Gang Wang

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.

The paper introduces CoT-Guard, a small, cost-effective 4B-parameter model that significantly outperforms large, expensive monitors like GPT-5 in detecting hidden objectives in code generation tasks.

SCARA is a novel, end-to-end framework that autonomously connects binary-level vulnerability candidates to conditionally validated remedies for opaque industrial software, achieving high precision and success rates on a specialized benchmark.

The paper introduces CCLab, an adversarial testing framework, to systematically evaluate the robustness of both learning-based and traditional congestion controllers, finding that learning-based controllers are generally more robust and can be further improved using adversarial traces.

OctoT2I introduces a self-evolving, agentic routing framework that efficiently selects and combines multiple Text-to-Image models, achieving high performance while significantly boosting inference speed and energy efficiency.

This paper proposes a four-layer technical architecture for large model inference optimization, including Multi-model Fusion, Model Optimization, Compute-Model Fusion, and Compute-Network-Model Fusion.

Researchers investigated the impact of cognitive heuristics on Large Language Models in code vulnerability detection, finding all models susceptible with highest susceptibility to framing.

This paper proposes VisTCP, a visualization framework for structured representation of Traditional Chinese Paintings using a TCP-oriented intelligent model and expert knowledge.