Yuandong Tian

261 papers A* 88A 6B 2Journal 148Unranked 16
YearRankTypeTitle / Venue / Authors
2026 J jnl
AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications.
CoRR
Yujie Zhao, Boqin Yuan, Junbo Huang, Haocheng Yuan, Zhongming Yu, Haozhou Xu, Lanxiang Hu, Abhilash Shankarampeta, Zimeng Huang, Wentao Ni, Yuandong Tian, Jishen Zhao
2026 J jnl
Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Training.
CoRR
Yixin Liu, Yue Yu, DiJia Su, Sid Wang, Xuewei Wang, Song Jiang, Bo Liu, Arman Cohan, Yuandong Tian, Zhengxing Chen
2026 J jnl
STEM: Scaling Transformers with Embedding Modules.
CoRR
Ranajoy Sadhukhan, Sheng Cao, Harry Dong, Changsheng Zhao, Attiano Purpura-Pontoniere, Yuandong Tian, Zechun Liu, Beidi Chen
2025 A* conf
AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs.
ICML
Anselm Paulus, Arman Zharmagambetov, Chuan Guo, Brandon Amos, Yuandong Tian
2025 A* conf
Agent-as-a-Judge: Evaluate Agents with Agents.
ICML
Mingchen Zhuge, Changsheng Zhao, Dylan R. Ashley, Wenyi Wang, Dmitrii Khizbullin, Yunyang Xiong, Zechun Liu, Ernie Chang, Raghuraman Krishnamoorthi, Yuandong Tian, Yangyang Shi, Vikas Chandra, Jürgen Schmidhuber
2025 J jnl
Deep Think with Confidence.
CoRR
Yichao Fu, Xuewei Wang, Yuandong Tian, Jiawei Zhao
2025 A* conf
Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces.
ICLR
DiJia Su, Sainbayar Sukhbaatar, Michael Rabbat, Yuandong Tian, Qinqing Zheng
2025 J jnl
Emergence of Superposition: Unveiling the Training Dynamics of Chain of Continuous Thought.
CoRR
Hanlin Zhu, Shibo Hao, Zhiting Hu, Jiantao Jiao, Stuart Russell, Yuandong Tian
2025 A* conf
From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications.
ICML
Ajay Kumar Jaiswal, Yifan Wang, Lu Yin, Shiwei Liu, Runjin Chen, Jiawei Zhao, Ananth Grama, Yuandong Tian, Zhangyang Wang
2025 J jnl
GSM-Infinite: How Do Your LLMs Behave over Infinitely Increasing Context Length and Reasoning Complexity?
CoRR
Yang Zhou, Hongyi Liu, Zhuoming Chen, Yuandong Tian, Beidi Chen
2025 A* conf
GSM-∞: How Do your LLMs Behave over Infinitely Increasing Reasoning Complexity and Context Length?
ICML
Yang Zhou, Hongyi Liu, Zhuoming Chen, Yuandong Tian, Beidi Chen
2025 J jnl
GaLore 2: Large-Scale LLM Pre-Training by Gradient Low-Rank Projection.
CoRR
DiJia Su, Andrew Gu, Jane Xu, Yuandong Tian, Jiawei Zhao
2025 J jnl
Inpainting-Guided Policy Optimization for Diffusion Large Language Models.
CoRR
Siyan Zhao, Mengchen Liu, Jing Huang, Miao Liu, Chenyu Wang, Bo Liu, Yuandong Tian, Guan Pang, Sean Bell, Aditya Grover, Feiyu Chen
2025 J jnl
LLM Pretraining with Continuous Concepts.
CoRR
Jihoon Tack, Jack Lanchantin, Jane Yu, Andrew Cohen, Ilia Kulikov, Janice Lan, Shibo Hao, Yuandong Tian, Jason Weston, Xian Li
2025 J jnl
Language Self-Play For Data-Free Training.
CoRR
Jakub Grudzien Kuba, Mengting Gu, Qi Ma, Yuandong Tian, Vijai Mohan
2025 A* conf
MagicPIG: LSH Sampling for Efficient LLM Generation.
ICLR
Zhuoming Chen, Ranajoy Sadhukhan, Zihao Ye, Yang Zhou, Jianyu Zhang, Niklas Nolte, Yuandong Tian, Matthijs Douze, Léon Bottou, Zhihao Jia, Beidi Chen
2025 A* conf
Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge.
EMNLP
Tianhao Wu, Weizhe Yuan, Olga Golovneva, Jing Xu, Yuandong Tian, Jiantao Jiao, Jason E. Weston, Sainbayar Sukhbaatar
2025 J jnl
MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes.
CoRR
Changsheng Zhao, Ernie Chang, Zechun Liu, Chia-Jung Chang, Wei Wen, Chen Lai, Sheng Cao, Yuandong Tian, Raghuraman Krishnamoorthi, Yangyang Shi, Vikas Chandra
2025 J jnl
NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions.
CoRR
Weizhe Yuan, Jane Yu, Song Jiang, Karthik Padthe, Yang Li, Dong Wang, Ilia Kulikov, Kyunghyun Cho, Yuandong Tian, Jason E. Weston, Xian Li
2025 A* conf
ParamΔ for Direct Mixing: Post-Train Large Language Model At Zero Cost.
ICLR
Sheng Cao, Mingrui Wu, Karthik Prasad, Yuandong Tian, Zechun Liu
2025 J jnl
ParamΔ for Direct Weight Mixing: Post-Train Large Language Model at Zero Cost.
CoRR
Sheng Cao, Mingrui Wu, Karthik Prasad, Yuandong Tian, Zechun Liu
2025 J jnl
ParetoQ: Scaling Laws in Extremely Low-bit LLM Quantization.
