Kangsan Kim

Kangsan Kim on Hugging Face Daily Papers: 8 papers, 2 in the top 3 of their day, 302 upvotes.

1. Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents 38 upvotes, #10 of 2026-05-28
2. It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs 30 upvotes, #10 of 2026-05-21
3. Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents 29 upvotes, #5 of 2026-04-16
4. MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents 28 upvotes, #6 of 2026-03-12
5. WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning 22 upvotes, #14 of 2025-12-03
6. UniversalRAG: Retrieval-Augmented Generation over Multiple Corpora with Diverse Modalities and Granularities 60 upvotes, #3 of 2025-04-30
7. VideoRAG: Retrieval-Augmented Generation over Video Corpus 65 upvotes, #2 of 2025-01-13
8. VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding 22 upvotes, #6 of 2024-12-05

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.