Research map / Video / Video generation
Towards Closed-Loop Embodied Empathy Evolution: Probing LLM-Centric Lifelong Empathic Motion Generation in Unseen Scenarios
Jiawen Wang, Jingjing Wang, Tianyang Chen, Min Zhang, Guodong Zhou
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add causal-guided emotion decoupling block (ablation) | ES-MoE · L2-EMG Unseen | AWF: 0.312 -> 0.340 | Improved |
| add causal-guided emotion decoupling block (ablation) | ES-MoE · L2-EMG Mixed | AF: 1.70 -> 1.39 | Improved |
| add scenario-adapted MoE experts (ablation) | ES-MoE · L2-EMG Unseen | AF: 2.48 -> 1.89 | Improved |
| add scenario-adapted MoE experts (ablation) | ES-MoE · L2-EMG Unseen | FR: 3.26 -> -1.03 | Improved |
| add emotion classification loss Lemo (ablation) | ES-MoE · L2-EMG Unseen | AWF: 0.326 -> 0.340 | Improved |
| add emotion classification loss Lemo (ablation) | ES-MoE · L2-EMG Mixed | AR: 0.237 -> 0.259 | Improved |
| ES-MoE vs best baseline SAPT | ES-MoE · L2-EMG Unseen | AF: 2.12 -> 1.89 | Improved |
| ES-MoE vs multi-task learning upper bound | ES-MoE · L2-EMG Unseen | AF: 1.05 vs 1.89 | Hurt |
| ES-MoE vs SAPT on multimodality | ES-MoE · L2-EMG Unseen | AMM: 1.59 vs 1.47 | No clear effect |
Closest papers by meaning
- Nano-EmoX: Unifying Multimodal Emotional Intelligence from Perception to Empathy (CVPR 2026 · similarity 0.84)
- Apathetic or Empathetic? Evaluating LLMs' Emotional Alignments with Humans (NeurIPS 2024 · similarity 0.84)
- $E^3$: Exploring Embodied Emotion Through A Large-Scale Egocentric Video Dataset (NeurIPS 2024 · similarity 0.84)
- CAREBench: Evaluating LLMs' Emotion Understanding by Assessing Cognitive Appraisal Reasoning (NeurIPS 2026 · similarity 0.82)
- EmpathyChat: Structured Cognitive Reasoning in Empathetic Spoken Dialogue (NeurIPS 2026 · similarity 0.82)
- RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents (ICLR 2026 · similarity 0.81)
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.
