6 papers
DeepTutor: Towards Agentic Personalized Tutoring
Bingxi Zhao, Jiahao Zhang, Xubin Ren +4
Education is one of the most promising real-world applications for Large Language Models (LLMs). However, current LLMs rely on static pre-training knowledge and lack adaptation to…
DexHoldem: Playing Texas Hold'em with Dexterous Embodied System
Feng Chen, Tianzhe Chu, Li Sun +6
Evaluating embodied systems on real dexterous hardware requires more than isolated primitive skills: an agent must perceive a changing tabletop scene, choose a context-appropriate…
Pointer-CAD: Unifying B-Rep and Command Sequences via Pointer-based Edges & Faces Selection
Dacheng Qi, Chenyu Wang, Jingwei Xu +6
Constructing computer-aided design (CAD) models is labor-intensive but essential for engineering and manufacturing. Recent advances in Large Language Models (LLMs) have inspired th…
GenDexHand: Generative Simulation for Dexterous Hands
Feng Chen, Zhuxiu Xu, Tianzhe Chu +7
Data scarcity remains a fundamental bottleneck for embodied intelligence. Existing approaches use large language models (LLMs) to automate gripper-based simulation generation, but…
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
Tianzhe Chu, Yuexiang Zhai, Jihan Yang +6
Supervised fine-tuning (SFT) and reinforcement learning (RL) are widely used post-training techniques for foundation models. However, their roles in enhancing model generalization…
Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs
Chun-Hsiao Yeh, Chenyu Wang, Shengbang Tong +7
Multi-view understanding, the ability to reconcile visual information across diverse viewpoints for effective navigation, manipulation, and 3D scene comprehension, is a fundamental…