← Back to all news
arXiv Machine Learning By Ishani Janveja, Davis Zhang, Seoyul Oh, Deepak Vasisht

Exploiting answer-invariant redundancies in satellite imagery for efficient VLM inference on edge

Read the original on arXiv Machine Learning →

The paper introduces Rift, a two‑stage system that reduces the computational load of vision‑language models on satellites by pruning image tiles that do not affect the answer and then applying elastic prefill to limit token usage. By exploiting answer‑invariant token redundancy, Rift cuts energy consumption by 78 % and latency by 69 % compared to exhaustive tiled inference, while boosting accuracy from 45 % to 73 % on LLaVA‑1.5 7B running on a Jetson AGX Orin.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Jun 11

AVIS: Adaptive Test-Time Scaling for Vision-Language Models

arXiv:2606. 11576v1 Announce Type: cross Abstract: Modern Vision-Language Models (VLMs) benefit from chain-of-thought prompting and test-time scaling, but these gains often come with prohibitive inference cost due to large visual contexts and long decoding chains.

By Ahmadreza Jeddi, Minh Ngoc Le, Amirhossein Kazerouni, Hakki Can Karaimer, Hue Nguyen, Iqbal Mohomed, Michael Brudno, Alex Levinshtein, Konstantinos G. Derpanis, Babak Taati, Radek Grzeszczuk
llmsreinforcement-learningefficiencymultimodalbenchmarks
More like this →
arXiv AI
Aug 28

PACE: A Unified Condense-and-Extract Paradigm for Fast VLM Inference

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
llmsefficiencymultimodal
More like this →
arXiv Computer Vision
Aug 28

Multi-Image Visual Token Pruning in Large Visual Language Models

The paper introduces Adaptive Visual Token Pruning (AVTP), a training‑free framework that dynamically selects pruning layers and ratios for large vision‑language models (LVLMs) when processing multiple image sequences. By analyzing visual attention distributions across different LVLM architectures, AVTP adapts token retention to image importance, enabling efficient inference without relying on attention‑based computations incompatible with FlashAttention. Experiments show significant speedups—up to 2× for Qwen3VL‑8B—while preserving or even improving accuracy on multi‑image benchmarks.

By Rongyang Zhang, Chengqiang Lu, Cong Li, Hongchao Gu, Tingjia Shen, Xuyang Zhi, Qimeng Wang, Yan Gao, Yi Wu, Yao Hu, Hao Wang, Enhong Chen
llmsefficiencybenchmarks
More like this →