When Does Correction Become Repair? Mechanistic Auditing of Internal Interventions in Tool-Using LLMs Paper • 2609.36138 • Published 6 days ago • 6
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF Image-Text-to-Text • 177B • Updated 5 days ago • 1.89M • 528
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Paper • 2609.19969 • Published 17 days ago • 215
Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening Paper • 2609.18708 • Published 18 days ago • 84