arXiv AI
Bottlenecked semantic compression by representation reconstruction
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Sep 22
VPRune: Efficient Training-free Pre-LLM Visual Token Pruning
arXiv:2609.24485v1 Announce Type: new Abstract: Visual token pruning is a promising approach to reducing the inference cost of large vision-language models (LVLMs), yet aggressive token reduction oft...
arXiv Computer Vision
Oct 9
ERASE: Eliminating Redundant Visual Tokens via Adaptive Two-Stage Token Pruning
ERASE is an adaptive two-stage token pruning framework designed to reduce computational overhead in Vision‑Language Models by eliminating redundant visual tokens. Stage 1 removes image‑level redundancy using lightweight raw‑image statistics, while Stage 2 progressively prunes instruction‑irrelevant tokens across decoder layers. Experiments on Qwen2.5‑VL‑7B show that ERASE retains 95.70 % of the original accuracy while keeping only 25 % of the tokens.
Hugging Face Trending Papers
Aug 3
CRAFT: Compression via Recursive Adaptive Fusion of Video Tokens for Vision-Language Models
In video understanding, vision-language models (VLMs) must ingest massive numbers of visual tokens, causing the computational and memory cost of the prefill stage to rise sharply. Such visual sequences are highly redundant along the spatio-temporal dimension, yet a high compression ratio is often accompanied by the loss of critical details.
arXiv AI
Aug 12
Hybrid Token Compression for Vision-Language Models
arXiv:2512. 08240v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) rely on hundreds of visual tokens, leading to high computational and memory costs.
arXiv AI
2d ago
Just Respect the Semantics: Image-Token Compression via Pre-LLM Semantic Variable-Resolution Tokenization and In-LLM Relevance Pruning
The paper introduces Varest, a method for image-token compression that reduces computational load while preserving semantic integrity. Varest uses variable-resolution tokenization guided by semantic fungibility, merging tokens within coherent regions coarsely and maintaining finer distinctions at object boundaries and text. After early decoder processing, learned relevance registers prune visual tokens, enabling a single checkpoint to perform well across multiple budgets and backbones, achieving 86.10‑92.33% of full-token performance with only 5.56% of the original token count.
Hugging Face Trending Papers
Sep 21
VPRune: Efficient Training-free Pre-LLM Visual Token Pruning
Visual token pruning is a promising approach to reducing the inference cost of large vision-language models (LVLMs), yet aggressive token reduction often causes substantial performance degradation. We...