OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning Paper • 2610.12458 • Published 6 days ago • 16
SearchJev: A Fast and Calibrated System-1 Model for Search Agents Paper • 2610.05107 • Published 10 days ago • 26
When Does Correction Become Repair? Mechanistic Auditing of Internal Interventions in Tool-Using LLMs Paper • 2609.36138 • Published 16 days ago • 7
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Paper • 2609.19969 • Published 27 days ago • 229
Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening Paper • 2609.18708 • Published 28 days ago • 84