Deqing Fu

Deqing Fu on Hugging Face Daily Papers: 13 papers, 0 in the top 3 of their day, 166 upvotes.

1. TabFM-Auto: Self-Evolving Pipelines for Tabular Foundation Models 11 upvotes, #51 of 2026-09-30
2. TabFM: A Zero-Shot Foundation Model for Tabular Data 20 upvotes, #45 of 2026-09-30
3. Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift 6 upvotes, #26 of 2026-07-21
4. Value-Aware Stochastic KV Cache Eviction for Reasoning Models 8 upvotes, #26 of 2026-06-03
5. Convergent Evolution: How Different Language Models Learn Similar Number Representations 7 upvotes, #16 of 2026-04-23
6. Are LLM Decisions Faithful to Verbal Confidence? 3 upvotes, #21 of 2026-01-13
7. When Do Transformers Learn Heuristics for Graph Connectivity? 2 upvotes, #34 of 2025-10-23
8. Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning 32 upvotes, #6 of 2025-07-23
9. Resa: Transparent Reasoning Models via SAEs 20 upvotes, #14 of 2025-06-13
10. Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models 1 upvotes, #66 of 2025-05-27
11. FoNE: Precise Single-Token Number Embeddings via Fourier Features 11 upvotes, #10 of 2025-02-17
12. VisualLens: Personalization through Visual History 15 upvotes, #13 of 2024-11-26
13. TLDR: Token-Level Detective Reward Model for Large Vision Language Models 15 upvotes, #9 of 2024-10-08

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.