high sampling frequency of EHA sensor data pose challenges for accurate and efficient anomaly detection. Conventional statistical and classical machine-learning methods such as Z-score, Interquartile Range (IQR), Median Absolute Deviation (MAD), Isolation Forest, Gaussian Mixture, and k-means often fail to capture the temporal depende…

Physics-constrained Gaussian Processes for Predicting Shockwave Hugoniot Curves

arXiv:2601.06655v2 Announce Type: replace-cross Abstract: A physics-constrained Gaussian Process regression framework is developed for predicting shocked material states and their associated uncertainties along the Hugoniot curve using data from a small number of shockwave simulations. The proposed Gaussian process is constrained by the Rankine-Hugoniot jump conditions between the various shocked material states to construct a thermodynamically consistent covariance function. This leads to the formulation of an optimization problem over a small number of interpretable hyperparameters and enab…

Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness

arXiv:2606.06306v1 Announce Type: new Abstract: Factual sycophancy occurs when a language model abandons a correct, verifiable answer under social pressure. Because a flip occurs only when pressure toward a false answer exceeds the model's neutral preference for the truth, flip rates conflate two mechanisms: the strength of that baseline preference (truth margin), and how far pressure shifts it (manipulation sensitivity). We decompose factual sycophancy into these channels and use them to separate the effects of size and instruction tuning across 56 open-weight models spanning 0.3B-32B parame…

Probing Spatial Structure in Pretrained Audio Representations

arXiv:2606.05544v1 Announce Type: cross Abstract: Pretrained spatial audio encoders are increasingly used as general-purpose representations for perceptual tasks, yet their spatial encoding capabilities remain poorly understood. We introduce the Spatial Audio Representation Learning (SARL) benchmark, a controlled framework for evaluating spatial information in pretrained audio models. SARL probes source-level factors (azimuth, elevation, distance, class) and room-level factors (RT60, volume, shape). Experiments across diverse encoders reveal three patterns: input configuration and training pa…

EMBER: Efficient Memory via Budgeted Evidence Retention for Long-Horizon Agents

arXiv:2606.05894v1 Announce Type: new Abstract: Long-horizon agents can archive large histories, but future answers still incur retrieval, rereading, and context costs. When retained memory misses answer-relevant evidence, the system must return to larger portions of the raw history. We study budgeted evidence survival: before the query is known, which source evidence should be retained so that it remains recoverable and usable under a fixed retained source-evidence token budget? We instantiate this setting as Budgeted Pre-Query Retention, where memory is written during ingestion and later re…

A differentiable machine learning small-angle X-ray scattering analysis framework for structure elucidation of lipid nanoparticles

arXiv:2606.05200v1 Announce Type: cross Abstract: Lipid nanoparticles (LNPs) are efficient delivery systems for negatively charged nucleic acids. Their multi-component architecture yields a core-shell structure. Small-angle X-ray scattering (SAXS) is an important characterization technique for LNPs, but recovering internal structure and size distribution from SAXS is an inverse problem with non-unique solutions. Realistic models are often too expensive for systematic exploration. We introduce a machine-learning-accelerated, differentiable framework for SAXS analysis of heterogeneous, polydisp…

Automated Proving of Shannon-Type Entropy Inequalities via Fine-Tuned Language Models and Guided Tree Search

arXiv:2606.05729v1 Announce Type: cross Abstract: Proving Shannon-type entropy inequalities is a fundamental task in information theory that often requires constructing non-trivial linear combinations of known constraints, which is a combinatorial search problem that scales poorly with the number of random variables. We investigate whether small-scale large language models (0.6B--1.7B parameters), fine-tuned on atomic proof steps and combined with guided beam search, can automate this process. On a held-out test set of 60 inequalities spanning n=10 to 15 variables, our 0.6B fine-tuned model a…

Formal Concept Lattices are Good Semantic Scaffolds for Concept-Based Learning

arXiv:2606.05471v1 Announce Type: new Abstract: Learning semantics is essential for deep learning models to be interpretable and better aligned with human reasoning. Concept-based models approach this by representing classes through meaningful semantic abstractions, but typically treat all concepts as a flat, unstructured set learned at a single neural network layer. This overlooks a fundamental property of human semantic understanding: concepts being organized hierarchically, from general to specific. While deep networks do learn a hierarchy of visual features, this structure is rarely align…

