Picture for Zhangyang Wang

Zhangyang Wang

Atlas

Foundation Models for Logistics: Toward Certifiable, Conversational Planning Interfaces

Add code
Jul 15, 2025
Viaarxiv icon

Martian World Models: Controllable Video Synthesis with Physically Accurate 3D Reconstructions

Add code
Jul 10, 2025
Viaarxiv icon

LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning

Add code
Jun 18, 2025
Viaarxiv icon

Demystifying the Visual Quality Paradox in Multimodal Large Language Models

Add code
Jun 18, 2025
Viaarxiv icon

On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention

Add code
Jun 12, 2025
Viaarxiv icon

CXR-LT 2024: A MICCAI challenge on long-tailed, multi-label, and zero-shot disease classification from chest X-ray

Add code
Jun 09, 2025
Viaarxiv icon

Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models

Add code
Jun 09, 2025
Viaarxiv icon

HALoS: Hierarchical Asynchronous Local SGD over Slow Networks for Geo-Distributed Large Language Model Training

Add code
Jun 05, 2025
Viaarxiv icon

FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting

Add code
Jun 04, 2025
Viaarxiv icon

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Add code
May 26, 2025
Viaarxiv icon