Taiwei Shi

Taiwei Shi on Hugging Face Daily Papers: 8 papers, 2 in the top 3 of their day, 221 upvotes.

1. The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents 24 upvotes, #9 of 2026-04-15
2. Video-Based Reward Modeling for Computer-Use Agents 41 upvotes, #4 of 2026-03-13
3. Experiential Reinforcement Learning 66 upvotes, #1 of 2026-02-17
4. CoAct-1: Computer-using Agents with Coding as Actions 13 upvotes, #10 of 2025-08-08
5. The Hallucination Tax of Reinforcement Finetuning 8 upvotes, #26 of 2025-05-21
6. Efficient Reinforcement Finetuning via Adaptive Curriculum Learning 9 upvotes, #14 of 2025-04-09
7. Discovering Knowledge Deficiencies of Language Models on Massive Knowledge Base 6 upvotes, #26 of 2025-04-02
8. On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective 44 upvotes, #2 of 2025-02-20

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.