Megadose AI progress, ranked and analyzed.

Context-Matched Distillation: Teacher Causality for Autoregressive Video Distillation

· HF Daily Papers ·
The paper’s core claim is that video distillation works better when the teacher sees only the same past context the student had at generation time.

CMD replaces full-clip, bidirectional teacher scoring with a causal teacher that cannot use future frames or controls. It also scores targets against the student-generated prefix that actually led to them, then perturbs weak early prefixes to stabilize training. The authors report state-of-the-art aggregate results among autoregressive methods on short- and long-video benchmarks, plus stronger adherence to changing camera controls. HF Daily Papers' note

score 5

Categories: Research