Conditional Equivalence of DPO and RLHF: Implicit Assumption, Failure Modes, and Provable Alignment Paper • 2605.20834 • Published 2 days ago • 3
CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence Paper • 2605.12882 • Published 9 days ago • 260
Watch Before You Answer: Learning from Visually Grounded Post-Training Paper • 2604.05117 • Published Apr 6 • 36
Adam's Law: Textual Frequency Law on Large Language Models Paper • 2604.02176 • Published Apr 2 • 503
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning Paper • 2604.02721 • Published Apr 3 • 629
CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence Paper • 2603.28032 • Published Mar 30 • 342
Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models Paper • 2603.25750 • Published Mar 20 • 36
Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization Paper • 2603.28342 • Published Mar 30 • 26
InCoder-32B: Code Foundation Model for Industrial Scenarios Paper • 2603.16790 • Published Mar 17 • 311
Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning Paper • 2603.04597 • Published Mar 4 • 210
DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval Paper • 2603.04743 • Published Mar 5 • 53
From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models Paper • 2602.22859 • Published Feb 26 • 151
Less is Enough: Synthesizing Diverse Data in Feature Space of LLMs Paper • 2602.10388 • Published Feb 11 • 244
TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents Paper • 2602.07274 • Published Feb 6 • 210