no code implementations • 10 Jun 2024 • Jiaming Ji, Kaile Wang, Tianyi Qiu, Boyuan Chen, Jiayi Zhou, Changye Li, Hantao Lou, Yaodong Yang
Empirically, we demonstrate the elasticity of post-alignment models, i. e., the tendency to revert to the behavior distribution formed during the pre-training phase upon further fine-tuning.
2 code implementations • 8 Jun 2024 • Minghao Shao, Sofija Jancheska, Meet Udeshi, Brendan Dolan-Gavitt, Haoran Xi, Kimberly Milner, Boyuan Chen, Max Yin, Siddharth Garg, Prashanth Krishnamurthy, Farshad Khorrami, Ramesh Karri, Muhammad Shafique
Large Language Models (LLMs) are being deployed across various domains today.
no code implementations • 29 May 2024 • Fengshuo Bai, Mingzhi Wang, Zhaowei Zhang, Boyuan Chen, Yinda Xu, Ying Wen, Yaodong Yang
This paper explores an efficient method for aligning black-box large models using smaller models, introducing a model-agnostic and lightweight Bayesian Persuasion Alignment framework.
no code implementations • 24 May 2024 • Boyuan Chen, Mingzhi Zhu, Brendan Dolan-Gavitt, Muhammad Shafique, Siddharth Garg
Meanwhile, model cascading has been proven effective to conserve computational resources while enhancing accuracy in LLMs on natural language generation tasks.
no code implementations • 16 Apr 2024 • Ahmed E. Hassan, Gustavo A. Oliva, Dayi Lin, Boyuan Chen, Zhen Ming, Jiang
We envision AI pair programmers that are goal-driven, human partners, SE-aware, and self-learning.
no code implementations • 4 Apr 2024 • Kairui Ding, Boyuan Chen, Ruihai Wu, Yuyang Li, Zongzheng Zhang, Huan-ang Gao, Siqi Li, Yixin Zhu, Guyue Zhou, Hao Dong, Hao Zhao
Robotic manipulation of ungraspable objects with two-finger grippers presents significant challenges due to the paucity of graspable features, while traditional pre-grasping techniques, which rely on repositioning objects and leveraging external aids like table edges, lack the adaptability across object categories and scenes.
no code implementations • 25 Feb 2024 • Ahmed E. Hassan, Dayi Lin, Gopi Krishnan Rajbahadur, Keheliya Gallaba, Filipe R. Cogo, Boyuan Chen, Haoxiang Zhang, Kishanthan Thangarajah, Gustavo Ansaldi Oliva, Jiahuei Lin, Wali Mohammad Abdullah, Zhen Ming Jiang
Finally, we (i) show how the unique properties of FMArts enabled us to design and develop a complex FMware for a large customer in a timely manner and (ii) discuss the lessons that we learned in doing so.
no code implementations • 4 Feb 2024 • Jiaming Ji, Boyuan Chen, Hantao Lou, Donghai Hong, Borong Zhang, Xuehai Pan, Juntao Dai, Tianyi Qiu, Yaodong Yang
However, the tension between the complexity of current alignment methods and the need for rapid iteration in deployment scenarios necessitates the development of a model-agnostic alignment approach that can operate under these constraints.
2 code implementations • 24 Jan 2024 • Suning Huang, Boyuan Chen, Huazhe Xu, Vincent Sitzmann
Inspired by nature and recent novel robot designs, we propose to go a step further and explore the novel reconfigurable robots, defined as robots that can change their morphology within their lifetime.
no code implementations • CVPR 2024 • Boyuan Chen, Zhuo Xu, Sean Kirmani, Brian Ichter, Danny Driess, Pete Florence, Dorsa Sadigh, Leonidas Guibas, Fei Xia
By training a VLM on such data, we significantly enhance its ability on both qualitative and quantitative spatial VQA.
