News
Paper acceptances, awards, talks, and lab milestones.
2026
16 items- award
🎉 We received a Microsoft AI and the New Future of Work grant. Thank you, Microsoft!
- team
🎓 Congrats to Taiwei Shi for passing his PhD defense. Wish you all the best, Dr. Shi!
- paper
📑 Efficient Reinforcement Finetuning via Adaptive Curriculum Learning is accepted to TMLR 2026.
- paper
📑 Video-Based Reward Modeling for Computer-Use Agents is accepted to ECCV 2026.
- paper
ProMediate accepted to ACL 2026 Findings.
- paper
Data attribution paper for filtering unsafe training data accepted to ICML 2026.
- paper
ICLR 2026 accepted: CoAct-1, Doxing via the Lens, and TrustGen.
- release
ERL code is now available — play with it.
- paper
New paper out: Video-Based Reward Modeling for Computer-Use Agents.
- team
Welcomed Jiaqi Deng to the group.
- paper
Two papers at EACL: "What's Missing in Vision-Language Models?" (Causal Order Reasoning) and GRAVITY.
- team
Reopened the open office hour. 🍋🟩
- paper
New paper out: Experiential Reinforcement Learning.
- team
Ziyi passed her PhD qualifying exam.
- award
Received the OORI Research Catalyst Program Award.
- paper
WildFeedback accepted to ACL 2026 main.