arXiv Machine Learning July 2, 2026 By Guohao Sun, Xiaofang Wang, Yash Patel, Mengchen Liu, Zhiqiang Tao, Praveen Krishnan

Information-Regularized Attention for Visual-Centric Reasoning

Read the original on arXiv Machine Learning →

arXiv:2607. 00434v1 Announce Type: cross Abstract: Vision-language models (VLMs) have become a paradigm for multimodal learning, yet remain unstable due to object hallucination, weak visual grounding, and catastrophic forgetting after full-parameter instruction tuning.

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 Machine Learning.

arXiv Computer Vision

2d ago

Do Vision Transformers Need All-to-All Attention? Global Communication Through Elastic Learned Cores

arXiv:2605.12491v2 Announce Type: replace Abstract: Vision Transformers (ViTs) learn rich visual-semantic representations through all-to-all self-attention among patch tokens. However, this design im...

By Alan Z. Song, Yinjie Chen, Mu Nan, Deva Ramanan, Michael J. Tarr, Andrew F. Luo

llms computer-vision benchmarks

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 5

Balancing Efficiency and Efficacy: Training-Free Attention-Guided Switching Between Explicit and Latent Thoughts for MLLMs

arXiv:2608. 03450v1 Announce Type: cross Abstract: Reasoning in Multimodal Large Language Models (MLLMs) requires both fine-grained visual perception and rigorous logical deduction.

By Haoqian Kang, Liupeng Li, Kuofeng Gao, Jinpeng Wang, Zhenyu Lu, Bin Chen, Ke Chen, Yaowei Wang

llms multimodal benchmarks safety

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 Computer Vision

Sep 18

Understanding and Exploiting Diagonal Attention Sparsity in Autoregressive Image Generation

The paper investigates how attention sparsity behaves in autoregressive image generation, finding a distinct diagonal sparsity pattern due to spatial locality of visual tokens. It introduces a diagonal‑aware sparse attention mechanism that skips KV entries along the diagonal within a recent window, achieving up to 3.1× higher throughput and 1.19× lower latency with less than 2% quality loss compared to dense inference.

By Daeun Kim, Junwha Hong, Changhun Oh, Yoonsung Kim, Yoonhyeong Lee, Jongse Park

llms diffusion efficiency multimodal

arXiv AI

Jul 1

Attend, Transform, or Silence: Operator-Level Visual Skipping for Efficient Multimodal LLM Inference

arXiv:2606. 31903v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) increasingly process long visual-token sequences, increasing the overall inference computation.

By Zhaoyang Luo, Runmin Dong, Miao Yang, Fan Wei, Yushan Lai, Bin Luo, Haohuan Fu

llms multimodal benchmarks

One email a morning, machine-written

Related stories

Do Vision Transformers Need All-to-All Attention? Global Communication Through Elastic Learned Cores

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

Balancing Efficiency and Efficacy: Training-Free Attention-Guided Switching Between Explicit and Latent Thoughts for MLLMs

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

Understanding and Exploiting Diagonal Attention Sparsity in Autoregressive Image Generation

Attend, Transform, or Silence: Operator-Level Visual Skipping for Efficient Multimodal LLM Inference