6 results found Sort:

yueliu1999
Awesome-Jailbreak-on-LLMs yueliu1999
38
414
mit
22
Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel, exciting jailbreak methods on LLMs. It contains papers, codes, datasets, evaluations, and analyses.
ai llm vlm llms vlms safety privacy security jailbreak
Created 2024-06-27
172 commits to main branch, last one 3 days ago
tianyi-lab
HallusionBench tianyi-lab
7
259
bsd-3-clause
4
[CVPR'24] HallusionBench: You See What You Think? Or You Think What You See? An Image-Context Reasoning Benchmark Challenging for GPT-4V(ision), LLaVA-1.5, and Other Multi-modality Models
llm lmm vlms gpt-4 llava gpt-4v benchmark benchmarks hallucination large-language-models large-vision-language-models
Created 2023-10-22
136 commits to main branch, last one about a month ago
dvlab-research
VisionZip dvlab-research
7
191
apache-2.0
3
Official repo for "VisionZip: Longer is Better but Not Necessary in Vision Language Models"
vlms efficiency multi-modality vision-language-model
Created 2024-12-02
8 commits to main branch, last one 6 days ago
Beckschen
ViTamin Beckschen
6
185
apache-2.0
6
[CVPR 2024] Official implementation of "ViTamin: Designing Scalable Vision Models in the Vision-language Era"
vlms scalable-vision-encoder
Created 2024-04-02
48 commits to main branch, last one 6 months ago
MCG-NJU
AWT MCG-NJU
2
87
apache-2.0
4
[NeurIPS 2024] AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation
clip vlms siglip computer-vision transfer-learning zero-shot-learning video-understanding open-set-recognition
Created 2024-10-04
6 commits to main branch, last one 2 months ago
foundation-multimodal-models
CAL foundation-multimodal-models
2
57
apache-2.0
0
[NeurIPS'24] Official PyTorch Implementation of Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment
vlms contrastive-alignment
Created 2024-05-28
16 commits to main branch, last one 2 months ago