VoCodec: A Low-bitrate Streamable Neural Speech Codec with Voicing-driven Quantization

arXiv:2606.05892v1 Announce Type: new Abstract: Neural speech codecs are key to speech transmission and storage, but most use uniform quantization across frames, allocating the same bitrate regardless of content and wasting bits. We propose VoCodec, a low-bitrate streamable neural speech codec with voicing-driven quantization that assigns higher bitrate to voiced frames and lower bitrate to unvoiced frames according to perceptual sensitivity. VoCodec embeds a voicing detector in a fully causal encoder-quantizer-decoder neural coding framework, using residual scalar-vector quantization for voi…

Stop Training for the Worst: Progressive Unmasking Accelerates Masked Diffusion Training

arXiv:2602.10314v2 Announce Type: replace Abstract: Masked Diffusion Models (MDMs) have emerged as a promising approach for generative modeling in discrete spaces. By generating sequences in any order and allowing for parallel decoding, they enable fast inference and strong performance on non-causal tasks. However, this flexibility comes with a training complexity trade-off: MDMs train on an exponentially large set of masking patterns, which is not only computationally expensive, but also creates a train--test mismatch between the random masks used in training and the highly structured masks…

Predictable Scaling Laws of Optimal Hyperparameters for LLM Continued Pre-training

arXiv:2606.05610v1 Announce Type: new Abstract: The efficacy of continued pre-training for Large Language Models (LLMs) hinges upon hyperparameter configurations, such as learning rate and batch size. However, current practices often rely on heuristics or grid searches, leading to training instability and excessive costs. In this work, we first empirically discover that optimal hyperparameters follow stable and predictable scaling laws throughout the continued pre-training process. Leveraging these insights, we propose a novel framework to establish quantitative relationships between compute…

Amortized Nonlinear Model Predictive Control

arXiv:2606.05840v1 Announce Type: cross Abstract: Nonlinear Model Predictive Control requires solving a constrained nonlinear program (NLP) in real-time at every sampling instant, a computational bottleneck that limits deployment on resource-constrained hardware or at high sampling rates. We address this challenge for the broad class of input-affine nonlinear systems to show that the optimal control move can be approximated by a state-dependent quadratic program (QP) whose cost parameters depend on the current state and reference. We propose a single-network residual-corrector architecture: a…

Improving Answer Extraction in Context-based Question Answering Systems Using LLMs

arXiv:2606.06197v1 Announce Type: new Abstract: Question answering (QA) systems have achieved notable progress with the advent of large language models (LLMs). However, they still face challenges in accurately extracting and generating precise answers from given contexts, particularly when dealing with complex or ambiguous queries. Existing approaches often struggle with contextual understanding, answer consistency, and generalization across diverse domains. In this work, we propose a question answering system based on large language models, where the input consists of a textual context and a…

VTI-CoT: Visual-Textual Interleaved Chain of Thought for Video Reasoning

arXiv:2606.05736v1 Announce Type: new Abstract: Video reasoning aims to understand complex temporal events and causal relationships within videos. Recently, Chain-of-Thought (CoT) has been introduced to this field to enhance reasoning accuracy. However, existing CoT-based video reasoning methods primarily rely on text-only information for logical deduction, overlooking critical visual information during the inference process. Inspired by the human cognitive mechanism of reviewing visual segments during inference, we propose VTI-CoT, a Visual-Textual Interleaved CoT framework. VTI-CoT integrat…

Can LLMs Write Correct TLA+ Specifications? Evaluating Natural-Language-to-TLA+ Generation

arXiv:2606.05792v1 Announce Type: cross Abstract: TLA+ has supported industrial verification at companies such as Amazon and Microsoft, yet writing correct TLA+ specifications from natural language still requires time and expertise, which limits adoption. LLMs show promise, but no prior study measures whether they produce semantically correct TLA+ specifications from natural language. This paper presents the first systematic evaluation of LLM-based TLA+ specification synthesis from natural language. Our study evaluates 30 LLMs across eight families on a curated dataset of 205 TLA+ specificati…

