arXiv:2605.25346v1 Announce Type: cross Abstract: Neural network (NN) dynamics models and control policies achieve strong performance in robotics, but providing sound guarantees under uncertainty remains difficult, especially for closed-loop NN systems. Existing reachability tools provide formal over-approximations, yet are often non-differentiable, overly conservative, or too slow for modern learning and online planning pipelines. To address […]
Specification-Based Code-Text-Code Reengineering for LLM-Mediated Software Evolution
arXiv:2605.25232v1 Announce Type: cross Abstract: Direct Code2Code transformation remains challenging to control because it can preserve surface-level syntax while introducing semantic drift, hidden behavioral changes, loss of traceability, non-idiomatic target implementations, or incomplete reconstruction of domain logic. This paper proposes a specification-based Code2Text2Code reengineering framework for LLM-mediated software evolution. The central idea is to transform […]
Learning Protein Structure-Function Relationships through Knowledge-guided Representation Decomposition
arXiv:2605.23960v1 Announce Type: new Abstract: Proteins encode diverse functions within complex three-dimensional structures, yet most deep learning representations remain highly entangled, obscuring the biophysical signals that underlie function. Here we introduce ProtDiS, a knowledge-guided framework that decomposes pretrained protein micro-environment embeddings into biologically grounded and task-relevant dimensions. Inspired by the information bottleneck principle, ProtDiS learns […]
Latent Q-Barrier Shielding for Safe In-Context Reinforcement Learning
arXiv:2605.25267v1 Announce Type: cross Abstract: Safe in-context reinforcement learning (ICRL) adapts online from interaction history without test-time parameter updates while controlling episode cost under a safety budget. Under out-of-distribution (OOD) deployment shifts, pretraining-only safe ICRL can give poor reward-safety tradeoffs because the remaining budget affects behavior only through frozen policy conditioning, not an explicit action-level […]
Binding Visual Features Point by Point
arXiv:2605.25427v1 Announce Type: cross Abstract: Despite success on standard benchmarks, vision language models display persistent failures on tasks involving processing of multi-object scenes, including many tasks that are relatively easy for humans. Recent work has found that these failures may stem from a basic inability to accurately bind object features in-context, a challenge that is […]
How Few-Shot Examples Add Up: A Causal Decomposition of Function Vectors in In-Context Learning
arXiv:2605.16591v2 Announce Type: replace-cross Abstract: In-context learning (ICL) excels at new tasks from minimal examples, yet we still lack a mechanistic explanation of how few-shot prompts shape a model’s function vector (FV)–a causal activation direction that drives task behavior on the ICL query. Across tasks and models, an $n$-shot FV is well-approximated by a linear […]
From Muscle Bursts to Motor Intent: Self-Supervised Token Modeling for Heterogeneous EMG
arXiv:2605.03462v3 Announce Type: replace-cross Abstract: Surface electromyography provides a practical way to infer human movement intention from wearable muscle recordings, but models trained under a single acquisition setting often lose reliability when the user, session, electrode layout, or gesture protocol changes. This paper proposes AEMG, a self-supervised learning approach designed to extract reusable neuromuscular representations […]
Multi-Objective Learning for Diffusion Models: A Statistical Theory under Semi-Supervised Learning
arXiv:2605.25210v1 Announce Type: cross Abstract: Diffusion models are increasingly used as powerful conditional generators, yet real deployments often involve multiple target distributions arising from different tasks, e.g., diverse prompt domains in text-to-image generation, or multiple environments in robotics with diffusion policies. This naturally leads to a multi-objective learning (MOL) problem. A key challenge is that […]
Hide to Guide: Learning via Semantic Masking
arXiv:2605.25198v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a powerful paradigm for improving language models on reasoning-intensive tasks, but its effectiveness is often limited by exploration. For example, models often fail on hard problems, leaving little useful reward signal. External expert traces offer a natural source of guidance, yet they […]
TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting
arXiv:2605.22365v2 Announce Type: replace-cross Abstract: Time Series Forecasting (TSF) is highly vulnerable to backdoor attacks, yet effective defenses remain underexplored due to challenges arising from data entanglement and shifts in task formulation. To fill this gap, we conduct a systematic evaluation of thirteen representative backdoor defenses across the TSF life cycle and analyze their failure […]
EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models
arXiv:2605.25477v1 Announce Type: cross Abstract: The ability to efficiently and reliably learn new tasks has been a foundational challenge in robotics. Vision-Language-Action (VLA) models have demonstrated strong generalization across diverse manipulation tasks, yet pretrained policies consistently fall short of the reliability required for real-world deployment. Reinforcement learning (RL) fine-tuning offers a promising path to bridge […]
Frequency Matters: Fast Model-Agnostic Data Curation for Pruning and Quantization
arXiv:2603.16105v3 Announce Type: replace-cross Abstract: Post-training model compression is essential for enhancing the portability of Large Language Models (LLMs) while preserving their performance. While several compression approaches have been proposed, less emphasis has been placed on selecting the most suitable set of data (the so-called emphcalibration data) for finding the compressed model configuration. The choice […]