Picture for Tong Zhang

Tong Zhang

Nanjing University of Science and Technology, Nanjing, China

Coherent and Multi-modality Image Inpainting via Latent Space Optimization

Add code
Jul 10, 2024
Figure 1 for Coherent and Multi-modality Image Inpainting via Latent Space Optimization
Figure 2 for Coherent and Multi-modality Image Inpainting via Latent Space Optimization
Figure 3 for Coherent and Multi-modality Image Inpainting via Latent Space Optimization
Figure 4 for Coherent and Multi-modality Image Inpainting via Latent Space Optimization
Viaarxiv icon

Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning

Add code
Jul 10, 2024
Viaarxiv icon

TheoremLlama: Transforming General-Purpose LLMs into Lean4 Experts

Add code
Jul 03, 2024
Viaarxiv icon

ScaleBiO: Scalable Bilevel Optimization for LLM Data Reweighting

Add code
Jun 28, 2024
Figure 1 for ScaleBiO: Scalable Bilevel Optimization for LLM Data Reweighting
Figure 2 for ScaleBiO: Scalable Bilevel Optimization for LLM Data Reweighting
Figure 3 for ScaleBiO: Scalable Bilevel Optimization for LLM Data Reweighting
Figure 4 for ScaleBiO: Scalable Bilevel Optimization for LLM Data Reweighting
Viaarxiv icon

Large Batch Analysis for Adagrad Under Anisotropic Smoothness

Add code
Jun 21, 2024
Viaarxiv icon

Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts

Add code
Jun 18, 2024
Figure 1 for Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts
Figure 2 for Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts
Viaarxiv icon

Leveraging Locality to Boost Sample Efficiency in Robotic Manipulation

Add code
Jun 15, 2024
Viaarxiv icon

Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs

Add code
Jun 14, 2024
Figure 1 for Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs
Figure 2 for Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs
Figure 3 for Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs
Figure 4 for Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs
Viaarxiv icon

AdaNCA: Neural Cellular Automata As Adaptors For More Robust Vision Transformer

Add code
Jun 12, 2024
Viaarxiv icon

VeraCT Scan: Retrieval-Augmented Fake News Detection with Justifiable Reasoning

Add code
Jun 12, 2024
Figure 1 for VeraCT Scan: Retrieval-Augmented Fake News Detection with Justifiable Reasoning
Figure 2 for VeraCT Scan: Retrieval-Augmented Fake News Detection with Justifiable Reasoning
Figure 3 for VeraCT Scan: Retrieval-Augmented Fake News Detection with Justifiable Reasoning
Figure 4 for VeraCT Scan: Retrieval-Augmented Fake News Detection with Justifiable Reasoning
Viaarxiv icon