1 code implementation • 23 Dec 2023 • Gabe Guo, Judah Goldfeder, Ling Lan, Aniv Ray, Albert Hanming Yang, Boyuan Chen, Simon JL Billinge, Hod Lipson
The revolution in materials in the past century was built on a knowledge of the atomic arrangements and the structure-property relationship.
no code implementations • 30 Oct 2023 • Jiaming Ji, Tianyi Qiu, Boyuan Chen, Borong Zhang, Hantao Lou, Kaile Wang, Yawen Duan, Zhonghao He, Jiayi Zhou, Zhaowei Zhang, Fanzhi Zeng, Kwan Yee Ng, Juntao Dai, Xuehai Pan, Aidan O'Gara, Yingshan Lei, Hua Xu, Brian Tse, Jie Fu, Stephen Mcaleer, Yaodong Yang, Yizhou Wang, Song-Chun Zhu, Yike Guo, Wen Gao
The former aims to make AI systems aligned via alignment training, while the latter aims to gain evidence about the systems' alignment and govern them appropriately to avoid exacerbating misalignment risks.
1 code implementation • 5 Jul 2023 • Zhaofeng Wu, Linlu Qiu, Alexis Ross, Ekin Akyürek, Boyuan Chen, Bailin Wang, Najoung Kim, Jacob Andreas, Yoon Kim
The impressive performance of recent language models across a wide range of tasks suggests that they possess a degree of abstract reasoning skills.
3 code implementations • 7 Feb 2023 • Haoran Zhu, Boyuan Chen, Carter Yang
Vision transformer (ViT) is an attention neural network architecture that is shown to be effective for computer vision tasks.
no code implementations • 4 Oct 2022 • Ray Chen Zheng, Kaizhe Hu, Zhecheng Yuan, Boyuan Chen, Huazhe Xu
To tackle this problem, we introduce Extraneousness-Aware Imitation Learning (EIL), a self-supervised approach that learns visuomotor policies from third-person demonstrations with extraneous subsequences.
no code implementations • 3 Oct 2022 • Yunxiang Zhang, Benjamin Liang, Boyuan Chen, Paul Torrens, S. Farokh Atashzar, Dahua Lin, Qi Sun
Closing the gap between real-world physicality and immersive virtual experience requires a closed interaction loop: applying user-exerted physical forces to the virtual environment and generating haptic sensations back to the users.
no code implementations • 20 Sep 2022 • Boyuan Chen, Fei Xia, Brian Ichter, Kanishka Rao, Keerthana Gopalakrishnan, Michael S. Ryoo, Austin Stone, Daniel Kappler
Large language models (LLMs) have unlocked new capabilities of task planning from human instructions.
no code implementations • 5 Sep 2022 • Robert Kwiatkowski, Yuhang Hu, Boyuan Chen, Hod Lipson
Self-Modeling is the process by which an agent, such as an animal or machine, learns to create a predictive model of its own dynamics.
no code implementations • 4 Feb 2022 • Yingzhe Lyu, Gopi Krishnan Rajbahadur, Dayi Lin, Boyuan Chen, Zhen Ming, Jiang
Artificial Intelligence for IT Operations (AIOps) has been adopted in organizations in various tasks, including interpreting models to identify indicators of service failures.
1 code implementation • 4 Feb 2022 • Boyuan Chen, Mingzhi Wen, Yong Shi, Dayi Lin, Gopi Krishnan Rajbahadur, Zhen Ming, Jiang
However, DL models are challenging to be reproduced due to issues like randomness in the software (e. g., DL algorithms) and non-determinism in the hardware (e. g., GPU).
1 code implementation • 20 Dec 2021 • Boyuan Chen, Kuang Huang, Sunand Raghupathi, Ishaan Chandratreya, Qiang Du, Hod Lipson
All physical laws are described as relationships between state variables that give a complete and non-redundant description of the relevant system dynamics.
1 code implementation • 11 Nov 2021 • Boyuan Chen, Robert Kwiatkowski, Carl Vondrick, Hod Lipson
Internal computational models of physical bodies are fundamental to the ability of robots and animals alike to plan and control their actions.
no code implementations • 3 Nov 2021 • Gopi Krishnan Rajbahadur, Erika Tuck, Li Zi, Dayi Lin, Boyuan Chen, Zhen Ming, Jiang, Daniel M. German
Publicly available datasets are one of the key drivers for commercial AI software.
