Fanhua Shang

Full Professor@Tianjin University·中国·OpenReview

研究方向

Large Model Fine-Tuning · Multimodal Large Language Models · Image and Vision Recovery · federated learning · Deep Learning · stochastic optimization · sparse and Low-rank reconvery

5.0

iLLaVA: An Image is Worth Fewer Than 1/3 Input Tokens in Large Multimodal Models

ICLR 2026Poster

三作

4.5

FedMuon: Accelerating Federated Learning with Matrix Orthogonalization

ICLR 2026Withdrawn

二作

4.5

Parameter-Free Variance Reduced Zeroth-Order Optimization for Non-Convex Problems

ICLR 2026Rejected

三作

4.0

LAVA: A UNIFIED FRAMEWORK FOR FINETUNING LANGUAGE AND VISION MODELS

ICLR 2026Rejected

二作

3.3

SADUNs: Sharpness-Aware Deep Unfolding Networks for Image Restoration

ICLR 2026Rejected

二作

7.0

Tight High-Probability Bounds for Nonconvex Heavy-Tailed Scenario under Weaker Assumptions

NeurIPS 2025Poster

三作

6.8

QBasicVSR: Temporal Awareness Adaptation Quantization for Video Super-Resolution

NeurIPS 2025Poster

二作

5.5

Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging

合作者 (17)