A Judge-Aware Ranking Framework for Evaluating Large Language Models without Ground Truth

arXiv:2601.21817v2 Announce Type: replace-cross Abstract: Evaluating large language models (LLMs) on open-ended tasks without ground-truth labels is increasingly done via the LLM-as-a-judge paradigm. A critical but under-modeled issue is that judge LLMs differ substantially in reliability; treating all judges equally can yield biased leaderboards and misleading uncertainty estimates. More data can make evaluation more confidently wrong under misspecified aggregation. We propose a judge-aware ranking framework that extends the Bradley-Terry-Luce model by introducing judge-specific discriminati…

LoRi: Low-Rank Distillation for Implicit Reasoning

arXiv:2606.05315v1 Announce Type: new Abstract: Implicit chain-of-thought (iCoT) methods aim to internalize reasoning in large language models, but often underperform explicit CoT prompting. We empirically find that hidden-state reasoning trajectories exhibit low-rank structure. Motivated by this observation, we propose a low-rank distillation framework that transfers reasoning by aligning teacher and student trajectories in a shared low-rank tensor subspace using first- and second-order statistics. The resulting formulation captures the global structure of reasoning while supporting a compac…

LEVANTE-bench: Multi-Scale Comparison of VLMs to Children Using Cognitive Tasks (or, "Is Your VLM Smarter Than a 5th Grader?")

arXiv:2606.05497v1 Announce Type: new Abstract: Given the inherently multimodal nature of human experience, vision-language models (VLMs) hold substantial promise for modeling human cognition as it grows and develops with experience. Realizing their potential requires tools for comparing VLMs with human cognitive development across tasks, ages, and populations. We present LEVANTE-bench, a benchmark based on tasks and data from the Learning Variability Network (LEVANTE), which distributes open-source tasks and data measuring children's cognition across languages and cultures. In LEVANTE-bench,…

Mutation Without Variation: Convergence Dynamics in LLM-Driven Program Evolution

arXiv:2606.05408v1 Announce Type: cross Abstract: When an LLM repeatedly mutates a program, does it explore new forms or circle back to the same ones? We study this question by analyzing LLM-driven mutation chains in the absence of selection pressure within a domain-specific language, varying prompt design, model family, and stochastic replication. We find that LLM-based mutation consistently converges toward restricted attractor regions in program space. Convergence is especially severe at the structural level: in 87% of chains, over 93% of mutations revisit a previously seen structural form…

Generalized TV--$\ell_p$ Structured Priors for Bayesian $T_1$ Mapping

arXiv:2606.05381v1 Announce Type: new Abstract: We propose an extended family of structured spatial priors that incorporates the total variation (TV) function with $\ell_p$ norms. The prior is proven to be proper and incorporated into a Bayesian regression framework to enable uncertainty quantification in $T_1$ mapping, with posterior inference performed using the No-U-Turn Sampler (NUTS). This TV--$\ell_p$ construction is proven to constitute a well-defined family of prior distributions, and it naturally enforces spatial consistency and smooth variations in the estimated parameter maps. The…

Contextualized Prompting For Stance Detection On Social Media

arXiv:2606.06022v1 Announce Type: new Abstract: Stance detection on social media is challenging due to short, noisy, and context-dependent language. While large language models (LLMs) show zero-shot generalization, they are typically prompted without contextual information, which limits their ability to interpret ambiguous posts. In this work, we systematically investigate the impact of incorporating real-world (e.g., user biographies), derived (e.g., political party), and LLM-generated (e.g., target descriptions) contextual features into zero-shot prompting for stance detection on Twitter. O…

Towards Realistic 3D Sonar Simulation

arXiv:2606.06130v1 Announce Type: new Abstract: As underwater robotics research increasingly addresses complex 3D perception and autonomous navigation, the fidelity of sonar simulation has become a key factor in algorithm development. Current simulation frameworks typically rely on geometry-driven rendering, approximating 3D sonar as an underwater equivalent to LiDAR, which fails to account for fundamental acoustic phenomena such as refraction, multi-path interference, and phase-dependent signal formation. This paper proposes a modular architecture for realistic 3D sonar simulation that integ…

