AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Talking Points: Describing and Localizing Pixels

Matan Rusanovsky, Shimon Malnick, Shai Avidan

ICLR 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Visual grounding transformers · 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 Gaussian attention masks to the Point Descriptor (ablation)Point Descriptor · LlamaPointInPart testmPCK: 23.63 -> 78.13Improved
add LoRA adaptation of the language model in the Point Localizer (ablation)Point Localizer · LlamaPointInPart testmPCK: 47.60 -> 78.83Improved
add localization-based GRPO fine-tuning (train on Bovidae, test on Canidae)TP zero-shot · AP-10K CanidaemPCK: 29.85 -> 29.96No clear effect
add localization-based GRPO fine-tuning (train on Canidae, test on Bovidae)TP zero-shot · AP-10K BovidaemPCK: 28.56 -> 30.36Improved
replace OMG-LLaVA descriptions with TP generated descriptionsPoint Localizer · LlamaPointInPart testmPCK: 31.03 -> 78.13Improved
replace DAM descriptions with TP generated descriptionsPoint Localizer · LlamaPointInPart testmPCK: 42.87 -> 78.13Improved
use TP generated descriptions instead of ground-truth descriptionsPoint Localizer · LlamaPointInPart testmPCK: 78.83 -> 78.13No clear effect
use TP descriptions instead of ChatGPT-5 descriptionsPoint Localizer · LlamaPointInPart 100-sample subsetmPCK (%): 62% -> 78%Improved
use TP descriptions instead of human descriptionsPoint Localizer · LlamaPointInPart 100-sample subsetmPCK (%): 56% -> 78%Improved

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