AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

Hulk: A Universal Knowledge Translator for Human-Centric Tasks

Yizhou Wang, Yixuan Wu, Weizhen He, Xun Guo, Feng Zhu, Lei Bai, Rui Zhao, Jian Wu, Tong He, Wanli Ouyang, Shixiang Tang

TPAMI 2025 · Vision-language and multimodal › Robot action and navigation · approach: Embodied multimodal LLM agents · 33 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
share modality tokenizers instead of dataset-specific ones (ablation)Hulk · 8-task ablation averageaverage score: 41.1 -> 41.8Improved
share decoder parameters in addition to encoder (ablation)Hulk · 8-task ablation averageaverage score: 29.0 -> 41.1Improved
share decoder parameters in addition to encoder (ablation)Hulk · NTU60-XSubAcc: 1.7 -> 93.8Improved
add 2D pose task to joint training (ablation)Hulk · CrowdHumanAP: 52.6 -> 71.6Improved
add 3D pose task to joint training (ablation)Hulk · CrowdHumanAP: 52.6 -> 57.8Improved
add 2D pose task to joint training (ablation)Hulk · RAPv2mA: 75.4 -> 78.7Improved
add 2D pose task to joint training (ablation)Hulk · NTU60-XSubAcc: 93.1 -> 93.5No clear effect
add 2D pose task to training (ablation)Hulk · CrowdHumanAP: 65.0 -> 81.8Improved
add 2D pose task to training (ablation)Hulk · 3DPW mesh100-MPVPE: -18.9 -> -0.3Improved
add parsing task to training (ablation)Hulk · LIP parsingmIoU: 56.8 -> 57.4Hurt
add detection task to training (ablation)Hulk · AIC 2D poseAP: 26.4 -> 25.5Hurt
add mesh and 3D pose tasks to training (ablation)Hulk · 8-task averageaverage score: -0.1No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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