Picture for Hao Sun

Hao Sun

LLMs for Generalizable Language-Conditioned Policy Learning under Minimal Data Requirements

Add code
Dec 09, 2024
Viaarxiv icon

Constructing optimal treatment length strategies to maximize quality-adjusted lifetimes

Add code
Dec 06, 2024
Viaarxiv icon

Detailed Object Description with Controllable Dimensions

Add code
Nov 28, 2024
Viaarxiv icon

StreamAdapter: Efficient Test Time Adaptation from Contextual Streams

Add code
Nov 14, 2024
Viaarxiv icon

Over-parameterized Student Model via Tensor Decomposition Boosted Knowledge Distillation

Add code
Nov 10, 2024
Viaarxiv icon

Rethinking Bradley-Terry Models in Preference-Based Reward Modeling: Foundations, Theory, and Alternatives

Add code
Nov 07, 2024
Viaarxiv icon

Token-level Proximal Policy Optimization for Query Generation

Add code
Nov 01, 2024
Viaarxiv icon

High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented Transformer

Add code
Oct 30, 2024
Viaarxiv icon

P$^2$C$^2$Net: PDE-Preserved Coarse Correction Network for efficient prediction of spatiotemporal dynamics

Add code
Oct 29, 2024
Figure 1 for P$^2$C$^2$Net: PDE-Preserved Coarse Correction Network for efficient prediction of spatiotemporal dynamics
Figure 2 for P$^2$C$^2$Net: PDE-Preserved Coarse Correction Network for efficient prediction of spatiotemporal dynamics
Figure 3 for P$^2$C$^2$Net: PDE-Preserved Coarse Correction Network for efficient prediction of spatiotemporal dynamics
Figure 4 for P$^2$C$^2$Net: PDE-Preserved Coarse Correction Network for efficient prediction of spatiotemporal dynamics
Viaarxiv icon

Cross-model Control: Improving Multiple Large Language Models in One-time Training

Add code
Oct 23, 2024
Figure 1 for Cross-model Control: Improving Multiple Large Language Models in One-time Training
Figure 2 for Cross-model Control: Improving Multiple Large Language Models in One-time Training
Figure 3 for Cross-model Control: Improving Multiple Large Language Models in One-time Training
Figure 4 for Cross-model Control: Improving Multiple Large Language Models in One-time Training
Viaarxiv icon