Huang

Huang on Hugging Face Daily Papers: 10 papers, 5 in the top 3 of their day, 378 upvotes.

1. VideoLoop: Looped Working Memory Against Semantic Thrashing in Long-Form Video Agents 11 upvotes, #51 of 2026-09-30
2. SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning 59 upvotes, #3 of 2026-03-25
3. SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models 242 upvotes, #3 of 2026-03-18
4. A Survey on Latent Reasoning 78 upvotes, #2 of 2025-07-09
5. OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation 52 upvotes, #8 of 2025-05-28
6. QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehension 4 upvotes, #32 of 2025-03-12
7. Identity-Preserving Text-to-Video Generation by Frequency Decomposition 30 upvotes, #3 of 2024-11-28
8. Autoregressive Models in Vision: A Survey 13 upvotes, #9 of 2024-11-12
9. ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation 37 upvotes, #3 of 2024-06-27
10. MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators 19 upvotes, #7 of 2024-04-09

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.