collaborators

6 papers

cs.AI2026

MCPEvol-Bench: Benchmarking LLM Agent Performance Across Dynamic Evolutions of MCP Servers

Huanxi Liu, Kun Hu, Jiaqi Liao +6

The paper introduces MCPEvol-Bench, a benchmark that tests how well large language model agents adapt to changing tool interfaces and functionalities in Model Context Protocol (MCP…

cs.CV2026

Learning Fine-Grained Geometry for Sparse-View Splatting via Cascade Depth Loss

Wenjun Lu, Haodong Chen, Anqi Yi +4

Novel view synthesis is a fundamental task in 3D computer vision that aims to reconstruct photorealistic images from novel viewpoints given a set of posed images. However, reconstr…

cs.CV2026

DuoCast: Duo-Probabilistic Diffusion for Precipitation Nowcasting

Penghui Wen, Mengwei He, Patrick Filippi +5

Accurate short-term precipitation forecasting is critical for weather-sensitive decision-making in agriculture, transportation, and disaster response. Existing deep learning approa…

cs.LG2026

Charting Empirical Laws for LLM Fine-Tuning in Scientific Multi-Discipline Learning

Lintao Wang, Zhuqiang Lu, Yilin Zhu +6

While large language models (LLMs) have achieved strong performance through fine-tuning within individual scientific domains, their learning dynamics in multi-disciplinary contexts…

cs.CL2026

Benchmark^2: Systematic Evaluation of LLM Benchmarks

Qi Qian, Chengsong Huang, Jingwen Xu +13

The rapid proliferation of benchmarks for evaluating large language models (LLMs) has created an urgent need for systematic methods to assess benchmark quality itself. We propose B…

cs.CV2025

B-VLLM: A Vision Large Language Model with Balanced Spatio-Temporal Tokens

Zhuqiang Lu, Zhenfei Yin, Mengwei He +4

Recently, Vision Large Language Models (VLLMs) integrated with vision encoders have shown promising performance in vision understanding. The key of VLLMs is to encode visual conten…