Picture for Jiacheng Zhang

Jiacheng Zhang

Mitigating Hallucination for Large Vision Language Model by Inter-Modality Correlation Calibration Decoding

Add code
Jan 03, 2025
Viaarxiv icon

OnlineVPO: Align Video Diffusion Model with Online Video-Centric Preference Optimization

Add code
Dec 19, 2024
Figure 1 for OnlineVPO: Align Video Diffusion Model with Online Video-Centric Preference Optimization
Figure 2 for OnlineVPO: Align Video Diffusion Model with Online Video-Centric Preference Optimization
Figure 3 for OnlineVPO: Align Video Diffusion Model with Online Video-Centric Preference Optimization
Figure 4 for OnlineVPO: Align Video Diffusion Model with Online Video-Centric Preference Optimization
Viaarxiv icon

Prompt-A-Video: Prompt Your Video Diffusion Model via Preference-Aligned LLM

Add code
Dec 19, 2024
Viaarxiv icon

An Efficient Occupancy World Model via Decoupled Dynamic Flow and Image-assisted Training

Add code
Dec 18, 2024
Viaarxiv icon

Minimax-optimal trust-aware multi-armed bandits

Add code
Oct 04, 2024
Viaarxiv icon

EAGLE: Towards Efficient Arbitrary Referring Visual Prompts Comprehension for Multimodal Large Language Models

Add code
Sep 26, 2024
Figure 1 for EAGLE: Towards Efficient Arbitrary Referring Visual Prompts Comprehension for Multimodal Large Language Models
Figure 2 for EAGLE: Towards Efficient Arbitrary Referring Visual Prompts Comprehension for Multimodal Large Language Models
Figure 3 for EAGLE: Towards Efficient Arbitrary Referring Visual Prompts Comprehension for Multimodal Large Language Models
Figure 4 for EAGLE: Towards Efficient Arbitrary Referring Visual Prompts Comprehension for Multimodal Large Language Models
Viaarxiv icon

EventHallusion: Diagnosing Event Hallucinations in Video LLMs

Add code
Sep 25, 2024
Figure 1 for EventHallusion: Diagnosing Event Hallucinations in Video LLMs
Figure 2 for EventHallusion: Diagnosing Event Hallucinations in Video LLMs
Figure 3 for EventHallusion: Diagnosing Event Hallucinations in Video LLMs
Figure 4 for EventHallusion: Diagnosing Event Hallucinations in Video LLMs
Viaarxiv icon

Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training

Add code
Jun 02, 2024
Figure 1 for Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training
Figure 2 for Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training
Figure 3 for Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training
Figure 4 for Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training
Viaarxiv icon

Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection

Add code
Jun 01, 2024
Viaarxiv icon

ID-Aligner: Enhancing Identity-Preserving Text-to-Image Generation with Reward Feedback Learning

Add code
Apr 23, 2024
Viaarxiv icon