Yuqing Yang

SMILE: Self-Explainable Multimodal Information Bottleneck for Medical Diagnosis

Yuqing Yang, Alexander Schmatz, Zhaozhao Ma, et al.

From Noisy Traces to Root Causes: Structural Trajectory Analysis and Causal Extraction for Agent Optimization

Ying Chang, Jiahang Xu, Xuan Feng, et al.

When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors

Yuqing Yang, Qi Zhu, Zhen Han, et al.

MM-WebAgent: A Hierarchical Multimodal Web Agent for Webpage Generation

Yan Li, Zezi Zeng, Yifan Yang, et al.

AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation

Ziwei Zhou, Zeyuan Lai, Rui Wang, et al.

Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?

Jeonghye Kim, Xufang Luo, Minbeom Kim, et al.

SortedRL: Accelerating RL Training for LLMs through Online Length-Aware Scheduling

Yiqi Zhang, Huiqiang Jiang, Xufang Luo, et al.

Act While Thinking: Accelerating LLM Agents via Pattern-Aware Speculative Tool Execution

Yifan Sui, Han Zhao, Rui Ma, et al.

This paper addresses the slowness of AI agents (LLMs that use external tools) by proposing PASTE, a method that predicts and executes likely future tool calls before the LLM finishes thinking. By recognizing that agents tend to follow recurring patterns of tool usage, PASTE can execute tools speculatively while the LLM is still processing, hiding wait times and achieving 48.5% faster task completion.