No article text was recorded for this version.
semantic token compression
Version 1 of 133 papers42 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Focusing on What Matters: Object-Agent-centric Tokenization for Vision Language Action models
- Blog: Isomer: Isomerous Transformer for Zero-shot Video Object Segmentation
- Blog: DTMFormer: Dynamic Token Merging for Boosting Transformer-Based Medical Image Segmentation
- Blog: Reading Images Like Texts: Sequential Image Understanding in Vision-Language Models
- Blog: Visual Transformers: Where Do Transformers Really Belong in Vision Models?
- Blog: Neural Slot Interpreters: Grounding Object Semantics in Emergent Slot Representations
- Blog: Iwin: Human-Object Interaction Detection via Transformer with Irregular Windows
- Blog: SimVLG: Simple and Efficient Pretraining of Visual Language Generative Models
- Blog: Remote Sensing Image Change Detection With Transformers
- Blog: Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding
- Blog: NExT-GPT: Any-to-Any Multimodal LLM
- Blog: UHR-BAT: Budget-Aware Token Compression Vision-Language model for Ultra-High-Resolution Remote Sensing
- Blog: Making Vision Transformers Efficient from A Token Sparsification View
- Blog: Graph Reasoning Transformer for Image Parsing
- Blog: Structure over Pixels: Learning Variable-Length Visual Programs
- Blog: One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding
- Blog: TokenLearner: Adaptive Space-Time Tokenization for Videos
- Blog: Efficient Discriminative Joint Encoders for Large Scale Vision-Language Reranking
- Blog: Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning
- Blog: Efficient Multi-modal Large Language Models via Visual Token Grouping
- Blog: Boosting Audio Visual Question Answering via Key Semantic-Aware Cues
- Blog: SVFAP: Self-supervised Video Facial Affect Perceiver
- Blog: ScalableViT: Rethinking the Context-Oriented Generalization of Vision Transformer
- Blog: Expedited Training of Visual Conditioned Language Generation via Redundancy Reduction
- Blog: Image embedding and user multi-preference modeling for data collection sampling
- Blog: Single-pass Adaptive Image Tokenization for Minimum Program Search
- Blog: AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark
- Blog: Adapting Large Vision-Language Models to Visually-Aware Conversational Recommendation
- Blog: MCAT: Visual Query-Based Localization of Standard Anatomical Clips in Fetal Ultrasound Videos Using Multi-Tier Class-Aware Token Transformer
- Blog: MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
- Blog: BccT: an efficient transformer model for blood cell classification
- Blog: LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models
- Blog: Native Segmentation Vision Transformers
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_semantic_token_compression_cc870e3e,
title = {semantic token compression},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/semantic-token-compression/rdr_cc870e3e7fb94d97aa885c4c5265076b},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_semantic_token_compression_cc870e3e_v1,
title = {semantic token compression},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/semantic-token-compression/rdr_cc870e3e7fb94d97aa885c4c5265076b/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}