arXiv Machine Learning
Jul 3
DecompRL: Solving Harder Problems by Learning Modular Code Generation
arXiv:2607. 02390v1 Announce Type: new Abstract: How can Large Language Models (LLMs) solve problems they currently cannot?
Reinforcement learning
Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv AI
Jul 3
Rank-Then-Act: Reward-Free Control from Frame-Order Progress
arXiv:2607. 01897v1 Announce Type: cross Abstract: We introduce Rank-Then-Act (RTA), a framework for learning control policies from expert video demonstrations without environment rewards.
arXiv Machine Learning
Jul 3
Class-Grouped Normalized Momentum and Faster Hyperparameter Exploration to Tackle Class Imbalance in Federated Learning
arXiv:2607. 01474v1 Announce Type: new Abstract: Class imbalance poses a critical challenge in federated learning (FL), where underrepresented classes suffer from poor predictive performance yet cannot be addressed by standard centralized techniques due to privacy and heterogeneity constraints.
arXiv AI
Jul 3
Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning
arXiv:2604. 02091v2 Announce Type: replace-cross Abstract: Rerankers play a pivotal role in refining retrieval results for Retrieval-Augmented Generation.
arXiv Machine Learning
Jul 3
Cross-Platform Control for Autonomous Surface Vehicles via Adaptive Reinforcement Learning
arXiv:2607. 02037v1 Announce Type: cross Abstract: Autonomous surface vehicles vary widely in hydrodynamic and actuation characteristics, yet most controllers are designed for single-platform deployment.
arXiv AI
Jul 3
Token Geometry
arXiv:2607. 01455v1 Announce Type: cross Abstract: Language models learn continuous programs over discrete symbols, with the embedding table and LM-head acting as the read/write interface between them.
arXiv AI
Jul 3
ART for Diffusion Sampling: Continuous-Time Control and Actor-Critic Learning
arXiv:2607. 02137v1 Announce Type: cross Abstract: We study timestep allocation for score-based diffusion sampling, where a learned reverse-time dynamics is discretized on a finite grid.
arXiv AI
Jul 3
Working Paper: Towards a Category-theoretic Comparative Framework for Artificial General Intelligence
arXiv:2603. 28906v4 Announce Type: replace Abstract: AGI has become the Holly Grail of AI with the promise of level intelligence and the major Tech companies around the world are investing unprecedented amounts of resources in its pursuit.
arXiv AI
Jul 3
MAGIK: Mapping to Analogous Goals via Imagination-enabled Knowledge Transfer
arXiv:2506. 01623v4 Announce Type: replace Abstract: Humans excel at analogical reasoning - applying knowledge from one task to a related one with minimal relearning.
arXiv AI
Jul 3
Scaling with Confidence: Calibrating Confidence of LLMs for Adaptive Test Time Scaling
arXiv:2607. 01612v1 Announce Type: new Abstract: Training large language models (LLMs) with reinforcement learning (RL) has significantly advanced their performance on reasoning and question-answering tasks.
arXiv Machine Learning
Jul 3
Composite Reward Design in PPO-Driven Adaptive Filtering
arXiv:2506. 06323v2 Announce Type: replace-cross Abstract: Model-free and reinforcement learning-based adaptive filtering methods are gaining traction for denoising in dynamic, non-stationary environments such as wireless signal channels, biomedical monitoring, and sensor networks.
arXiv AI
Jul 3
Learning-based Multi-agent Race Strategies in Formula 1
arXiv:2602. 23056v2 Announce Type: replace Abstract: In Formula 1, race strategies are adapted according to evolving race conditions and competitors' actions.
arXiv AI
Jul 3
Don't Let Gains FADE: Breaking Down Policy Gradient Weights in RL
arXiv:2607. 01490v1 Announce Type: cross Abstract: Reinforcement learning post-training dramatically improves LLM reasoning, but suffers from training instability and diversity collapse.
arXiv Machine Learning
Jul 3
Optimizing Visual Generative Models via Distribution-wise Rewards
arXiv:2607. 02291v1 Announce Type: new Abstract: Conventional reinforcement learning strategies for visual generation typically employ sample-wise reward functions, yet this practice frequently results in reward hacking that degrades image diversity and introduces visual anomalies.
arXiv AI
Jul 3
Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation
arXiv:2607. 02460v1 Announce Type: cross Abstract: Post-training large language models (LLMs) without real-world interaction feedback or human-labeled supervision remains challenging, particularly in specialized domains where expert annotations are costly to obtain.
arXiv AI
Jul 3
Lightweight Safe Reinforcement Learning for End-to-End UAV Navigation
arXiv:2607. 01794v1 Announce Type: cross Abstract: With the rapid development of autonomous aerial systems, Unmanned Aerial Vehicles (UAVs) are increasingly deployed in applications such as inspection, environmental monitoring, and rescue, creating growing demand for reliable autonomous navigation.
arXiv AI
Jul 3
Breaking Safety at the Token Boundary: How BPE Tokenization Creates Exploitable Gaps in LLM Alignment
arXiv:2607. 01239v1 Announce Type: cross Abstract: Character-level perturbations bypass safety alignment in modern LLMs despite leaving prompts human-readable.
arXiv AI
Jul 3
Enhancing Fitness Intelligence through Domain-Specific LLM Post-Training
arXiv:2607. 02118v1 Announce Type: new Abstract: Scientific Fitness Coaching (SFC) is typically delivered by human professionals, making it costly and inaccessible to many.
arXiv AI
Jul 3
Generalization in offline RL: The structure is more important than the amount of pessimism
arXiv:2607. 02288v1 Announce Type: cross Abstract: While pessimism counteracts overestimation bias in offline reinforcement learning (RL), being overly conservative has been associated with hindering certain forms of generalization.
arXiv AI
Jul 3
CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation
arXiv:2603. 22435v2 Announce Type: replace-cross Abstract: "Code-as-Policy" considers how executable code can complement data-intensive Vision-Language-Action (VLA) methods, yet their effectiveness as autonomous controllers for embodied manipulation remains underexplored.