TensorBench: Benchmarking Coding Agents on a Compiler-Based Tensor Framework

arXiv:2606.05570v1 Announce Type: new Abstract: Repository-level coding benchmarks face a trade-off between task difficulty and evaluation reliability: tasks that challenge frontier models often involve large codebases with incomplete test coverage, while human review does not scale. We introduce TensorBench, a benchmark of 199 feature-addition and refactoring tasks on an open-source compiler-based tensor framework that extends PyTorch with first-class support for dense and sparse tensors. Tasks cover new sparse formats, dense optimization passes, IR transformations, scheduler changes, runtim…

SpeechJBB: Probing Safety Alignment and Comprehension in Large Audio Language Models under Code-Switched Speech

arXiv:2606.06037v1 Announce Type: cross Abstract: Large audio language models (LALMs) are increasingly deployed in real-world applications, yet their safety alignment is still primarily evaluated on monolingual, text-based harmful prompts. This leaves their generalizability under multilingual and spoken settings, particularly code-switched speech, largely underexplored. To address this gap, we introduce SpeechJBB, an audio jailbreak dataset for benchmarking across multiple state-of-the-art LALMs. The extent of safety weaknesses is further probed by introducing an augmented setting where phono…

CHASE: Adversarial Red-Blue Teaming for Improving LLM Safety using Reinforcement Learning

arXiv:2606.05523v1 Announce Type: new Abstract: Despite advances in safety alignment, prompt-rewriting attacks such as persona modulation, fictional framing and persuasion-based reformulation, can bypass safety filters even on frontier models. Existing defenses either rely on non-scalable human curation or white-box optimisation that overfits to specific model internals, leaving aligned models brittle against the very class of adaptive black-box adversaries they will face in deployment. To address this gap, we introduce CHASE (Co-evolutionary Hardening through Adversarial Safety-Escalation),…

QueryAgent-R1: Bridging Query Generation and Product Retrieval for E-Commerce Query Recommendation

arXiv:2606.05671v1 Announce Type: new Abstract: Query recommendation in e-commerce search aims to proactively suggest queries that match users' potential interests. However, existing methods mainly optimize query-level relevance, while neglecting whether the retrieved products align with users' downstream preferences. This mismatch often leads to high query click through rates (CTR) but low product conversion rates (CVR). To bridge this gap, we propose QueryAgent-R1, a memory-augmented agentic framework that improves end-to-end alignment via chain-of-retrieval optimization. Our QueryAgent-R1…

Towards Truly Multilingual ASR: Generalizing Code-Switching ASR to Unseen Language Pairs

arXiv:2606.05846v1 Announce Type: cross Abstract: Automatic Speech Recognition (ASR) has become a key technology for human--AI interaction. However, code-switching ASR (CS-ASR) remains particularly challenging due to the severe scarcity of multilingual CS speech resources across diverse language pairs. Existing approaches primarily improve CS-ASR performance through synthetic CS speech generation or pair-specific fine-tuning on limited bilingual datasets. Nevertheless, these approaches face an inherent scalability limitation, as support for CS must be developed separately for language pairs w…

Improving Heart-Focused Medical Question Answering in LLMs via Variance-Aware Rubric Rewards with GRPO

arXiv:2606.05174v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown strong promise in healthcare applications. Yet deploying general-purpose models in real-world settings remains difficult due to data privacy constraints, inference costs, and limited suitability for edge or on-device use. These challenges motivate the development of smaller, more efficient models that require robust post-training strategies to ensure reliable medical reasoning. In this work, we investigate Group Relative Policy Optimization (GRPO) for post-training LLMs on heart-focused medical question an…

Representation Learning Enables Scalable Multitask Deep Reinforcement Learning

arXiv:2606.05555v1 Announce Type: new Abstract: Scaling reinforcement learning (RL) to diverse multitask settings remains a central challenge. While recent advances in model-based RL achieve strong performance, they rely on planning and complex training pipelines, making it unclear which components are essential for scalability. We revisit this question and argue that the primary driver of scalable multitask RL is not model-based control, but \emph{representation learning}. In particular, we show that combining predictive, model-based representations with high-capacity value function approxim…

