Skip to content
View yjyddq's full-sized avatar
20 followers · 6 following

Achievements

Achievement: Starstruckx2

Achievements

Achievement: Starstruckx2

Highlights

  • Pro

Block or report yjyddq

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
yjyddq/README.md

Hi, I'm Jingyi Yang

1st. Ph.D. student at Fudan University & Shanghai AI Lab. My current research interests includes: Computer-Use, AI Agents, Reinforcement Learning, and Diffusion Large Language Models. Homepage · Google Scholar · [email protected]

Highlights

  • WildClawBench: Hard, practical, end-to-end evaluation for AI agents — in the wild.
    Project · Code · GitHub Repo stars

  • DARE: Diffusion Large Language Models Alignment and Reinforcement Executor.
    Code · GitHub Repo stars

  • [NeurIPS 2025] RiOSWorld: Benchmarking the risk of multimodal computer-use agents.
    Project · Code · GitHub Repo stars

  • [ICLR 2026] Your agent may misevolve: Emergent risks in self-evolving llm agents.
    Code · GitHub Repo stars

Pinned Loading

  1. RiOSWorld RiOSWorld Public

    [NeurIPS 2025] Official repository of RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents

    HTML 118 6

  2. DARE DARE Public

    Official repository of DARE: Diffusion Large Language Models Alignment and Reinforcement Executor

    Python 167 3

  3. EOSER-ASS-RL EOSER-ASS-RL Public

    Official Repository of "Taming Masked Diffusion Language Models via Consistency Trajectory Reinforcement Learning with Fewer Decoding Step"

    Python 27 1

  4. WildClawBench WildClawBench Public

    Forked from InternLM/WildClawBench

    An in-the-wild benchmark for AI agents in the OpenClaw Environment.

    Python

  5. DADM DADM Public

    [ICCV 2025] Official implementation of DADM: Dual Alignment of Domain and Modality for Face Anti-spoofing

    Python 9

  6. Tencent/WeDLM Tencent/WeDLM Public

    WeDLM: The fastest diffusion language model with standard causal attention and native KV cache compatibility, delivering real speedups over vLLM-optimized baselines.

    Python 638 43