arXiv AI
Mitigating Cross-Image Information Leakage in Multi-Image Understanding with Large Vision-Language Models
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 2
On the Limits of Token Reduction for Efficient Unified Vision Language Training
arXiv:2606. 01503v1 Announce Type: cross Abstract: Unified vision-language models (VLMs) integrate visual understanding and visual generation within a single autoregressive backbone, but their joint training is computationally expensive and largely overlooked from an efficiency perspective.
arXiv AI
Jun 19
The Hidden Evolution of Disguised Visual Context inside the VLM
arXiv:2606. 20077v1 Announce Type: cross Abstract: Visual tokens enter Large Language Models (LLMs) as raw, foreign signals.
arXiv AI
Sep 2
Revealing Multi-View Hallucination in Large Vision-Language Models
The paper introduces the concept of multi-view hallucination (MVH), where large vision-language models produce incorrect answers when processing images from multiple viewpoints. It presents MVH-Bench, a benchmark of 4.8k question-answer pairs that target cross-instance and cross-view hallucinations, and shows that MVH is common across recent models. The authors propose Reference Shift Contrastive Decoding (RSCD), a training-free decoding method that mitigates visual interference, achieving significant performance gains on MVH-Bench with LLaVA-OneVision and Qwen2.5-VL.
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.
arXiv Computer Vision
Sep 1
Phantom-Insight: Adaptive Multi-cue Fusion for Video Camouflaged Object Detection with Multimodal LLM
arXiv:2509.06422v2 Announce Type: replace Abstract: Video camouflaged object detection (VCOD) is challenging due to dynamic environments. Existing methods face two main issues: (1) SAM-based methods...
arXiv AI
Sep 16
VideoMM: Adaptive Macro-Micro Inference for Efficient Video MLLMs
arXiv:2609.16722v1 Announce Type: new Abstract: Scaling Multimodal Large Language Models (MLLMs) to long-form video understanding is bottlenecked by the explosion of visual tokens, which saturates co...