Wei Huang

21

Papers

133

Total Citations

Papers (21)

VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection

Mixture Compressor for Mixture-of-Experts LLMs Gains More

TIME-FS: Joint Learning of Tensorial Incomplete Multi-View Unsupervised Feature Selection and Missing-View Imputation

DiffSal: Joint Audio and Video Learning for Diffusion Saliency Prediction

On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent

GaRe: Relightable 3D Gaussian Splatting for Outdoor Scenes from Unconstrained Photo Collections

Representation Enhancement-Stabilization: Reducing Bias-Variance of Domain Generalization

Projection Pursuit Density Ratio Estimation

Understanding the Forgetting of (Replay-based) Continual Learning via Feature Learning: Angle Matters

Decision SpikeFormer: Spike-Driven Transformer for Decision Making

Towards Unsupervised Training of Matching-based Graph Edit Distance Solver via Preference-aware GAN

Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression

BiLLM: Pushing the Limit of Post-Training Quantization for LLMs

NLPrompt: Noise-Label Prompt Learning for Vision-Language Models

Breaking Data Silos in Parkinson’s Disease Diagnosis: An Adaptive Federated Learning Approach for Privacy-Preserving Facial Expression Analysis

GapMatch: Bridging Instance and Model Perturbations for Enhanced Semi-Supervised Medical Image Segmentation

Earthfarsser: Versatile Spatio-Temporal Dynamical Systems Modeling in One Model

Learning Large-Factor EM Image Super-Resolution with Generative Priors

Global and Local Prompts Cooperation via Optimal Transport for Federated Learning

Diffusion Models Demand Contrastive Guidance for Adversarial Purification to Advance

Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples