Jiangchao Yao

30

Papers

76

Total Citations

Papers (30)

ReMamber: Referring Image Segmentation with Mamba Twister

On Harmonizing Implicit Subpopulations

From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?

Multi-modal Medical Diagnosis via Large-small Model Collaboration

Learning to Instruct for Visual Instruction Tuning

NeurIPS 2025arXiv

Differential-informed Sample Selection Accelerates Multimodal Contrastive Learning

Fast and Accurate Blind Flexible Docking

Long-tailed Recognition with Model Rebalancing

4DGCPro: Efficient Hierarchical 4D Gaussian Compression for Progressive Volumetric Video Streaming

NeurIPS 2025arXiv

CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration

Diversified Batch Selection for Training Acceleration

Federated Domain Generalization With Generalization Adjustment

Class-Balancing Diffusion Models

LamRA: Large Multimodal Model as Your Advanced Retrieval Assistant

RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical Diagnosis

MetaNeRV: Meta Neural Representations for Videos with Spatial-Temporal Guidance

Large Language Models Enhanced Personalized Graph Neural Architecture Search in Federated Learning

Low-Rank Knowledge Decomposition for Medical Foundation Models

Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning

Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization

Unraveling the Impact of Heterophilic Structures on Graph Positive-Unlabeled Learning

Mitigating Label Noise on Graphs via Topological Sample Selection

Exploring Training on Heterogeneous Data with Mixture of Low-rank Adapters

Masking: A New Perspective of Noisy Supervision

Combating Representation Learning Disparity with Geometric Harmonization

Combating Bilateral Edge Noise for Robust Link Prediction

Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolation

Federated Learning with Bilateral Curation for Partially Class-Disjoint Data

Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation

How does Disagreement Help Generalization against Label Corruption?