Hugging Face Trending Papers

VLM-as-a-Judge for Person Re-Identification

The paper demonstrates that a frozen vision‑language model (VLM) can serve as a zero‑shot judge to rerank candidate lists for cloth‑changing person re‑identification (CC‑ReID). Using the VLM to rerank two expert models on the CHIRLA benchmark improves rank‑1 performance by an average of 12.9 points over the best expert and 9.4 over a naive ensemble, without any fine‑tuning on target data. By gating the VLM’s use to cases where the experts disagree at rank‑1, the authors reduce compute by 40% with minimal impact on rank‑1 accuracy.

arXiv AI

Oct 5

AMBER: Multi-View Adaptive Budget Allocation for Listwise Vision-Language Reranking

AMBER is a new online, budgeted multi‑view reranking framework for vision‑language models that dynamically allocates computation to maximize information gain. It treats fragmented listwise VLM outputs as local tournaments and uses continuous Elo updates to maintain a lightweight global ranking state. Experiments on CIRR, CIRCO, and PhotoBench show that AMBER outperforms other multi‑call VLM reranking methods under comparable budgets, and remains effective even with lower budgets.

By Wenteng Chen, Jiachen Zhu, Rong Shan, Tianyi Xu, Yuxiang Chen, Congmin Zheng, Teng Wang, Junjie Wu, Weiwen Liu, Changwang Zhang, Weinan Zhang, Jun Wang, Jianghao Lin

llms rag multimodal

arXiv Computer Vision

Sep 2

From Saliency to Discriminability: Rank-Preserving Visual Token Pruning for VLM Rerankers

arXiv:2609.00667v1 Announce Type: cross Abstract: Large vision-language models used as listwise rerankers must jointly process visual tokens from tens of candidates per query, making token pruning es...

By Siyi Liu, Hanjun Yang, Chenchen Zhang, Xiaorong Zhu, Xinyu Zuo, Lisheng Duan, Haijin Liang, Jin Ma, Junfu Pu, Yongqi Zhang

llms efficiency multimodal benchmarks

arXiv Computation and Language

Oct 1

Listening to the Wise Few: Query-Key Alignment Unlocks Latent Correct Answers in Large Language Models

arXiv:2410.02343v2 Announce Type: replace Abstract: Large language models (LLMs) routinely fail to output the correct option in multiple-choice question answering (MCQA) while encoding the answer int...

By Eduard Tulchinskii, Kristian Kuznetsov, Laida Kushnareva, Anastasia Voznyuk, Andrei Andriiainen, Irina Piontkovskaya, Evgeny Burnaev, Serguei Barannikov

llms rag nlp benchmarks safety

arXiv Computer Vision

Oct 21

In PRAISE of Attributes: Grounding Retrieval Geometry with Query-Conditioned Subspaces for Person Re-Identification

The paper introduces PRAISE, a test‑time adaptation framework for vision‑language model based person re‑identification. PRAISE constructs an Attribute‑Conditioned Subspace (ACS) from a bank of attribute prompts, reshaping query‑gallery affinities without requiring identity or attribute labels. Experiments on image‑to‑image and text‑to‑image ReID benchmarks show that PRAISE consistently improves retrieval performance over existing backbones and TTA baselines.

By Rajarshi Bhattacharya, Aryan Shukla, Shakeeb Murtaza, Christian Desrosiers, Jose Dolz, Maguelonne Heritier, Eric Granger

llms diffusion multimodal benchmarks

arXiv AI

Jun 3

CoEval: Ranking Language Models for Custom Tasks Without Labeled Data or Trustworthy Benchmarks

arXiv:2606. 03650v1 Announce Type: cross Abstract: Choosing or ranking language models for a specific application is hardest when no task-specific labeled data exists, and standard public benchmarks cannot be trusted, their items having likely leaked into pretraining, so scores reflect memorization rather than fitness.

By Alexander Apartsin, Yehudit Aperstein

llms benchmarks safety

arXiv AI

Oct 15

Attention Sinks in VLMs Are Borrowed, Not Seen

arXiv:2610.15855v1 Announce Type: new Abstract: We study how to detect and mitigate visual attention sinks in vision-language models (VLMs). Visual attention sinks are image tokens that absorb a larg...

By Dengjia Zhang, Alexander Martin, Pengyu Yan, Xihan Sun, Jiaqi Li, Benjamin Van Durme, Andrew Yates, Reno Kriz, William Walden

llms multimodal benchmarks

arXiv AI

Jun 9

Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents

arXiv:2606. 08151v1 Announce Type: new Abstract: Tool-using LLM agents often fail not because relevant text is absent, but because decisive evidence is not selected, compressed, or surfaced at action time.

By Xinyu Guan, Qianyang Zhao, Yuming Deng

llms rag agents fine-tuning benchmarks

arXiv AI

Oct 21

Don't Skip the Baseline: A Controlled Comparison of Dynamic Expert Skipping in MoEs

arXiv:2610.28369v1 Announce Type: cross Abstract: A growing body of work proposes dynamic expert-skipping methods for Mixture-of-Experts (MoE) models that adjust the number of experts activated per t...

By Jakob Steimle, Thomas Elsken, Daniel Ehrhardt, Lukas Rinder, Daniel Cremers, Xi Wang

llms multimodal benchmarks

arXiv AI

Sep 15

A Generative AI Integrated Multimodal Framework for Low-Latency Multi-Camera Person Re-Identification

arXiv:2609.14419v1 Announce Type: cross Abstract: Person re-identification (ReID) is essential for multi-camera surveillance and tracking, yet remains difficult due to viewpoint and illumination chan...

By Leon Fernando, C Dombawala, P. Hettigoda, Vanodhya G. Warnasooriya, Ishara Neranjana, Rashmika Nawaratne

llms rag multimodal benchmarks

arXiv Machine Learning

Jun 2

Reason, Retrieve, Re-rank: A Zero-Shot Reasoning-Aware Framework for Composed Video Retrieval

arXiv:2606. 00910v1 Announce Type: cross Abstract: Composed Video Retrieval (CoVR) seeks the target video that results from applying a free-form textual modification to a reference video.

By Ali Alavi

llms multimodal

arXiv Computer Vision

Aug 31

Conditional Visual Evidence Utility: State-Dependent Rank Reversals in Frozen Vision-Language Encoders

arXiv:2608.28316v1 Announce Type: new Abstract: Static importance scores compress visual evidence into a single ranking, but the value of remaining evidence can change after one cue has been observed...

By Yunxuan Fang, Xinhe Wang

rag multimodal

arXiv Machine Learning

Oct 28

SAKI-RoPE: Score-Aware Low-Rank Key Indexing with RoPE-Aware Covariance and Random-Matrix Noise Analysis

The paper introduces SAKI-RoPE, a training‑free low‑rank key‑indexing method that optimally preserves attention scores by solving a covariance‑weighted rank‑r problem using query and key statistics. It outperforms key‑PCA across multiple large language models and context lengths, achieving higher recall with significantly lower rank. The authors also analyze random‑matrix noise to justify the calibration token budget and demonstrate that clipping the Marchenko‑Pastur bulk improves performance when calibration data is limited.

By Lin Zhang

llms

Related stories