method · first seen 4 Oct 2026
visual token reduction
Also: token compression, token condensation, visual token pruning, visual token routing, spatial token pruning, image-token compression, pixel-space compression
Pruning or merging image tokens in vision-language models to cut inference cost while preserving accuracy.
Mentions per week
PapersCodeDiscussion
Rank 28 on 16 Nov 2026 · 30 mentions in 28 days · 30 independent groups · papers · first seen 6 weeks ago · acceleration +1.40
Earliest sources
- When and What to Prune? Stage-Aware Visual Token Pruning for Efficient VLAPapers · 4 Oct 2026 · Tianjun Shi, Haotian Xiong, Ziyu Gong, Qi Lu, Li Li
- Video Encoders Built on Image RepresentationsPapers · 5 Oct 2026 · Jusheng Zhang, Wenhao Wang, Longqi Cai, Liangzhe Yuan, Yuxiao Wang, Ming-Hsuan Y…
- Foveated Compression: Selective High-Resolution Preservation for Token-Efficient VLMsPapers · 6 Oct 2026 · Donghyun Han, Jangho Park, Yuseok Bae
- Decide Before You Look: Learning Which Retrieved Memories Deserve PixelsPapers · 6 Oct 2026 · Youxing LI
- VLA-ACL: Action-Consistent Visual Token Pruning for Efficient Vision-Language-Action ModelsPapers · 6 Oct 2026 · Owen Du, Yang Yue, Jie Zhang, Jiaqi Pi, Chi Bene Chen, Gao Huang
- CARE: Certifying Acceleration for Vision-Language-Action InferencePapers · 6 Oct 2026 · Rui Liu, Tong Zheng, Jindong Gu, Zhipeng Wang
Latest sources
- Beyond Token Stacking: Multi-scale Visual Modulation and Adaptive Fused-feature Calibration for MLLMsPapers · 16 Nov 2026 · Ye Xiao, Shesheng Song, Yi Ren, Shasha Li, Bin Ji, Xiaodong Liu, Jun Ma, Jie Yu
- POKE: Probe Offline, Keep Efficiently for Vision-Language-Action ModelsPapers · 16 Nov 2026 · Jaehyuk Lee, Yeajin Lee, Suhyun Bae, Donghun Lee
- How Reliable Is Visual Token Selection? Rethinking Pruning in Multimodal LLMsPapers · 16 Nov 2026 · Chaehee Song, Seokil Ham, KiHyun Seol, Jihyun Lee, Yubin Choi, Changick Kim
- Glance, then Select: Evidence-Tempered Visual Token Selection for Extremely Compressed Multimodal LLMsPapers · 15 Nov 2026 · Yuxuan Wang, Guangxiang Zhao, Yuxuan Tian, Yahui Han, Xinyu Tan, Feiyu Wang, Zon…
- TIVS: Mapping the Sensitivity Landscape of Visual Token Transformations in MLLMsPapers · 15 Nov 2026 · Yikang Qiao, Jianye Zeng, Duan Huang, Ziying Song
- StreamEmbed: Real-Time Indexing from Pixels for Screenshot RetrievalPapers · 13 Nov 2026 · Dayoon Ko, Yichuan Wang, Soyeong Jeong, Joseph E. Gonzalez, Gunhee Kim, Sewon Mi…
- DRAMA: Dissecting Attention Redundancy for Accelerating Multimodal Diffusion Large Language ModelsPapers · 12 Nov 2026 · Yi-Hsin Hung, Fangfu Liu, Shao-Yuan Lo, Chu-Song Chen
- DiFiT: Distribution-Fidelity-guided Visual Token Pruning for Multimodal Large Language ModelsPapers · 11 Nov 2026 · Jingyuan Zhang, Nihao Niu, Xinyang Lv, Beibei Han, Xiaoyun Wang, Yanning Hou, Ke…
- C$^2$-Routing: Complementary Cropping and Compression for Efficient Vision-Language InferencePapers · 10 Nov 2026 · Guorui Lu, Qinyu Chen
- OpticalRAG: Pixel-Space Compression for Token-Efficient Retrieval-Augmented GenerationPapers · 10 Nov 2026 · Senhao Liu, Yuheng Zhang, Chunyu Wei, Yueguo Chen, Xinran Zhang
- APS-VLA: Action-Guided and Future-Aware Token Pruning for Efficient Vision-Language-Action ModelsPapers · 9 Nov 2026 · Xiaoyang Xing, Chun-Mei Feng, Anthony Cohn, Xiaoliang Gong, Asoke Nandi
- UTOPI: Efficient Egocentric Long-Video Understanding in AR via User-Guided Token Pre-CompressionPapers · 8 Nov 2026 · Ziqi Wang, Su Chen, Qiance Tang, Jieyu Lin, Ziyun Li, Barbara De Salvo, Sai Qian…