Picture for Liang Zheng

Liang Zheng

REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers

Add code
Apr 14, 2025
Viaarxiv icon

R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents

Add code
Apr 09, 2025
Viaarxiv icon

ARINAR: Bi-Level Autoregressive Feature-by-Feature Generative Models

Add code
Mar 04, 2025
Viaarxiv icon

Think on your feet: Seamless Transition between Human-like Locomotion in Response to Changing Commands

Add code
Feb 26, 2025
Viaarxiv icon

Learning Camera Movement Control from Real-World Drone Videos

Add code
Dec 12, 2024
Figure 1 for Learning Camera Movement Control from Real-World Drone Videos
Figure 2 for Learning Camera Movement Control from Real-World Drone Videos
Figure 3 for Learning Camera Movement Control from Real-World Drone Videos
Figure 4 for Learning Camera Movement Control from Real-World Drone Videos
Viaarxiv icon

Negative Token Merging: Image-based Adversarial Feature Guidance

Add code
Dec 02, 2024
Figure 1 for Negative Token Merging: Image-based Adversarial Feature Guidance
Figure 2 for Negative Token Merging: Image-based Adversarial Feature Guidance
Figure 3 for Negative Token Merging: Image-based Adversarial Feature Guidance
Figure 4 for Negative Token Merging: Image-based Adversarial Feature Guidance
Viaarxiv icon

Can We Predict Performance of Large Models across Vision-Language Tasks?

Add code
Oct 14, 2024
Viaarxiv icon

Vec2Face: Scaling Face Dataset Generation with Loosely Constrained Vectors

Add code
Sep 04, 2024
Viaarxiv icon

Perceive, Reflect, and Plan: Designing LLM Agent for Goal-Directed City Navigation without Instructions

Add code
Aug 08, 2024
Figure 1 for Perceive, Reflect, and Plan: Designing LLM Agent for Goal-Directed City Navigation without Instructions
Figure 2 for Perceive, Reflect, and Plan: Designing LLM Agent for Goal-Directed City Navigation without Instructions
Figure 3 for Perceive, Reflect, and Plan: Designing LLM Agent for Goal-Directed City Navigation without Instructions
Figure 4 for Perceive, Reflect, and Plan: Designing LLM Agent for Goal-Directed City Navigation without Instructions
Viaarxiv icon

The NING Humanoid: The Concurrent Design and Development of a Dynamic and Agile Platform

Add code
Aug 02, 2024
Figure 1 for The NING Humanoid: The Concurrent Design and Development of a Dynamic and Agile Platform
Figure 2 for The NING Humanoid: The Concurrent Design and Development of a Dynamic and Agile Platform
Figure 3 for The NING Humanoid: The Concurrent Design and Development of a Dynamic and Agile Platform
Figure 4 for The NING Humanoid: The Concurrent Design and Development of a Dynamic and Agile Platform
Viaarxiv icon