Yuhao Zhou

Deploying Models to Non-participating Clients in Federated Learning without Fine-tuning: A Hypernetwork-based Approach

EarthSE: A Benchmark Evaluating Earth Scientific Exploration Capability for Large Language Models

VeriWeb: Verifiable Long-Chain Web Benchmark for Agentic Information-Seeking

DD-Ranking: Rethinking the Evaluation of Dataset Distillation

Learning Locally, Revising Globally: Global Reviser for Federated Learning with Noisy Labels

Data Efficient Any Transformer-to-Mamba Distillation via Attention Bridge

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training

Towards Personalized Parameter Generation via Data-Conditioned Mapping

InternAgent-DR: Advancing deep research with dynamic structured knowledge flow

MSEarth: A Multimodal Scientific Dataset and Benchmark for Phenomena Uncovering in Earth Science

OFS: Overlapped Feature Synthesis for Communication-Efficient Federated Learning

ResearchGPT: Benchmarking and Training LLMs for End-to-End Computer Science Research Workflows

Make Optimization Once and for All with Fine-grained Guidance

Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights

Pruning-Robust Mamba with Asymmetric Multi-Scale Scanning Paths

REPA Works Until It Doesn’t: Early-Stopped, Holistic Alignment Supercharges Diffusion Training