Junho Kim

Junho Kim on Hugging Face Daily Papers: 6 papers, 0 in the top 3 of their day, 41 upvotes.

1. GRASP: Learning to Ground Social Reasoning in Multi-Person Non-Verbal Interactions 3 upvotes, #41 of 2026-05-19
2. Narrative-Driven Paper-to-Slide Generation via ArcDeck 7 upvotes, #22 of 2026-04-16
3. STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understanding 11 upvotes, #22 of 2026-03-31
4. ReFoCUS: Reinforcement-guided Frame Optimization for Contextual Understanding 3 upvotes, #35 of 2025-06-04
5. Look Every Frame All at Once: Video-Ma^2mba for Efficient Long-form Video Understanding with Multi-Axis Gradient Checkpointing 10 upvotes, #12 of 2024-12-02
6. SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis 5 upvotes, #13 of 2024-11-27

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.