Policy-Compliant Cloud Storage Systems

arXiv:2606.05423v1 Announce Type: new Abstract: Privacy regulations such as the General Data Protection Regulation (GDPR) impose strict requirements on how personal data is stored, processed, and audited. While key-value stores (KVS) are widely used in latency-sensitive applications, their simple data model and untrusted cloud deployment environments make GDPR compliance particularly challenging. Existing approaches require invasive code modifications, impose high performance overheads, or overlook the integrity of compliance mechanisms themselves. This paper presents GDPRuler, a trusted midd…

CASS-RTL: Correctness-Aware Subspace Steering for RTL Generation with LLMs

arXiv:2606.05680v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have enabled the automatic synthesis (generation) of register-transfer level (RTL) code from natural language instructions, offering a promising pathway to accelerate chip design. Unlike typical natural language (and software coding) tasks, LLM-based RTL code generation demands strict cycle accuracy with concurrency, where minor logical errors can render a circuit unusable or insecure. While prior work has explored hallucination mitigation via external verification, self-evaluation prompts, retri…

Towards One-to-Many Temporal Grounding

arXiv:2606.06294v1 Announce Type: new Abstract: Temporal Grounding (TG) aims to localize video segments corresponding to a textual query. Prior research predominantly focuses on single-segment retrieval. Real-world scenarios, however, often require localizing multiple disjoint segments for a single query -- a setting we term One-to-Many Temporal Grounding (OMTG). Previous state-of-the-art MLLMs, optimized for one-to-one settings, struggle in this context, often yielding near-zero scores due to a lack of event cardinality perception. To bridge this gap, we present a systematic solution with th…

Pushing the limits of unconstrained machine-learned interatomic potentials

arXiv:2601.16195v3 Announce Type: replace-cross Abstract: Machine-learned interatomic potentials (MLIPs) are increasingly used to replace computationally demanding electronic-structure calculations to model matter at the atomic scale. The most commonly used model architectures are constrained to fulfill a number of physical laws exactly, from geometric symmetries to energy conservation. Evidence is mounting that relaxing some of these constraints can be beneficial to the efficiency and (somewhat surprisingly) accuracy of MLIPs, even though care should be taken to avoid qualitative failures as…

ACE-SQL: Adaptive Co-Optimization via Empirical Credit Assignment for Text-to-SQL

arXiv:2606.05906v1 Announce Type: new Abstract: Text-to-SQL maps natural language questions to executable SQL queries. Modern databases often contain large and complex schemas, making schema linking a critical step for accurate SQL generation. Existing methods either rely on full-schema generation, which leaves schema linking implicit within a large search space, or use a separate retriever trained with static gold-column supervision, whose targets may be suboptimal for the current generator policy. To address this issue, we propose Adaptive Co-optimization via Empirical Credit Assignment for…

When Surface Form Changes Moderation Decisions: A Paired Study of Code-Mixed Workflow Instability

arXiv:2606.05654v1 Announce Type: cross Abstract: Hate moderation is often evaluated as classification on clean English inputs, but deployed systems must route content to actions such as ALLOW, FLAG, or REVIEW. We study how this workflow changes under code-mixed inputs using a paired evaluation setting where the same underlying content is expressed as clean English and Tamil-English code-mix. Under thresholds tuned on clean English development data, code-mixed inputs produce substantial action instability, with a paired clean- to-code-mix decision flip rate of 0.265. The main workflow effects…

Accuracy Limits of Causal Trees for Individualized Treatment Effects

arXiv:2509.11381v3 Announce Type: replace-cross Abstract: Recursive decision trees are widely used to estimate heterogeneous causal treatment effects in experimental and observational studies. These methods are typically implemented using CART-type recursive partitioning, with splitting criteria designed to identify variation in treatment effects across covariate-defined subgroups. We study causal tree estimators based on adaptive recursive partitioning and establish lower bounds on their estimation accuracy. The class we analyze includes versions with and without sample splitting, based on c…

