AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Afford-X: Generalizable and Slim Affordance Reasoning for Task-Oriented Manipulation

Xiaomeng Zhu, Yuyang Li, Leiyao Cui, Pengfei Li, Huan-ang Gao, Yixin Zhu, Hao Zhao

TPAMI 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Chain-of-thought multimodal reasoning · 5 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 VA and BF modules to MDETRMDETR · COCO-TasksmAP box: 41.3 -> 43.2Improved
add VA module (verb-pronoun input) (ablation)baseline (no VA, BF) · COCO-Tasks verb-pronounmAP box: 41.3 -> 43.2Improved
add BF module (verb-pronoun input) (ablation)baseline (no VA, BF) · COCO-Tasks verb-pronounmAP box: 41.3 -> 43.0Improved
add both VA and BF (verb-pronoun) (ablation)baseline · COCO-Tasks verb-pronounmAP box: 41.3 -> 43.4Improved
add both VA and BF (verb-noun) (ablation)baseline · COCO-Tasks verb-nounmAP box: 53.2 -> 54.8Improved
add both VA and BF (distill setting) (ablation)baseline · COCO-Tasks distillmAP box: 44.1 -> 45.3Improved
add noun-pronoun distillation through clustered intermediate features (ablation)MDETR · COCO-TasksmAP box: 41.3 -> 44.1Improved
distill noun to pronoun directly instead of via cluster features (ablation)MDETR · COCO-TasksmAP box: 44.1 -> 41.9Hurt
add SBTL alone to baseline (ablation)MDETR · COCO-TasksmAP box: 41.3 -> 43.4Improved
add CL alone to baseline (ablation)MDETR · COCO-TasksmAP box: 41.3 -> 42.0Improved
add CCR, CL and SBTL together (ablation)MDETR · COCO-TasksmAP box: 41.3 -> 44.1Improved
vary cluster number K from 1 to 10 (ablation)distillation · COCO-TasksmAP boxImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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