Picture for Zhoujun Li

Zhoujun Li

A Survey on Latent Reasoning

Add code
Jul 08, 2025
Viaarxiv icon

DinoCompanion: An Attachment-Theory Informed Multimodal Robot for Emotionally Responsive Child-AI Interaction

Add code
Jun 14, 2025
Viaarxiv icon

Act-as-Pet: Benchmarking the Abilities of Large Language Models as E-Pets in Social Network Services

Add code
Jun 04, 2025
Viaarxiv icon

SNS-Bench-VL: Benchmarking Multimodal Large Language Models in Social Networking Services

Add code
May 29, 2025
Viaarxiv icon

VLM Can Be a Good Assistant: Enhancing Embodied Visual Tracking with Self-Improving Vision-Language Models

Add code
May 28, 2025
Viaarxiv icon

Hierarchical Instruction-aware Embodied Visual Tracking

Add code
May 27, 2025
Viaarxiv icon

U2-BENCH: Benchmarking Large Vision-Language Models on Ultrasound Understanding

Add code
May 23, 2025
Viaarxiv icon

P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmark

Add code
May 21, 2025
Viaarxiv icon

KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation

Add code
May 21, 2025
Viaarxiv icon

What are they talking about? Benchmarking Large Language Models for Knowledge-Grounded Discussion Summarization

Add code
May 18, 2025
Viaarxiv icon