Xinjie Shen
News
Research updates, releases, and talks.
- Released Shortcuts & Boundaries, on verifiable RL misalignment and contextual safety learning. Read the interactive blog.
- Released SEAD, a state-based framework for attack and defense in tool-using agents. Project · Code and data.
- Released VHD-Play, a Qwen technical report on generating verifiable agentic RL environments from solved mechanisms. I also wrote about how we iterated on its teaser figure.
- Qwen3.8-Max-Preview reached No. 1 on NVIDIA’s FlashInfer-Bench during our kernel-optimization work. Our longer real-world self-improvement runs exceeded 60 hours and 10,000 tool calls. Read the report.
- Gave an invited talk at Tsinghua University PI Lab on physical-world privacy awareness in LLMs and VLM agents.
- Released E-Commerce Bench, a 365-day benchmark for long-horizon autonomous business operation.
- Gave the Jiangmen / TechBeat talk Distributed Hidden Malice: Attacks and Defenses, connecting CKA-Agent attacks with TurnGate defenses for multi-turn dialogue.
- How Far Are VLMs from Privacy Awareness in the Physical World? was accepted to NeurIPS 2026. Paper.
- The Trojan Knowledge was accepted to ICML 2026.
- Our behavioral study of overreliance on conversational language models was accepted to CHI 2026. Paper.
- Our physical-world privacy benchmark was accepted to ICLR 2026. Paper | Code and data.
- We open-sourced RD-Agent for automatic data-centric R&D.
- I received Microsoft Research Asia’s Star of Tomorrow award.