Tao Huang

22

Papers

247

Total Citations

Papers (22)

SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference

Diffusion Reward: Learning Rewards via Conditional Video Diffusion

Training-free Composite Scene Generation for Layout-to-Image Synthesis

Learning Mask Invariant Mutual Information for Masked Image Modeling

A Unified Framework for Industrial Cel-Animation Colorization with Temporal-Structural Awareness

GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scene

EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba

Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learning

FreeKD: Knowledge Distillation via Semantic Frequency Prompt

GreedyNAS: Towards Fast One-Shot NAS With Greedy Supernet

Neighbor2Neighbor: Self-Supervised Denoising From Single Noisy Images

Prioritized Architecture Sampling With Monto-Carlo Tree Search

Deep Gaussian Scale Mixture Prior for Spectral Compressive Imaging

DyRep: Bootstrapping Training With Dynamic Re-Parameterization

GreedyNASv2: Greedier Search With a Greedy Path Filter

Low-Light Image Enhancement with Multi-Stage Residue Quantization and Brightness-Aware Attention

MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders

Parameterized Blur Kernel Prior Learning for Local Motion Deblurring

Gain from Neighbors: Boosting Model Robustness in the Wild via Adversarial Perturbations Toward Neighboring Classes

SAM Encoder Breach by Adversarial Simplicial Complex Triggers Downstream Model Failures

Knowledge Distillation from A Stronger Teacher

Knowledge Diffusion for Distillation