From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models Paper • 2602.22859 • Published 1 day ago • 141
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training Paper • 2602.10693 • Published 16 days ago • 185
SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise Paper • 2602.12783 • Published 14 days ago • 146
Less is Enough: Synthesizing Diverse Data in Feature Space of LLMs Paper • 2602.10388 • Published 17 days ago • 234
TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents Paper • 2602.07274 • Published 21 days ago • 204