paper-with-me

Papers

Score-Guided Intermediate Layer Optimization: Fast Langevin Mixing for Inverse Problems

2022-06-18 · Giannis Daras, Yuval Dagan, Alexandros G. Dimakis, Constantinos Daskalakis

We prove fast mixing and characterize the stationary distribution of the Langevin Algorithm for inverting random weighted DNN generators. This result extends the work of Hand and Voroninski from efficient inversion to efficient posterior sampling. In practice, to allow for increased expressivity, we propose to do posterior sampling in the latent space of a pre-trained generative model. To achieve that, we train a score-based model in the latent space of a StyleGAN-2 and we use it to solve inverse problems. Our framework, Score-Guided Intermediate Layer Optimization (SGILO), extends prior work by replacing the sparsity regularization with a generative prior in the intermediate layer. Experimentally, we obtain significant improvements over the previous state-of-the-art, especially in the low measurement regime.

📄 PDF Abstract BibTeX arXiv:2206.09104

Code (2)

giannisdaras/sgilo 공식 구현 pytorch
giannisdaras/ilo pytorch

Similar Papers 제목 키워드 기반

OISD: On-Policy Internal Self-Distillation of Language Models

2026-05-27 · Xinyu Liu, Darryl Cherian Jacob, Yang Zhou, Jindong Wang 외 arxiv

Recent reinforcement learning (RL) post-training approaches primarily optimize the final output policy using sparse outcome-level rewards, while largely overlooking predictive signals encoded in intermediate representati…

Reinforcement LearningMathematical Reasoning

Intermediate Text Representation Guided Text-to-Image Generation for Enhancing One-and-Only Alignment

2026-06-29 · Soyoun Won, Aryan Yazdan Parast, Basim Azam, Jean Honorio 외 arxiv

Text-to-image (T2I) diffusion models often fail to faithfully render explicit textual descriptions, instead defaulting to strongly learned visual priors due to a phenomenon referred to as concept association bias. We sho…

Text-to-Image Generation

Evaluating Image Editing with LLMs: A Comprehensive Benchmark and Intermediate-Layer Probing Approach

2026-03-20 · Shiqi Gao, Zitong Xu, Kang Fu, Huiyu Duan 외 arxiv

Evaluating text-guided image editing (TIE) methods remains a challenging problem, as reliable assessment should simultaneously consider perceptual quality, alignment with textual instructions, and preservation of origina…

Image Editing

Emotion-Aligned Generation in Diffusion Text to Speech Models via Preference-Guided Optimization

2025-09-29 · Jiacheng Shi, Hongfei Du, Yangfan He, Y. Alicia Hong 외 arxiv

Emotional text-to-speech seeks to convey affect while preserving intelligibility and prosody, yet existing methods rely on coarse labels or proxy classifiers and receive only utterance-level feedback. We introduce Emotio…

Text to Speech

SGHA-Attack: Semantic-Guided Hierarchical Alignment for Transferable Targeted Attacks on Vision-Language Models

2026-02-02 · Haobo Wang, Weiqi Luo, Xiaojun Jia, Xiaochun Cao arxiv

Large vision-language models (VLMs) are vulnerable to transfer-based adversarial perturbations, enabling attackers to optimize on surrogate models and manipulate black-box VLM outputs. Prior targeted transfer attacks oft…