Picture for Hangjie Yuan

Hangjie Yuan

MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems

Add code
Mar 19, 2025
Viaarxiv icon

DreamRelation: Relation-Centric Video Customization

Add code
Mar 10, 2025
Viaarxiv icon

Frequency Autoregressive Image Generation with Continuous Tokens

Add code
Mar 07, 2025
Viaarxiv icon

Generative Artificial Intelligence in Robotic Manipulation: A Survey

Add code
Mar 05, 2025
Viaarxiv icon

ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think

Add code
Jan 03, 2025
Figure 1 for ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think
Figure 2 for ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think
Figure 3 for ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think
Figure 4 for ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think
Viaarxiv icon

FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion

Add code
Dec 12, 2024
Figure 1 for FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion
Figure 2 for FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion
Figure 3 for FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion
Figure 4 for FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion
Viaarxiv icon

DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion Control

Add code
Oct 17, 2024
Figure 1 for DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion Control
Figure 2 for DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion Control
Figure 3 for DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion Control
Figure 4 for DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion Control
Viaarxiv icon

EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models

Add code
Oct 10, 2024
Figure 1 for EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models
Figure 2 for EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models
Figure 3 for EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models
Figure 4 for EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models
Viaarxiv icon

FreeMask: Rethinking the Importance of Attention Masks for Zero-Shot Video Editing

Add code
Sep 30, 2024
Figure 1 for FreeMask: Rethinking the Importance of Attention Masks for Zero-Shot Video Editing
Figure 2 for FreeMask: Rethinking the Importance of Attention Masks for Zero-Shot Video Editing
Figure 3 for FreeMask: Rethinking the Importance of Attention Masks for Zero-Shot Video Editing
Figure 4 for FreeMask: Rethinking the Importance of Attention Masks for Zero-Shot Video Editing
Viaarxiv icon

PAPM: A Physics-aware Proxy Model for Process Systems

Add code
Jul 07, 2024
Figure 1 for PAPM: A Physics-aware Proxy Model for Process Systems
Figure 2 for PAPM: A Physics-aware Proxy Model for Process Systems
Figure 3 for PAPM: A Physics-aware Proxy Model for Process Systems
Figure 4 for PAPM: A Physics-aware Proxy Model for Process Systems
Viaarxiv icon