arXiv AI September 18, 2026 By Wei Yang, Hong Xie, Tao Tan, Xin Li, Defu Lian, Enhong Chen

Model Specific Task Similarity for Vision Language Model Selection via Layer Conductance

The paper introduces a method for selecting the best vision‑language model for a downstream task by analyzing the internal dynamics of the visual encoder. It represents each task with layer‑wise conductance and uses an entropy‑regularized alignment to derive a target‑conditioned block importance distribution. The proposed Directional Conductance Divergence (DCD) metric captures asymmetric transferability, enabling accurate prediction of model rankings without direct inference, and achieves a 14.7% NDCG@5 improvement over SWAB on 48 VLMs across 21 datasets.

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

Aug 20

From Inference to Adaptation: A Unified Optimal Transport View of Vision Language Model

arXiv:2608. 18339v1 Announce Type: cross Abstract: Vision-language models (VLMs) have demonstrated remarkable zero-shot capabilities yet remain sensitive to real-world distribution shifts during inference.

By Qi Yu, Zhichen Zeng, Katherine Tieu, Xiyuan Yang, Ruizhong Qiu, Yuchen Yan, Lihui Liu, Yanjun Zhao, Lingjie Chen, Jingrui He, Hanghang Tong

llms rag computer-vision multimodal benchmarks safety

arXiv Computer Vision

Sep 10

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Pruning

arXiv:2608.06411v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) achieve strong performance across diverse vision-language tasks, but their efficiency is limited by...

By Yuyao Sun, Tao Deng, Shuang Li, Deqing Wang, Hao Geng, Minjun Yu

llms efficiency multimodal benchmarks

arXiv AI

Aug 10

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin

arXiv:2608. 06411v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) achieve strong performance across diverse vision-language tasks, but their efficiency is limited by the cost of processing numerous visual tokens.

By Yuyao Sun, Tao Deng, Shuang Li, Deqing Wang, Hao Geng, Minjun Yu

llms efficiency multimodal benchmarks

arXiv Machine Learning

Jun 5

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models

arXiv:2606. 05758v1 Announce Type: cross Abstract: Many modern vision-language models (VLMs) build on autoregressive decoding of discrete tokens.

By Zhuoming Liu, Jinhong Lin, Kwan Man Cheng, Lin Zhang, Shayok Bagchi, Yin Li

llms diffusion robotics multimodal

arXiv AI

Jun 16

Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual Embeddings

arXiv:2606. 15134v1 Announce Type: cross Abstract: Vision encoders for retrieval are typically trained with class-label supervision: each training pair reduces to a scalar that uniformly pushes the embedding apart or pulls it together, as if every visual attribute either differed or matched.

By Shubhang Bhatnagar, Dheeraj Baiju, Narendra Ahuja

llms rag efficiency multimodal benchmarks

Hugging Face Trending Papers

Aug 11

When Vision Becomes Text: Visual Token Pruning via Cross-Modal Residual Guidance in VLMs

Abundant visual information strengthens vision-language model (VLM) perception, yet massive visual tokens raise inference costs. Existing visual token pruning methods rely on similarity-based guidance, which exploits pairwise text-vision and vision-vision token correlations for compression.

llms efficiency multimodal

One email a morning, machine-written

Related stories

From Inference to Adaptation: A Unified Optimal Transport View of Vision Language Model

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Pruning

Learning to Predict Middle-Layer Attention in MLLMs for Visual Token Prunin

DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models

Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual Embeddings

When Vision Becomes Text: Visual Token Pruning via Cross-Modal Residual Guidance in VLMs