[논문리뷰] IAG: Input-aware Backdoor Attack on VLMs for Visual Grounding
Di Zhang이 [arXiv]에 게시한 ‘IAG: Input-aware Backdoor Attack on VLMs for Visual Grounding’ 논문에 대한 자세한 리뷰입니다.
Recent Posts
[논문리뷰] GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors
Qingnan Fan이 [arXiv]에 게시한 ‘GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors’ 논문에 대한 자세한 리뷰입니다.
[논문리뷰] Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation
Zhenghao Hu이 [arXiv]에 게시한 ‘Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation’ 논문에 대한 자세한 리뷰입니다.
[논문리뷰] Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing
Hao Zhang이 [arXiv]에 게시한 ‘Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing’ 논문에 대한 자세한 리뷰입니다.
[논문리뷰] Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models
Guiyang Hou이 [arXiv]에 게시한 ‘Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models’ 논문에 대한 자세한 리뷰입니다.