arXiv AI July 7, 2026 By Saba Fathi, Fardin Ayar, Maryam Abdolali, Ehsan Javanmardi, Manabu Tsukada, Mahdi Javanmardi

How Do Diffusion Classifiers Decide? A Bias-Centric Evaluation

arXiv:2607. 03831v1 Announce Type: cross Abstract: Diffusion models have recently been repurposed for zero-shot classification, giving rise to diffusion classifiers that identify the best-matching text prompt by minimizing the noise-prediction error.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jul 7

Self-Improving Diffusion Classifiers with Minority Preference Optimization

arXiv:2607. 03770v1 Announce Type: cross Abstract: Prior studies have demonstrated that diffusion classifiers achieve robust zero-shot classification performance.

By Hyunsoo Kim, Jungmyung Wi, Soobin Um, Donghyun Kim, Suhyun Kim

diffusion fine-tuning safety

arXiv Computation and Language

Sep 2

Reliability Challenges in Diffusion Vision-Language Models

The paper presents the first systematic reliability evaluation of diffusion-based Large Vision‑Language Models (dLVLMs), comparing six diffusion models to autoregressive (AR) baselines across four dimensions. Key findings include a reversal of the yes‑bias seen in AR models for binary visual queries, competitive hallucination rates but lower linguistic quality, near‑zero accuracy for underrepresented racial groups with opposite‑polarity gender bias, and accuracy collapse in multiple‑choice tasks when the correct option is shorter than distractors due to a length prior emerging at the first denoising step. Additionally, tokens committed late in denoising with low confidence correlate with hallucinated content, indicating a unique mechanistic signal in diffusion generation.

By Md. Atabuzzaman, Chris Thomas

llms diffusion multimodal benchmarks safety

arXiv Machine Learning

Aug 18

Discrete Diffusion Language Models Are Training-Free Multi-Label Classifiers

arXiv:2608. 14649v1 Announce Type: new Abstract: We present dLLM-SetScore, a training-free method that uses discrete masked-diffusion language models for multi-label text classification.

By Pawan Kumar

llms diffusion nlp fine-tuning

arXiv Machine Learning

Jul 15

Steering Diffusion Models via Class-Contrastive Influence for Few-Shot Medical Classification

arXiv:2607. 12464v1 Announce Type: cross Abstract: When labeled data are scarce, off-the-shelf diffusion models can augment training sets for few-shot medical image classification, but not all generated samples are equally useful for the downstream task.

By Jeeyung Kim, Erfan Esmaeili, Qiang Qiu

diffusion computer-vision reinforcement-learning fine-tuning benchmarks

arXiv Computer Vision

Aug 21

DIFFCZSL: Compositional Zero-Shot Learning Regularized by Diffusion Representations

arXiv:2608. 19871v1 Announce Type: new Abstract: Compositional Zero-Shot Learning (CZSL) aims to recognize unseen attribute-object compositions by leveraging knowledge of primitive concepts learned from seen compositions.

By Hangyu Tian, Zhenqi He, Yanghao Wang, Long Chen

llms rag diffusion multimodal benchmarks safety

arXiv Computer Vision

4d ago

Targeted Visual Counterfactual Explanations for Contrastive Vision-Language Model

arXiv:2609.37638v1 Announce Type: new Abstract: Current explanation methods for contrastive vision--language models such as CLIP mainly identify important regions without showing how to change the in...

By Van Bach Nguyen, J\"org Schl\"otterer, Christin Seifer

llms diffusion multimodal