Rethinking Token Reweighting for SFT: Suppress, Reverse, and Extrapolate Learned Features Paper • 2609.33463 • Published 14 days ago • 12
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF Image-Text-to-Text • 117B • Updated 11 days ago • 651k • 367
Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling Paper • 2609.19499 • Published 25 days ago • 37
Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout Paper • 2609.09123 • Published Sep 8 • 55