AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

On Locality and Length-Generalization in Visual Reasoning

Pulkit Madan, Sanjay Haresh, Reza Ebrahimi, Apratim Bhattacharyya, Sunny Panchal, Roland Memisevic

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: VLM capability analysis · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add local high-res glimpses to global-view VLM (ablation)Qwen-VL · Finding Zeros OOD-numrootsaccuracy (%): 32.63 -> 67.12Improved
add local glimpses to global-view VLM (ablation)Qwen-VL · Finding Zeros In-distributionaccuracy (%): 57.24 -> 82.26Improved
add local glimpses (multi-function split) (ablation)Qwen-VL · Finding Zeros multi-function OOD-numrootsaccuracy (%): 1.06 -> 63.66Improved
raise global glimpse resolution from 600x400 to 1200x800 with local glimpses (ablation)Foveated Qwen-VL · Finding Zeros OOD-subplots+numrootsaccuracy (%): 59.70 -> 57.46Hurt
replace global full image with local+peripheral glimpses (recurrent model) (ablation)Recurrent foveation model · Visual Parity / State Machine OODsuccess rateImproved
use nonlinear recurrent backbone instead of transformer, Mamba, xLSTM on local glimpses (ablation)Recurrent foveation model · State Machine OODsuccess rateImproved
fine-tune global-view Qwen-VL on Visual Parity/State MachineQwen-VL · Visual Parity / State Machine OODsuccess rateHurt
vary peripheral glimpse resolution and size (ablation)Recurrent foveation model · Visual Parityaccuracy / stepsMixed
use global model instead of foveated model on conjunctive search (recall)Qwen-VL · Conjunctive Search (recall)accuracyImproved
add black-dot marks on visited switches as external memory (ablation)Recurrent foveation model · Visual Parity without arrowstrainabilityImproved
uniformly raise global resolution at matched compute (ablation)Qwen-VL · Finding Zerosaccuracy (%)No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy