Video-R1 uses temporal-aware RL and mixed datasets to boost video reasoning in MLLMs, with a 7B model reaching 37.1% on VSI-Bench and surpassing GPT-4o.
Keypoint- based progressive chain-of-thought distillation for llms
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
DEAR identifies decision tokens via entropy and evidence tokens via cosine similarity plus divergence to improve on-policy reasoning distillation over standard methods.
Reasoning in large output spaces proceeds via shortlisting then fine-grained reasoning; this characterization enables a mechanistic distillation strategy that outperforms standard distillation.
citing papers explorer
-
Video-R1: Reinforcing Video Reasoning in MLLMs
Video-R1 uses temporal-aware RL and mixed datasets to boost video reasoning in MLLMs, with a 7B model reaching 37.1% on VSI-Bench and surpassing GPT-4o.
-
Finding the Evidence: Discovering Decision-Supporting Tokens for On-Policy Reasoning Distillation
DEAR identifies decision tokens via entropy and evidence tokens via cosine similarity plus divergence to improve on-policy reasoning distillation over standard methods.
-
Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces
Reasoning in large output spaces proceeds via shortlisting then fine-grained reasoning; this characterization enables a mechanistic distillation strategy that outperforms standard distillation.