Before Words, Beyond Speech: Evaluating Nonverbal Social Reasoning in Early Childhood
cs.CV, cs.AI, cs.LG
Submitted: 2026-11-09
Updated: 2026-11-13
Code: https://github.com/unslothai/unsloth
Project page: https://laubravo.github.io/nest_website
Terminology
Sources
- Qwen3-VL Technical Report
- SIV-Bench: A Video Benchmark for Social Interaction Understanding and Reasoning
- Mind the Motions: Benchmarking Theory-of-Mind in Everyday Body Language
- The BabyView dataset: High-resolution egocentric videos of infants' and young children's everyday experiences
- R^3-VQA: "Read the Room" by Video Social Reasoning
- Qwen3 Technical Report
- BabyVLM-V2: Toward Developmentally Grounded Pretraining and Benchmarking of Vision Foundation Models
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs