π_RL: Online RL Fine-tuning for Flow-based Vision-Language-Action Models Paper • 2510.25889 • Published 9 days ago • 58
INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats Paper • 2510.25602 • Published 9 days ago • 63
OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows Paper • 2510.24411 • Published 10 days ago • 70
DeepAgent: A General Reasoning Agent with Scalable Toolsets Paper • 2510.21618 • Published 14 days ago • 92
Towards Mixed-Modal Retrieval for Universal Retrieval-Augmented Generation Paper • 2510.17354 • Published 18 days ago • 33
ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping Paper • 2510.08457 • Published 29 days ago • 12
SpaceVista: All-Scale Visual Spatial Reasoning from mm to km Paper • 2510.09606 • Published 28 days ago • 17
MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization Paper • 2510.08540 • Published 29 days ago • 108
SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer Paper • 2509.24695 • Published Sep 29 • 44
Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference Learning Paper • 2509.23285 • Published Sep 27 • 13
Euclid's Gift: Enhancing Spatial Perception and Reasoning in Vision-Language Models via Geometric Surrogate Tasks Paper • 2509.24473 • Published Sep 29 • 16