Taki WU

Taki WU on Hugging Face Daily Papers: 10 papers, 2 in the top 3 of their day, 257 upvotes.

1. Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation 75 upvotes, #4 of 2026-04-14
2. The Art of Efficient Reasoning: Data, Reward, and Optimization 6 upvotes, #15 of 2026-02-25
3. BPDQ: Bit-Plane Decomposition Quantization on a Variable Grid for Large Language Models 9 upvotes, #13 of 2026-02-16
4. ProFit: Leveraging High-Value Signals in SFT via Probability-Guided Token Selection 15 upvotes, #13 of 2026-01-19
5. MMFormalizer: Multimodal Autoformalization in the Wild 102 upvotes, #2 of 2026-01-12
6. Revisiting Model Interpolation for Efficient Reasoning 8 upvotes, #22 of 2025-10-16
7. PhyX: Does Your Model Have the "Wits" for Physical Reasoning? 47 upvotes, #7 of 2025-05-26
8. Autoregressive Models in Vision: A Survey 13 upvotes, #9 of 2024-11-12
9. A Survey on the Honesty of Large Language Models 28 upvotes, #3 of 2024-09-30
10. Mixture-of-Subspaces in Low-Rank Adaptation 3 upvotes, #30 of 2024-06-19

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.