news

Dec 01, 2025 Selected as an Anthropic AI Research Fellow.
May 13, 2025 ArXiv release + open-sourcing of Measuring General Intelligence with Generated Games (GG-Bench framework).
May 01, 2025 ICML 2025 acceptance — Improving LLM Safety Alignment with Dual-Objective Optimization (Poster).
Apr 24, 2025 ICRA 2025 Best Paper Award Finalist for Robot LearningRobo-DM: Data Management For Large Robot Datasets.
Jan 27, 2025 ICRA 2025 acceptance — Robo-DM: Data Management For Large Robot Datasets.
Jan 22, 2025 NAACL 2025 acceptance — Stronger Universal & Transfer Attacks by Suppressing Refusals.
Oct 12, 2024 NeurIPS SafeGenAI Workshop 2024 acceptance — Stronger Universal & Transfer Attacks by Suppressing Refusals.
Jan 16, 2024 ICLR 2024 acceptance — Defending Against Transfer Attacks from Public Models.

News & Updates

  • Jan 16, 2024: ICLR 2024 acceptance — Defending Against Transfer Attacks from Public Models
  • Oct 12, 2024: NeurIPS SafeGenAI Workshop 2024 acceptance — Stronger Universal & Transfer Attacks by Suppressing Refusals
  • Jan 22, 2025: NAACL 2025 acceptance — Stronger Universal & Transfer Attacks by Suppressing Refusals
  • Jan 27, 2025: ICRA 2025 acceptance — Robo-DM: Data Management For Large Robot Datasets
  • Apr 24, 2025: ICRA 2025 Best Paper Award Finalist for Robot Learning — Robo-DM
  • May 1, 2025: ICML 2025 acceptance — Improving LLM Safety Alignment with Dual-Objective Optimization (Poster)
  • May 13, 2025: ArXiv release + open-sourcing of Measuring General Intelligence with Generated Games (GG-Bench framework)
  • Dec 2025: Selected as an Anthropic AI Research Fellow (~32 out of 2000+). </ul>