← Back to all news
arXiv Computer Vision By Barbara Toniella Corradini (AI for Good), Caterina Gallegati (University of Siena, Italy), Ludovica Genovese (AI for Good), Vittorio Murino (AI for Good)

From What to Which: Decoding Modifier Grounding in Frozen MLLMs

Read the original on arXiv Computer Vision →

The paper investigates whether frozen Multimodal Large Language Models (MLLMs) encode grounding information about specific visual instances within the tokens they generate, including modifiers such as attributes, spatial expressions, and relational terms. The authors introduce OTTER, a lightweight supervised probe that applies Optimal Transport to align generated tokens with visual regions, producing compact grounding maps. Experiments demonstrate that modifier tokens, especially spatial terms, carry instance‑discriminative visual information, that object nouns also encode referential cues, and that the recovered grounding remains robust to context changes and generalizes to free generation and cross‑dataset transfer.

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 Computer Vision.

Related stories

arXiv Computer Vision
Sep 22

DeCo: Efficient Decouple-to-Couple Learning for Multi-Task Visual Grounding

DeCo introduces an efficient decouple-to-couple learning framework for multi-task visual grounding, addressing conflicts between localization and segmentation tasks. It first applies Task-aware Semantic Decoupling (TSD) to separate shared visual cues into task-specific features guided by salient words, then uses Hybrid Prior Coupling (HPC) to merge sentence-level semantic priors with mask-derived spatial priors for improved grounding. Experiments across multiple natural and remote sensing datasets show that DeCo achieves state‑of‑the‑art performance while requiring only lightweight trainable parameters on a frozen multimodal encoder.

By Xiaoqiang Lu, Licheng Jiao, Long Sun, Yuting Yang, Xu Liu, Lingling Li, Wenping Ma, Fang Liu
llmscomputer-visionmultimodalbenchmarks
More like this →
arXiv Machine Learning
2d ago

S-Space: Exploring Spatial Workspace in Multimodal Language Models

The paper introduces S‑Space, a linear subspace within multimodal language models where object‑token representations encode continuous spatial coordinates along horizontal, vertical, and distance axes. This subspace is intrinsic, readable under non‑spatial queries, and serves as an internal spatial workspace: perception maps object locations into it, reasoning transforms it for viewpoint changes, and verbal responses selectively access it. Diagnostic experiments using S‑Space reveal that while models can form spatial representations, they struggle with spatial transformations needed for reliable reasoning across viewpoint changes.

By Zhiyuan Shi, Xiang Li, Xingzhuo Guo, Shangchen Miao, Weiliang Chen, Qiyu Dai, Jinshan Ren, Jiangran Lyu, Fangfu Liu, Mingsheng Long, Jialong Wu
llmsmultimodal
More like this →