1 code implementation • 14 Jun 2021 • Boyuan Chen, Pieter Abbeel, Deepak Pathak
Prior works show that structured latent space such as visual keypoints often outperforms unstructured representations for robotic control.
no code implementations • 26 May 2021 • Boyuan Chen, Yuhang Hu, Lianfeng Li, Sara Cummings, Hod Lipson
At present, progress in this field is hindered by the fact that each facial expression needs to be programmed by humans.
1 code implementation • 17 May 2021 • Boyuan Chen, Mia Chiquier, Hod Lipson, Carl Vondrick
Due to the many ways that robots use containers, we believe the box will have a number of applications in robotics.
no code implementations • 11 May 2021 • Boyuan Chen, Yuhang Hu, Robert Kwiatkowski, Shuran Song, Hod Lipson
We suggest that visual behavior modeling and perspective taking skills will play a critical role in the ability of physical robots to fully integrate into real-world multi-agent activities.
1 code implementation • ICLR 2021 • Boyuan Chen, Yu Li, Sunand Raghupathi, Hod Lipson
Our experiments reveal that high dimensional, high entropy labels achieve comparable accuracy to text (categorical) labels on the standard image classification task, but features learned through our label representations exhibit more robustness under various adversarial attacks and better effectiveness with a limited amount of training data.
2 code implementations • ICLR 2021 • Zhenggang Tang, Chao Yu, Boyuan Chen, Huazhe Xu, Xiaolong Wang, Fei Fang, Simon Du, Yu Wang, Yi Wu
We propose a simple, general and effective technique, Reward Randomization for discovering diverse strategic policies in complex multi-agent games.
1 code implementation • 8 Dec 2020 • Yiqing Liang, Boyuan Chen, Shuran Song
We introduce SSCNav, an algorithm that explicitly models scene priors using a confidence-aware semantic scene completion module to complete the scene and guide the agent's navigation planning.
1 code implementation • CVPR 2020 • Dave Epstein, Boyuan Chen, Carl Vondrick
We train a supervised neural network as a baseline and analyze its performance compared to human consistency on the tasks.
1 code implementation • 17 Oct 2019 • Huazhe Xu, Boyuan Chen, Yang Gao, Trevor Darrell
The agent is first presented with previous experiences in the training environment, along with task description in the form of trajectory-level sparse rewards.
no code implementations • 15 Oct 2019 • Boyuan Chen, Shuran Song, Hod Lipson, Carl Vondrick
We train embodied agents to play Visual Hide and Seek where a prey must navigate in a simulated environment in order to avoid capture from a predator.
no code implementations • 25 Sep 2019 • Huazhe Xu, Boyuan Chen, Yang Gao, Trevor Darrell
In this paper, we propose Scoring-Aggregating-Planning (SAP), a framework that can learn task-agnostic semantics and dynamics priors from arbitrary quality interactions as well as the corresponding sparse rewards and then plan on unseen tasks in zero-shot condition.
1 code implementation • 29 Jun 2018 • Iretiayo Akinola, Jacob Varley, Boyuan Chen, Peter K. Allen
This framework greatly improves the performance of standard online grasp planning algorithms by incorporating a notion of reachability into the online grasp planning process.
Robotics
no code implementations • 2 Mar 2018 • Boyuan Chen, Harvey Wu, Warren Mo, Ishanu Chattopadhyay, Hod Lipson
We introduce an automatic machine learning (AutoML) modeling architecture called Autostacker, which combines an innovative hierarchical stacking architecture and an Evolutionary Algorithm (EA) to perform efficient parameter search.
no code implementations • ICLR 2018 • Boyuan Chen, Warren Mo, Ishanu Chattopadhyay, Hod Lipson
We significantly reduce the time of AutoML with a naturally inspired algorithm - Parallel Hill Climbing (PHC).