paper-with-me

홈 › Papers

TAG: Tangential Amplifying Guidance for Hallucination-Resistant Sampling

2025-10-06 · Hyunmin Cho, Donghoon Ahn, Susung Hong, Jee Eun Kim, Seungryong Kim, Kyong Hwan Jin arxiv

Diffusion models achieve state-of-the-art image generation but often produce semantic inconsistencies, or hallucinations. Existing inference-time guidance methods rely on external signals or architectural modifications, adding computational overhead. We propose $\mathbf{T}$angential $\mathbf{A}$mplifying $\mathbf{G}$uidance $\mathbf{(TAG)}$, a training-free, architecture-agnostic, plug-and-play guidance method that operates purely on trajectory signals. TAG uses an intermediate sample as a projection basis and amplifies the tangential components of the estimated score to correct the sampling trajectory. A first-order Taylor analysis shows that this steers the state toward higher-probability regions of the data manifold, reducing inconsistencies and improving fidelity while adding negligible overhead to existing samplers. Code is available at our Project Page (https://hyeon-cho.github.io/TAG/).

📄 PDF Abstract BibTeX arXiv:2510.04533

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Similar Papers 제목 키워드 기반

ClipTTT: CLIP-Guided Test-Time Training Helps LVLMs See Better

2026-03-27 · Mriganka Nath, Anurag Das, Jiahao Xie, Bernt Schiele arxiv

Large vision-language models (LVLMs) tend to hallucinate, especially when visual inputs are corrupted at test time. We show that such corruptions act as additional distribution shifts, significantly amplifying hallucinat…

Capturing Gaze Shifts for Guidance: Cross-Modal Fusion Enhancement for VLM Hallucination Mitigation

2025-10-24 · Zheng Qi, Chao Shang, Evangelia Spiliopoulou, Nikolaos Pappas arxiv

Vision language models (VLMs) often generate hallucination, i.e., content that cannot be substantiated by either textual or visual inputs. Prior work primarily attributes this to over-reliance on linguistic prior knowled…

Acceleration-Based Control of Fixed-Wing UAVs for Guidance Applications

2026-02-27 · Jixiang Wang, Siyuan Yang, Ziyi Wu, Siqi Wei 외 arxiv

Acceleration-commanded guidance laws (e.g., proportional navigation) are attractive for high-level decision making, but their direct deployment on fixed-wing UAVs is challenging because accelerations are not directly act…

Decision Making

Improving the Euclidean Diffusion Generation of Manifold Data by Mitigating Score Function Singularity

2025-05-15 · Zichen Liu, Wei zhang, Tiejun Li

Euclidean diffusion models have achieved remarkable success in generative modeling across diverse domains, and they have been extended to manifold case in recent advances. Instead of explicitly utilizing the structure of…

Be Tangential to Manifold: Discovering Riemannian Metric for Diffusion Models

2025-10-07 · Shinnosuke Saito, Takashi Matsubara arxiv

Diffusion models are powerful deep generative models, but unlike classical models, they lack an explicit low-dimensional latent space that parameterizes the data manifold. This absence makes it difficult to perform manif…