VisionWeave introduces elastic visual representation weaving, a native capability for multimodal large language models that learns where and at what granularity to encode visual information. The method combines a gated spatial pooler for coarse representations with a granularity router that allocates content‑adaptive token usage, trained end‑to‑end on large‑scale data. Experiments on Qwen3.5‑4B and Qwen3.8‑27B show that VisionWeave can save 43.0% of tokens while preserving 98.9% of performance across eight benchmarks, and delivers significant throughput gains and latency reductions when deployed on the SGLang serving engine.
By Yuan Feng, Qize Yang, Ruizhe Chen, Sibo Song, Haolin He, Muzhi Zhu, Zihan Liu, Yunfei Chu, Xize Cheng, Yuxuan Wang, Jin Xu, Xike Xie
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
V-LUMEN introduces a visual lookup memory for vision‑language models by discretizing visual features with a frozen codebook, creating spatially aware memory keys via hashing, and modulating them with text‑conditioned relevance signals. The retrieved embeddings are fused into a frozen Qwen3‑VL‑2B backbone through a gated residual pathway, yielding substantial improvements on five reasoning‑intensive benchmarks and zero‑shot transfer to three disjoint image datasets. At a matched parameter budget, reallocating capacity from LoRA or MoE adapters to V‑LUMEN preserves accuracy on two backbones, demonstrating that external visual memory offers an independent capacity axis.
whyItMatters":"The paper shows that adding a non‑parametric visual lookup memory can significantly boost vision‑language model performance without increasing per‑token compute, offering a new way to scale such models."
By Miso Choi, Daekeun Kim, Eunji Kim, Jungbeom Lee
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
arXiv:2610.07729v1 Announce Type: new
Abstract: Visual tokens are a major source of inference cost in vision-language models, yet simple image downsampling remains a surprisingly strong compression b...
By Donghyun Han, Jangho Park, Yuseok Bae
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.
By Roy Xie, Dan Friedman, Donghan Yu, Bowen Pan, Christopher Fifty, Jang-Hyun Kim, Xianzhi Du, Zhe Gan, Vivek Rathod, Bhuwan Dhingra