FlowPRO: Reward-Free Reinforced Fine-Tuning of Flow-Matching VLAs via Proximalized Preference Optimization

arXiv:2606.05468v1 Announce Type: new Abstract: Post-training Vision-Language-Action (VLA) models into policies that can be reliably deployed on real robots remains a major bottleneck. SFT and DAgger exploit failure signals only indirectly, and reward-based RL is bottlenecked by the difficulty of real-world reward design and of training reliable critics. We present FlowPRO, a reward-free offline reinforced fine-tuning framework for flow-matching VLAs. Algorithmically, we propose RPRO (Robotic Flow-matching Proximalized Preference Optimization), a preference-optimization objective tailored to…

GCD: Garbled, Corrected, Demonstrandum -- Fixing and Proving Go's Extended GCD Implementation

arXiv:2606.05796v1 Announce Type: new Abstract: We verify the 'extendedGCD' implementation in Go's standard library ('crypto/internal/fips140/bigmod'), which plays a crucial role in the generation of RSA key pairs. Even though the Go implementation is supposedly a direct port from BoringSSL's implementation, we uncovered two deviations that each break the algorithm's invariants: (1) the Go implementation deviates in the way coefficients are updated, and (2) it permits a larger input domain. We address both deviations; the first by fixing the Go implementation, which results in an on average 2…

Large Language Models are Perplexed by some Political Parties

arXiv:2606.05937v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used, including in political applications, but their political fairness has been little studied. We assess it using perplexity, posing that a fair model should give equal probability to all political groups. However, we find, across ten LLMs and three datasets covering 37 languages, that LLMs are more perplexed by the texts of far right and nationalist parties than of social-democratic parties. We find this to be consistent with previous work on translation fairness, to the point that perplexity corr…

Asuka-Bench: Benchmarking Code Agents on Underspecified User Intent and Multi-Round Refinement

arXiv:2606.05920v1 Announce Type: cross Abstract: Existing code-generation benchmarks score a single mapping from a complete prompt to a one-shot output. However, real web development is different. Users seldom write a full spec at the start; many requirements only become clear once they look at an intermediate result and react to it. We present Asuka-Bench, a benchmark that pairs underspecified user intent with multi-round refinement, grounded in browser-rendered behavior. Each task is resolved through a closed loop: a Code Agent generates a web project, a UI Agent executes test cases on the…

Step-adaptive multimodal fusion network with multi-scale cloud feature learning for ultra-short-term solar irradiance forecasting

arXiv:2606.06102v1 Announce Type: cross Abstract: Ultra-short-term solar irradiance prediction is critical for photovoltaic system dispatch and power grid stability. Existing approaches suffer from three key shortcomings: single time-series models cannot capture the spatial dynamics of clouds under complex conditions, standard convolutions inadequately represent multi-scale cloud features, and fixed low-frequency compensation strategies fail to adapt to different prediction steps. To address these issues, this proposes a multi-source data fusion model for ultra-short-term irradiance predictio…

World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis

arXiv:2606.05979v1 Announce Type: new Abstract: We propose world-language-action (WLA) models as a new class of embodied foundation models. WLA takes textual instructions, images, and robot states as inputs to jointly predict textual subtasks, subgoal images, and robot actions, conjoining the \emph{world modeling interface} to learn from extensive egocentric videos as in the world-action model (WAM) and the \emph{language reasoning} capacities to solve complex long-horizon tasks as in vision-language-action (VLA) models. At the core of WLA lies an \emph{autoregressive (AR)} Transformer backbo…

Toward Scalable and Valid Conditional Independence Testing with Spectral Representations

arXiv:2512.19510v2 Announce Type: replace-cross Abstract: Conditional independence (CI) is central to causal inference, feature selection, and graphical modeling, yet it is untestable in many settings without additional assumptions. Existing CI tests often rely on restrictive structural conditions, limiting their validity. Kernel methods using partial covariance operators offer a more principled approach but suffer from limited adaptivity and scalability. In this work, we explore whether representation learning can help address these limitations. Specifically, we focus on representations deri…

