Picture for Deng Cai

Deng Cai

SeqPE: Transformer with Sequential Position Encoding

Add code
Jun 16, 2025
Viaarxiv icon

GeoCAD: Local Geometry-Controllable CAD Generation

Add code
Jun 12, 2025
Viaarxiv icon

Any-to-Bokeh: One-Step Video Bokeh via Multi-Plane Image Guided Diffusion

Add code
May 27, 2025
Viaarxiv icon

Self-Reasoning Language Models: Unfold Hidden Reasoning Chains with Few Reasoning Catalyst

Add code
May 20, 2025
Viaarxiv icon

InfiniteICL: Breaking the Limit of Context Window Size via Long Short-term Memory Transformation

Add code
Apr 03, 2025
Viaarxiv icon

MagicID: Hybrid Preference Optimization for ID-Consistent and Dynamic-Preserved Video Customization

Add code
Mar 16, 2025
Viaarxiv icon

GCA-3D: Towards Generalized and Consistent Domain Adaptation of 3D Generators

Add code
Dec 20, 2024
Viaarxiv icon

PersonalVideo: High ID-Fidelity Video Customization without Dynamic and Semantic Degradation

Add code
Nov 26, 2024
Viaarxiv icon

Delving into the Reversal Curse: How Far Can Large Language Models Generalize?

Add code
Oct 24, 2024
Figure 1 for Delving into the Reversal Curse: How Far Can Large Language Models Generalize?
Figure 2 for Delving into the Reversal Curse: How Far Can Large Language Models Generalize?
Figure 3 for Delving into the Reversal Curse: How Far Can Large Language Models Generalize?
Figure 4 for Delving into the Reversal Curse: How Far Can Large Language Models Generalize?
Viaarxiv icon

A Survey on the Honesty of Large Language Models

Add code
Sep 27, 2024
Figure 1 for A Survey on the Honesty of Large Language Models
Figure 2 for A Survey on the Honesty of Large Language Models
Figure 3 for A Survey on the Honesty of Large Language Models
Figure 4 for A Survey on the Honesty of Large Language Models
Viaarxiv icon