Picture for Jieping Ye

Jieping Ye

University of Michigan, DiDi Chuxing

Grounding 3D Object Affordance with Language Instructions, Visual Observations and Interactions

Add code
Apr 07, 2025
Viaarxiv icon

Improving Complex Reasoning with Dynamic Prompt Corruption: A soft prompt Optimization Approach

Add code
Mar 17, 2025
Viaarxiv icon

Don't Take Things Out of Context: Attention Intervention for Enhancing Chain-of-Thought Reasoning in Large Language Models

Add code
Mar 14, 2025
Viaarxiv icon

A Generalist Cross-Domain Molecular Learning Framework for Structure-Based Drug Discovery

Add code
Mar 06, 2025
Viaarxiv icon

Advancing vision-language models in front-end development via data synthesis

Add code
Mar 03, 2025
Viaarxiv icon

No Parameters, No Problem: 3D Gaussian Splatting without Camera Intrinsics and Extrinsics

Add code
Feb 27, 2025
Viaarxiv icon

PTZ-Calib: Robust Pan-Tilt-Zoom Camera Calibration

Add code
Feb 13, 2025
Viaarxiv icon

CoL3D: Collaborative Learning of Single-view Depth and Camera Intrinsics for Metric 3D Shape Recovery

Add code
Feb 13, 2025
Viaarxiv icon

GENERator: A Long-Context Generative Genomic Foundation Model

Add code
Feb 11, 2025
Viaarxiv icon

Not Every Patch is Needed: Towards a More Efficient and Effective Backbone for Video-based Person Re-identification

Add code
Jan 28, 2025
Figure 1 for Not Every Patch is Needed: Towards a More Efficient and Effective Backbone for Video-based Person Re-identification
Figure 2 for Not Every Patch is Needed: Towards a More Efficient and Effective Backbone for Video-based Person Re-identification
Figure 3 for Not Every Patch is Needed: Towards a More Efficient and Effective Backbone for Video-based Person Re-identification
Figure 4 for Not Every Patch is Needed: Towards a More Efficient and Effective Backbone for Video-based Person Re-identification
Viaarxiv icon