Lin Zhang

17

Papers

57

Total Citations

Papers (17)

GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control

DeRS: Towards Extremely Efficient Upcycled Mixture-of-Experts Models

Towards Audio-Visual Navigation in Noisy Environments: A Large-Scale Benchmark Dataset and an Architecture Considering Multiple Sound-Sources

SC-Captioner: Improving Image Captioning with Self-Correction by Reinforcement Learning

Representing Sounds as Neural Amplitude Fields: A Benchmark of Coordinate-MLPs and a Fourier Kolmogorov-Arnold Framework

OSDFace: One-Step Diffusion Model for Face Restoration

BigMac: A Communication-Efficient Mixture-of-Experts Model Structure for Fast Training and Inference

Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation

Learning From Temporal Gradient for Semi-Supervised Action Recognition

Self-Augmented Unpaired Image Dehazing via Density and Depth Decomposition

Fine-Tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning

MAP: Multimodal Uncertainty-Aware Vision-Language Pre-Training Model

Federated Learning for Non-IID Data via Unified Feature Learning and Optimization Objective Alignment

MT-ORL: Multi-Task Occlusion Relationship Learning

LMR: A Large-Scale Multi-Reference Dataset for Reference-Based Super-Resolution

RRSR:Reciprocal Reference-Based Image Super-Resolution with Progressive Feature Alignment and Selection

Exact Shape Correspondence via 2D graph convolution