OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning Paper • 2603.08655 • Published about 13 hours ago
Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders Paper • 2603.06569 • Published 3 days ago • 82
Reasoning Models Struggle to Control their Chains of Thought Paper • 2603.05706 • Published 4 days ago • 23
FlashPrefill: Instantaneous Pattern Discovery and Thresholding for Ultra-Fast Long-Context Prefilling Paper • 2603.06199 • Published 4 days ago • 9
UltraDexGrasp: Learning Universal Dexterous Grasping for Bimanual Robots with Synthetic Data Paper • 2603.05312 • Published 5 days ago • 7
RealWonder: Real-Time Physical Action-Conditioned Video Generation Paper • 2603.05449 • Published 5 days ago • 9
Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling Paper • 2603.04791 • Published 5 days ago • 14
SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration Paper • 2603.03823 • Published 6 days ago • 4
Proact-VL: A Proactive VideoLLM for Real-Time AI Companions Paper • 2603.03447 • Published 6 days ago • 25
Code2Math: Can Your Code Agent Effectively Evolve Math Problems Through Exploration? Paper • 2603.03202 • Published 7 days ago • 17