Rui Yang

The paper introduces ReCAP, a native GUI agent that significantly improves CAPTCHA solving success (from 30% to 80%) by integrating specialized CAPTCHA capabilities into a general-purpose, end-to-end vision-language model.

This paper introduces ComicJailbreak, a new benchmark demonstrating that structured visual narratives can effectively jailbreak Multimodal Large Language Models (MLLMs), requiring new safety alignment methods.

PRO-CUA introduces a process-reward optimization framework that enables efficient, step-level reinforcement learning for training computer use agents by decoupling environment interaction from policy optimization.

PRO-CUA introduces a process-reward optimization framework that enables efficient, step-level reinforcement learning for training computer use agents by decoupling environment interaction from policy optimization.

LoopFM proposes a novel framework to significantly improve knowledge distillation for recommendation systems by structuring the rich intermediate embeddings of large foundation models as input features, thereby overcoming the limitations of single-scalar prediction transfer.

LoopFM proposes a novel framework to significantly improve knowledge distillation for recommendation systems by structuring the rich intermediate embeddings of large foundation models as input features, thereby overcoming the limitations of single-scalar prediction transfer.

The paper introduces OpenWebRL, an open framework that enables training visual web agents using online multi-turn Reinforcement Learning directly on live websites, achieving state-of-the-art performance on challenging web benchmarks.

The paper introduces OpenWebRL, an open framework that enables training visual web agents using online multi-turn Reinforcement Learning directly on live websites, achieving state-of-the-art performance on challenging web benchmarks.

Integrates FOA into Omni LLMs for spatial audio understanding

This paper proposes a standardized task specification language and rulebook for EEG datasets to enable reusable and auditable benchmarking infrastructure.

This paper provides a comprehensive review of audio editing in the era of foundation models, including a unified taxonomy of existing editing tasks and major foundation-model paradigms.

This paper presents SkillGate, a security gateway that screens AI skill packages for malicious behavior before installation.