arXiv AI

LensVLM: Selective Context Expansion for Compressed Visual Representation of Text

LensVLM is an inference framework and post‑training recipe that lets Vision‑Language Models (VLMs) process compressed images of text by selectively expanding only the relevant parts back to full resolution. Using Qwen3.5‑9B‑Base, LensVLM achieves accuracy comparable to full‑text models at 4.3× compression and outperforms other compression baselines up to 10.1× across seven text QA benchmarks, while also improving performance on multimodal document and code tasks as compression increases.

arXiv AI

Aug 28

PACE: A Unified Condense-and-Extract Paradigm for Fast VLM Inference

PACE introduces a training‑free Condense‑and‑Extract framework that speeds up Vision‑Language Model inference by first adaptively downsampling visual inputs before encoding and then selectively retaining essential tokens during decoding. The Adaptive Pixel Compressor (APC) reduces encoder workload while preserving global context, and the Dynamic Dual‑Attention Extractor (DDAE) keeps task‑critical details by fusing visual and language signals. Applied to Qwen2.5‑VL‑7B, PACE maintains 93.8% of performance using only 10% of visual tokens, achieving a 3.1× speedup in time to first token.

By Junjie Liu, Shengyuan Ye, Xu Chen

llms efficiency multimodal

arXiv AI

Aug 13

QV-PIC: Query-Aware Visual Position-Independent Caching for Efficient RAG Serving

arXiv:2608. 12121v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) repeatedly prefills identical text chunks across queries, incurring redundant computations.

By Yilin Liu, Rui Meng, Wangze Ni, Jianxin Yan, Heng Cao, Libin Zheng, Peng Cheng, Jinfei Liu

rag

arXiv AI

Jun 30

How to Train Your Long-Context Visual Document Model

arXiv:2602. 15257v3 Announce Type: replace-cross Abstract: We present the first comprehensive, large-scale study of training long-context vision language models up to 344K context, targeting long-document visual question answering with measured transfer to long-context text.

By Austin Veselka

llms nlp fine-tuning benchmarks

arXiv Computation and Language

Sep 2

On the Design Fundamentals of Pixel Text Representation Learning

arXiv:2609.01147v1 Announce Type: cross Abstract: Text-rich visual inputs require models that can read, retrieve, and compress language directly in pixel space, yet existing pixel-text encoders strug...

By Chaohao Yuan, Ruifeng Yuan, Zhuoxu Huang, Yu Rong, Hong Cheng, Hou Pong Chan, Chenghao Xiao

multimodal benchmarks safety

arXiv AI

Jun 2

CLIP Tricks You: Training-free Token Pruning for Efficient Pixel Grounding in Large VIsion-Language Models

arXiv:2605. 13178v2 Announce Type: replace-cross Abstract: In large vision-language models, visual tokens typically constitute the majority of input tokens, leading to substantial computational overhead.

By Sangin Lee, Yukyung Choi

llms fine-tuning efficiency multimodal

arXiv AI

Sep 10

Bigger Text Encoders Can Hurt CLIP Zero-Shot Performance

arXiv:2609.05730v1 Announce Type: cross Abstract: Contrastive Language-Image Pretraining (CLIP) is a building block of many machine learning applications. Scaling laws have guided resource allocation...

By Samir Char, Carles Domingo-Enrich, Randall Balestriero

rag multimodal safety

Hugging Face Trending Papers

Jul 27

MAViE: A Multi-scale Adaptive Vision Encoder for Fine-grained Visual Perception and Efficient Multimodal Reasoning

Vision-language models commonly project all tokens produced by a pretrained vision encoder into a large language model. However, final-layer features can discard text, local attributes, and spatial relationships, while high-resolution inputs substantially increase context length and inference latency.

llms computer-vision efficiency multimodal benchmarks

arXiv Computation and Language

Aug 25

Learning to Look Again: Loss-Gap Supervision for Free-form Crop Routing in Vision-Language Models

arXiv:2608.21762v1 Announce Type: cross Abstract: Vision-language models (VLMs) fail many detail-centric questions for a concrete reason: the answer is visible in the image, yet lost after the image...

By Jinchang Zhu, Rong Fu, Yi Ding, Chenghao Wu, Ying Liu, Menglin Yang

llms computer-vision multimodal benchmarks

arXiv Computer Vision

Aug 28

Multi-Image Visual Token Pruning in Large Visual Language Models

The paper introduces Adaptive Visual Token Pruning (AVTP), a training‑free framework that dynamically selects pruning layers and ratios for large vision‑language models (LVLMs) when processing multiple image sequences. By analyzing visual attention distributions across different LVLM architectures, AVTP adapts token retention to image importance, enabling efficient inference without relying on attention‑based computations incompatible with FlashAttention. Experiments show significant speedups—up to 2× for Qwen3VL‑8B—while preserving or even improving accuracy on multi‑image benchmarks.

By Rongyang Zhang, Chengqiang Lu, Cong Li, Hongchao Gu, Tingjia Shen, Xuyang Zhi, Qimeng Wang, Yan Gao, Yi Wu, Yao Hu, Hao Wang, Enhong Chen

llms efficiency benchmarks

arXiv AI

Jun 2

CARES: Context-Aware Resolution Selector for VLMs

arXiv:2510. 19496v3 Announce Type: replace-cross Abstract: Large vision-language models (VLMs) commonly process images at native or high resolution to remain effective across tasks.

By Moshe Kimhi, Nimrod Shabtay, Raja Giryes, Chaim Baskin, Eli Schwartz

llms multimodal benchmarks

arXiv Computer Vision

Sep 7

FAVE: Foveated Adaptive Visual Encoding for Efficient Fine-Grained Visual Understanding

FAVE (Foveated Adaptive Visual Encoding) is a lightweight, variable‑resolution Vision Transformer that encodes user‑selected image regions at high acuity while maintaining the image’s native geometry. In controlled experiments on small‑object ImageNet crops, FAVE outperforms a fixed‑resolution ViT by 9.4 top‑1 points while using 12.7× fewer FLOPs. When added as a local branch to FastVLM, FAVE improves TextVQA by 1.60 points and GQA attribute accuracy by 1.31 points, achieving a 3.3× speedup over SmolVLM2-2.2B with only 16 extra local tokens.

By Amitangshu Mukherjee, Kaushik Roy

llms

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

Related stories