No article text was recorded for this version.
positional index preservation
Version 1 of 123 papers37 conceptsfrozen 2026-10-04
Papers in this version
- Blog: AstraNav-Memory: Contexts Compression for Long Memory
- Blog: SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration
- Blog: Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer
- Blog: Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference
- Blog: UMG-CLIP: A Unified Multi-granularity Vision Generalist for Open-World Understanding
- Blog: How to Prune Your Language Model: Recovering Accuracy on the "Sparsity May Cry" Benchmark
- Blog: Nüwa: Mending the Spatial Integrity Torn by VLM Token Pruning
- Blog: DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models
- Blog: Position Is All You Need: A Free Lunch Token Compression Strategy for MLLM-based Referring Expression Segmentation
- Blog: Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation
- Blog: Task-Aware Structured Memory for Dynamic Multi-modal In-Context Learning
- Blog: DPad: Efficient Diffusion Language Models with Suffix Dropout
- Blog: SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning
- Blog: mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding
- Blog: Making Vision Transformers Efficient from A Token Sparsification View
- Blog: ShowUI: One Vision-Language-Action Model for GUI Visual Agent
- Blog: Exploiting Spatial Sparsity for Event Cameras with Visual Transformers
- Blog: TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos
- Blog: VQToken: Neural Discrete Token Representation Learning for Extreme Token Reduction in Video Large Language Models
- Blog: LVPruning: An Effective yet Simple Language-Guided Vision Token Pruning Approach for Multi-modal Large Language Models
- Blog: SUBLLM: A Novel Efficient Architecture with Token Sequence Subsampling for LLM
- Blog: FastVID: Dynamic Density Pruning for Fast Video Large Language Models
- Blog: HiDrop: Hierarchical Vision Token Reduction in MLLMs via Late Injection, Concave Pyramid Pruning, and Early Exit
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_positional_index_preservation_08ae4eb0,
title = {positional index preservation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/positional-index-preservation/rdr_08ae4eb0c1f24868b26f6090589b6cc8},
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_positional_index_preservation_08ae4eb0_v1,
title = {positional index preservation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/positional-index-preservation/rdr_08ae4eb0c1f24868b26f6090589b6cc8/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}