Mismatch Matters: On-Policy Distillation Beyond Token Agreement Paper • 2608.09836 • Published 3 days ago • 5
messimanda/vbench2_videos_motion_refined_multi_teacher_opd_ckpt500_ema Viewer • Updated about 21 hours ago • 3.86k
messimanda/vbench2_videos_connector_pullback_motion_refined_opd_ckpt250_ema Viewer • Updated about 22 hours ago • 3.63k
messimanda/vbench2_videos_connector_pullback_motion_refined_opd_ckpt250_ema Viewer • Updated about 22 hours ago • 3.63k
messimanda/vbench2_videos_motion_refined_multi_teacher_opd_ckpt500_ema Viewer • Updated about 21 hours ago • 3.86k
DLM-Scope Collection Sparse Autoencoders of Diffusion Language Models (Dream-7B, LLaDA-8B) and Large Language Models (Qwen-2.5-7B, LLaMA-3-8B) • 6 items • Updated Feb 5 • 8