Convex Estimation of Gaussian Graphical Regression Models with Covariates

arXiv:2410.06326v3 Announce Type: replace-cross Abstract: Gaussian graphical models (GGMs) are widely used to recover the conditional independence structure among random variables. Recent work has sought to incorporate auxiliary covariates to improve estimation, particularly in applications such as co-expression quantitative trait locus (eQTL) studies, where both gene expression levels and their conditional dependence structure may be influenced by genetic variants. Existing approaches to covariate-adjusted GGMs either restrict covariate effects to the mean structure or lead to nonconvex form…

PyCC.id: A package for hypothesis-driven equation discovery with structural identifiability

arXiv:2606.05191v1 Announce Type: new Abstract: Data-driven equation discovery is fundamentally an inverse problem that seeks to infer the governing differential equations of a system directly from time-series measurements. A known issue is the ill-conditioned nature of the inverse problem, which frequently produces multiple mathematical models that fit the data similarly well. One path to address this issue is by incorporating known hypotheses and constraints into the training phase beforehand. While this approach effectively reduces the search space, it still results in multiple candidate m…

OPRD: On-Policy Representation Distillation

arXiv:2606.06021v1 Announce Type: new Abstract: On-policy distillation (OPD) supervises the student only in output space by matching next-token probabilities. This output-only paradigm has two limits: (1) sampling variance from Monte Carlo KL estimates over large vocabularies (e.g., Qwen's ~150k tokens) persists throughout training, and (2) it treats the teacher as a black-box, discarding all intermediate hidden states after the LM head. We propose On-Policy Representation Distillation (OPRD), which lifts distillation into hidden-state space by aligning student and teacher representations acr…

ComplexityMT: Benchmarking the Interaction Between Text Complexity and Machine Translation

arXiv:2606.05421v1 Announce Type: new Abstract: When a text is translated, does the translation retain the complexity of the original? We introduce ComplexityMT, a new challenge for assessing how text complexity and machine translation interact with and influence each other, using the Common European Framework of Reference for Languages (CEFR) levels as the measure of text complexity. Across six languages, including Arabic, Dutch, English, French, Hindi, and Russian, we evaluate three open-weight models, one closed model, and a commercial machine translation system on two tasks: i) correlatio…

A Differentiable Framework for Full and Phaseless Data Inversion Using Neural Implicit Contrast-Source Representation

arXiv:2508.10555v2 Announce Type: replace-cross Abstract: In this study, we extend the contrast source inversion to a fully differentiable, unsupervised framework based on a neural implicit representation of the contrast source. Specifically, instead of a pixel-wise discrete representation, the contrast source is parameterized by a lightweight residual multilayer perceptron (ResMLP) as a continuous neural field conditioned on spatial coordinates and transmitter settings. This continuous parameterization provides a more flexible representation of the contrast source and improves reconstruction…

Noise-Adaptive Regularization for Robust Multi-Label Remote Sensing Image Classification

arXiv:2601.08446v2 Announce Type: replace-cross Abstract: The development of reliable methods for multi-label classification (MLC) has become a prominent research direction in remote sensing (RS). As the scale of RS data continues to expand, annotation procedures increasingly rely on thematic products or crowdsourced procedures to reduce the cost of manual annotation. While cost-effective, these strategies often introduce multi-label noise in the form of partially incorrect annotations. In MLC, label noise arises as additive noise, subtractive noise, or a combination of both in the form of mi…

Staying with the Uncertainty: Uncertainty-Scaffolding Strategies for Artificial Moral Advisors in LLM-to-LLM Simulated Conversations

arXiv:2606.05890v1 Announce Type: new Abstract: LLMs are increasingly deployed as Artificial Moral Advisors (AMA) in a variety of contexts: what kind of conversational patterns should they display? In this paper, we study how AMA can help their interlocutors "stay with the uncertainty". We propose three modes of uncertainty (Perspective-Multiplying, Tension-Preserving, Process-Reflecting) and compare them against three control conditions (Baseline, Persuasive, Sycophantic). A user-agent LLM engages in a dialogue on an ethical dilemma with an AMA following a specific uncertainty strategy, and…