SearchJev: A Fast and Calibrated System-1 Model for Search Agents Paper • 2610.05107 • Published 6 days ago • 23
When Does Correction Become Repair? Mechanistic Auditing of Internal Interventions in Tool-Using LLMs Paper • 2609.36138 • Published 12 days ago • 7
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF Image-Text-to-Text • 177B • Updated 10 days ago • 3.56M • 732
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Paper • 2609.19969 • Published 23 days ago • 227
Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening Paper • 2609.18708 • Published 24 days ago • 84