Hugging Face Trending Papers June 11, 2026

Multi-Label Test-Time Adaptation with Bayesian Conditional Priors

Read the original on Hugging Face Trending Papers →

Multi-label recognition with frozen Vision-Language Models (VLMs) is brittle under distribution shift: standard zero-shot inference scores labels independently, ignoring co-occurrence structure and producing incoherent label sets where dominant concepts suppress weaker but compatible labels. We introduce Bayesian Conditional Priors (BCP) Estimation, a gradient-free test-time adaptation method that injects label dependency without tuning the backbone.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv Machine Learning

Jun 2

Density-Aware Translation of Spurious Correlations in Zero-Shot VLMs

arXiv:2606. 01710v1 Announce Type: cross Abstract: Vision-Language models (VLMs), such as CLIP, achieve powerful zero-shot classification.

By Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie, Sarah Erfani

llms rag fine-tuning multimodal benchmarks safety

arXiv Machine Learning

Jul 1

T-QPM: Enabling Temporal Out-Of-Distribution Detection and Domain Generalization for Vision-Language Models in Open-World

arXiv:2603. 18481v2 Announce Type: replace-cross Abstract: Out-of-distribution (OOD) detection remains a critical challenge in open-world learning, where models must adapt to evolving data distributions.

By Aditi Naiknaware, Salimeh Sekeh

llms multimodal benchmarks

arXiv Machine Learning

Jul 2

AdaBoosting Text Prompts for Vision-Language Models

arXiv:2607. 00684v1 Announce Type: new Abstract: The classification accuracy of pretrained Vision-Language Models (VLMs) relies on the quality of the text prompts.

By Seokhee Jin, Changhwan Sung, Sunung Mun, Hoyoung Kim, Jungseul Ok

llms multimodal benchmarks

arXiv AI

Jun 8

SS-TPT: Stability and Suitability-Guided Test-Time Prompt Tuning for Adversarially Robust Vision-Language Models

arXiv:2606. 06943v1 Announce Type: cross Abstract: Vision-language models (VLMs) such as CLIP achieve strong zero-shot recognition but remain highly fragile under adversarial perturbations.

By Sunoh Kim, Daeho Um

llms efficiency multimodal benchmarks safety

arXiv AI

Jul 3

AnyGroundBench: A Specialized-Domain Benchmark for Video Grounding in Vision-Language Models

arXiv:2607. 02269v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated immense promise in Spatio-Temporal Video Grounding (STVG).

By Rintaro Otsubo, Ryo Fujii, Reina Ishikawa, Taiki Kanaya, Kanta Sawafuji, Hiroki Kajita, Shigeki Sakai, Hideo Saito, Ryo Hachiuma

llms fine-tuning multimodal benchmarks

Hugging Face Trending Papers

Aug 6

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding

Recent advancements in MLLM-based long-form video understanding have mitigated inference-time computational cost and limited context lengths by selecting query-relevant frames. However, existing approaches predominantly rely on external proxy scorers and rigid heuristic rules, inevitably suffering from misalignment with the target MLLM's intrinsic evidence and failing to accommodate the non-uniform spatiotemporal information density.

benchmarks

Related stories

Density-Aware Translation of Spurious Correlations in Zero-Shot VLMs

T-QPM: Enabling Temporal Out-Of-Distribution Detection and Domain Generalization for Vision-Language Models in Open-World

AdaBoosting Text Prompts for Vision-Language Models

SS-TPT: Stability and Suitability-Guided Test-Time Prompt Tuning for Adversarially Robust Vision-Language Models

AnyGroundBench: A Specialized-Domain Benchmark for Video Grounding in Vision-Language Models

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding