yangsui

yangsui on Hugging Face Daily Papers: 5 papers, 2 in the top 3 of their day, 191 upvotes.

1. HoliTom: Holistic Token Merging for Fast Video Large Language Models 18 upvotes, #24 of 2025-05-28
2. 70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float 17 upvotes, #12 of 2025-04-18
3. Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models 23 upvotes, #15 of 2025-03-21
4. Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models 62 upvotes, #3 of 2025-03-21
5. BitsFusion: 1.99 bits Weight Quantization of Diffusion Model 34 upvotes, #2 of 2024-06-07

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.