77 citations · 188 across the 14 of their papers we have counts for
14 papers
ORIC: Benchmarking Object Recognition under Contextual Incongruity in Large Vision-Language Models
Zhaoyang Li, Zhan Ling, Yuchen Zhou +3
Large Vision-Language Models (LVLMs) excel at captioning, visual question answering, and robotics by combining vision and language, yet they often miss obvious objects or hallucina…
Unleashing the Creative Mind: Language Model As Hierarchical Policy For Improved Exploration on Challenging Problem Solving
Zhan Ling, Yunhao Fang, Xuanlin Li +5
Large Language Models (LLMs) have achieved tremendous progress, yet they still often struggle with challenging reasoning problems. Current approaches address this challenge by samp…
Reparameterized Policy Learning for Multimodal Trajectory Optimization
Zhiao Huang, Litian Liang, Zhan Ling +3
We investigate the challenge of parametrizing policies for reinforcement learning (RL) in high-dimensional continuous action spaces. Our objective is to develop a multimodal policy…
Distilling Large Vision-Language Model with Out-of-Distribution Generalizability
Xuanlin Li, Yunhao Fang, Minghua Liu +3
Large vision-language models have achieved outstanding performance, but their size and computational requirements make their deployment on resource-constrained devices and time-sen…
On the Efficacy of 3D Point Cloud Reinforcement Learning
Zhan Ling, Yunchao Yao, Xuanlin Li +1
Recent studies on visual reinforcement learning (visual RL) have explored the use of 3D visual representations. However, none of these work has systematically compared the efficacy…
Deductive Verification of Chain-of-Thought Reasoning
Zhan Ling, Yunhao Fang, Xuanlin Li +4
Large Language Models (LLMs) significantly benefit from Chain-of-Thought (CoT) prompting in performing various reasoning tasks. While CoT allows models to produce more comprehensiv…
ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills
Jiayuan Gu, Fanbo Xiang, Xuanlin Li +12
Generalizable manipulation skills, which can be composed to tackle long-horizon and complex daily chores, are one of the cornerstones of Embodied AI. However, existing benchmarks,…
PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models
Minghua Liu, Yinhao Zhu, Hong Cai +4
Generalizable 3D part segmentation is important but challenging in vision and robotics. Training deep models via conventional supervised methods requires large-scale 3D datasets wi…
Frame Mining: a Free Lunch for Learning Robotic Manipulation from 3D Point Clouds
Minghua Liu, Xuanlin Li, Zhan Ling +2
We study how choices of input point cloud coordinate frames impact learning of manipulation skills from 3D point clouds. There exist a variety of coordinate frame choices to normal…
Improving Policy Optimization with Generalist-Specialist Learning
Zhiwei Jia, Xuanlin Li, Zhan Ling +3
Generalization in deep reinforcement learning over unseen environment variations usually requires policy learning over a large set of diverse training variations. We empirically ob…
Approximate Convex Decomposition for 3D Meshes with Collision-Aware Concavity and Tree Search
Xinyue Wei, Minghua Liu, Zhan Ling +1
Approximate convex decomposition aims to decompose a 3D shape into a set of almost convex components, whose convex hulls can then be used to represent the input shape. It thus enab…
Close the Optical Sensing Domain Gap by Physics-Grounded Active Stereo Sensor Simulation
Xiaoshuai Zhang, Rui Chen, Ang Li +11
In this paper, we focus on the simulation of active stereovision depth sensors, which are popular in both academic and industry communities. Inspired by the underlying mechanism of…
ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations
Tongzhou Mu, Zhan Ling, Fanbo Xiang +6
Object manipulation from 3D visual inputs poses many challenges on building generalizable perception and policy models. However, 3D assets in existing benchmarks mostly lack the di…
State Alignment-based Imitation Learning
Fangchen Liu, Zhan Ling, Tongzhou Mu +1
Consider an imitation learning problem that the imitator and the expert have different dynamics models. Most of the current imitation learning methods fail because they focus on im…