A Framework for Scalable Heterogeneous Multi-Agent Adversarial Reinforcement Learning in IsaacLab. arxiv.org/abs/2510.01264

RLP: Reinforcement as a Pretraining Objective. arxiv.org/abs/2510.01265

Safe Reinforcement Learning-Based Vibration Control: Overcoming Training Risks with LQR Guidance. arxiv.org/abs/2510.01269

Identifying Information-Transfer Nodes in a Recurrent Neural Network Reveals Dynamic Representations. arxiv.org/abs/2510.01271

Noisy-Pair Robust Representation Alignment for Positive-Unlabeled Learning. arxiv.org/abs/2510.01278

Microsaccade-Inspired Probing: Positional Encoding Perturbations Reveal LLM Misbehaviours. arxiv.org/abs/2510.01288

ThinKV: Thought-Adaptive KV Cache Compression for Efficient Reasoning Models. arxiv.org/abs/2510.01290

Network-Level Vehicle Delay Estimation at Heterogeneous Signalized Intersections. arxiv.org/abs/2510.01292

Extreme value forecasting using relevance-based data augmentation with deep learning models. arxiv.org/abs/2510.02407

OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data. arxiv.org/abs/2510.02410

RainSeer: Fine-Grained Rainfall Reconstruction via Physics-Guided Modeling. arxiv.org/abs/2510.02414

How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models. arxiv.org/abs/2510.02453

Market-Based Data Subset Selection -- Principled Aggregation of Multi-Criteria Example Utility. arxiv.org/abs/2510.02456

Assessing the Potential for Catastrophic Failure in Dynamic Post-Training Quantization. arxiv.org/abs/2510.02457

SAGE: Streaming Agreement-Driven Gradient Sketches for Representative Subset Selection. arxiv.org/abs/2510.02470

Litespark Technical Report: High-Throughput, Energy-Efficient LLM Training Framework. arxiv.org/abs/2510.02483

From Pixels to Factors: Learning Independently Controllable State Variables for Reinforcement Learning. arxiv.org/abs/2510.02484

Improved Robustness of Deep Reinforcement Learning for Control of Time-Varying Systems by Bounded Extremum Seeking. arxiv.org/abs/2510.02490

Beyond Imitation: Recovering Dense Rewards from Demonstrations. arxiv.org/abs/2510.02493

Graph Generation with Spectral Geodesic Flow Matching. arxiv.org/abs/2510.02520