Picture for Yong Zhang

Yong Zhang

Beijing University of Technology

CASP: Compression of Large Multimodal Models Based on Attention Sparsity

Add code
Mar 07, 2025
Viaarxiv icon

DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models

Add code
Mar 04, 2025
Viaarxiv icon

Mobius: Text to Seamless Looping Video Generation via Latent Shift

Add code
Feb 27, 2025
Viaarxiv icon

PhenoProfiler: Advancing Phenotypic Learning for Image-based Drug Discovery

Add code
Feb 26, 2025
Viaarxiv icon

Self-Enhanced Reasoning Training: Activating Latent Reasoning in Small Models for Enhanced Reasoning Distillation

Add code
Feb 18, 2025
Viaarxiv icon

An Analysis Framework for Understanding Deep Neural Networks Based on Network Dynamics

Add code
Jan 05, 2025
Figure 1 for An Analysis Framework for Understanding Deep Neural Networks Based on Network Dynamics
Figure 2 for An Analysis Framework for Understanding Deep Neural Networks Based on Network Dynamics
Figure 3 for An Analysis Framework for Understanding Deep Neural Networks Based on Network Dynamics
Figure 4 for An Analysis Framework for Understanding Deep Neural Networks Based on Network Dynamics
Viaarxiv icon

Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models

Add code
Jan 02, 2025
Viaarxiv icon

Rethinking Layer Removal: Preserving Critical Components with Task-Aware Singular Value Decomposition

Add code
Dec 31, 2024
Viaarxiv icon

VideoMaker: Zero-shot Customized Video Generation with the Inherent Force of Video Diffusion Models

Add code
Dec 27, 2024
Viaarxiv icon

DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation

Add code
Dec 24, 2024
Viaarxiv icon