arXiv AI October 5, 2026 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

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

Read the original on arXiv AI →

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.

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 Computer Vision

6d ago

One Ranking, Any Budget: Matryoshka Evidence-to-Context Frame Selection for Long-Video Understanding

arXiv:2608.05707v2 Announce Type: replace Abstract: Frame selection is essential for applying Large Multimodal Models (LMMs) to long videos due to severe frame redundancy and limited context windows....

By Wang Chen, Yu Chen, Xiang Wang, Shuai Li, Jinfa Huang, Xiawu Zheng

multimodal benchmarks

arXiv AI

Sep 30

Hierarchical Compression of Vision-Language Model Benchmarks

arXiv:2609.37515v1 Announce Type: cross Abstract: Thorough evaluation of vision-language models (VLMs) has become prohibitively expensive, as benchmarks span an ever-broader spectrum of capabilities...

By Hyunjong Ok, Seunggu Kang, Jaeho Lee

llms rag efficiency multimodal benchmarks

arXiv AI

Jul 28

MM-ShiftKV: Decode-Aware Prefill-Stage KV Selection for Multimodal Large Language Models

arXiv:2607. 22586v1 Announce Type: new Abstract: Key-Value (KV) caching is essential for efficient inference in multimodal large language models (MLLMs), yet its memory footprint grows linearly with context length and becomes a major bottleneck due to the large number of visual tokens.

By Jinsong Shu, Chenyang Wu, Zhongle Xie, Baokun Wang, Lidan Shou

llms efficiency multimodal benchmarks

arXiv AI

Aug 5

When and Where to Look: Adaptive Visual Evidence Scheduling for Efficient Long Video Understanding

arXiv:2608. 03918v1 Announce Type: cross Abstract: Efficient long-video understanding requires vision--language models (VLMs) to reason over a small number of frames selected as sparse visual evidence.

By Ke Li, Jiayu Chen, Maoliang Li, Zihao Zheng, Hailong Zou, Hengyi Zhang, Xuanzhe Liu, Xiang Chen

llms agents multimodal

arXiv Computer Vision

Sep 30

When to Retrieve, When to Stay: Uncertainty-Aware Temporal Evidence Allocation for Streaming Video-LLMs

arXiv:2609.37345v1 Announce Type: new Abstract: Streaming video understanding requires Video Large Language Models (Video-LLMs) to reason over continuous visual streams under causal constraints. As t...

By Xiang Hu, Jiazuo Yu, Lu Zhang, Yunzhi Zhuge, Huchuan Lu

llms multimodal benchmarks

arXiv AI

Aug 26

VisCache: Visual KV Cache Pruning for Efficient Vision Large Language Model Inference

VisCache introduces a two-stage, plug‑and‑play framework for pruning visual key‑value caches in Vision Large Language Models without retraining. The first stage filters out temporally redundant keyframes, while the second stage, PruneKV, applies a parabolic layer‑wise budget and asymmetric update to selectively prune keys and fuse values, preserving essential context. Experiments show up to 2.35× speedup and significant memory savings with only 19–28% of the original cache retained, outperforming existing baselines.

By Lyuke Wang, Zhuo Li, Guangxu Zhu

llms efficiency multimodal

One email a morning, machine-written

Related stories

One Ranking, Any Budget: Matryoshka Evidence-to-Context Frame Selection for Long-Video Understanding

Hierarchical Compression of Vision-Language Model Benchmarks

MM-ShiftKV: Decode-Aware Prefill-Stage KV Selection for Multimodal Large Language Models

When and Where to Look: Adaptive Visual Evidence Scheduling for Efficient Long Video Understanding

When to Retrieve, When to Stay: Uncertainty-Aware Temporal Evidence Allocation for Streaming Video-LLMs

VisCache: Visual KV Cache Pruning for Efficient Vision Large Language Model Inference