CoRR
Zechun Liu, Changsheng Zhao, Hanxian Huang, Sijia Chen, Jing Zhang, Jiawei Zhao, Scott Roy, Lisa Jin, Yunyang Xiong, Yangyang Shi, Lin Xiao, Yuandong Tian, Bilge Soran, Raghuraman Krishnamoorthi, Tijmen Blankevoort, Vikas Chandra
2025 J jnl
Positional Encoding via Token-Aware Phase Attention.
CoRR
Yu Wang, Sheng Shen, Rémi Munos, Hongyuan Zhan, Yuandong Tian
2025 J jnl
Provable Scaling Laws of Feature Emergence from Learning Dynamics of Grokking.
CoRR
Yuandong Tian
2025 — conf
Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.
CPAL
Zhenyu Zhang, Ajay Kumar Jaiswal, Lu Yin, Shiwei Liu, Jiawei Zhao, Yuandong Tian, Zhangyang Wang
2025 A* conf
R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference.
ICLR
Zhenyu Zhang, Zechun Liu, Yuandong Tian, Harshit Khaitan, Zhangyang Wang, Steven Li
2025 J jnl
R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference.
CoRR
Zhenyu Zhang, Zechun Liu, Yuandong Tian, Harshit Khaitan, Zhangyang Wang, Steven Li
2025 J jnl
Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought.
CoRR
Hanlin Zhu, Shibo Hao, Zhiting Hu, Jiantao Jiao, Stuart Russell, Yuandong Tian
2025 J jnl
SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters.
CoRR
Yiping Wang, Hanxian Huang, Yifang Chen, Jishen Zhao, Simon Shaolei Du, Yuandong Tian
2025 J jnl
SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models.
CoRR
Chenyu Wang, Paria Rashidinejad, DiJia Su, Song Jiang, Sid Wang, Siyan Zhao, Cai Zhou, Shannon Zejiang Shen, Feiyu Chen, Tommi S. Jaakkola, Yuandong Tian, Bo Liu
2025 J jnl
SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks.
CoRR
Yifei Zhou, Song Jiang, Yuandong Tian, Jason Weston, Sergey Levine, Sainbayar Sukhbaatar, Xian Li
2025 A* conf
Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking.
ICLR
Paria Rashidinejad, Yuandong Tian
2025 J jnl
Spectral Journey: How Transformers Predict the Shortest Path.
CoRR
Andrew Cohen, Andrey Gromov, Kaiyu Yang, Yuandong Tian
2025 A* conf
SpinQuant: LLM Quantization with Learned Rotations.
ICLR
Zechun Liu, Changsheng Zhao, Igor Fedorov, Bilge Soran, Dhruv Choudhary, Raghuraman Krishnamoorthi, Vikas Chandra, Yuandong Tian, Tijmen Blankevoort
2025 J jnl
Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback.
CoRR
Yen-Ting Lin, Di Jin, Tengyu Xu, Tianhao Wu, Sainbayar Sukhbaatar, Chen Zhu, Yun He, Yun-Nung Chen, Jason Weston, Yuandong Tian, Arash Rahnama, Sinong Wang, Hao Ma, Han Fang
2025 J jnl
Tensor-GaLore: Memory-Efficient Training via Gradient Tensor Decomposition.
CoRR
Robert Joseph George, David Pitt, Jiawei Zhao, Jean Kossaifi, Cheng Luo, Yuandong Tian, Anima Anandkumar
2025 J jnl
The Path Not Taken: RLVR Provably Learns Off the Principals.
CoRR
Hanqing Zhu, Zhenyu Zhang, Hanxian Huang, DiJia Su, Zechun Liu, Jiawei Zhao, Igor Fedorov, Hamed Pirsiavash, Zhizhou Sha, Jinwon Lee, David Z. Pan, Zhangyang Wang, Yuandong Tian, Kai Sheng Tai
2025 J jnl
ThreadWeaver: Adaptive Threading for Efficient Parallel Reasoning in Language Models.
CoRR
Long Lian, Sida Wang, Felix Juefei-Xu, Tsu-Jui Fu, Xiuyu Li, Adam Yala, Trevor Darrell, Alane Suhr, Yuandong Tian, Xi Victoria Lin
2025 A* conf
Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning.
ICML
DiJia Su, Hanlin Zhu, Yingchen Xu, Jiantao Jiao, Yuandong Tian, Qinqing Zheng
2025 J jnl
Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning.
CoRR
DiJia Su, Hanlin Zhu, Yingchen Xu, Jiantao Jiao, Yuandong Tian, Qinqing Zheng
2025 A* conf
Towards General-Purpose Model-Free Reinforcement Learning.
ICLR
Scott Fujimoto, Pierluca D'Oro, Amy Zhang, Yuandong Tian, Michael Rabbat
2025 J jnl
Towards General-Purpose Model-Free Reinforcement Learning.
CoRR
Scott Fujimoto, Pierluca D'Oro, Amy Zhang, Yuandong Tian, Michael Rabbat
2025 — conf
You Only Use Reactive Attention Slice When Retrieving From Long Context.
EMNLP (Findings)
Yun Joon Soh, Hanxian Huang, Yuandong Tian, Jishen Zhao
2024 J jnl
AdvPrefix: An Objective for Nuanced LLM Jailbreaks.
CoRR
Sicheng Zhu, Brandon Amos, Yuandong Tian, Chuan Guo, Ivan Evtimov
2024 J jnl
AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs.
CoRR
Anselm Paulus, Arman Zharmagambetov, Chuan Guo, Brandon Amos, Yuandong Tian
2024 J jnl
Agent-as-a-Judge: Evaluate Agents with Agents.
CoRR
Mingchen Zhuge, Changsheng Zhao, Dylan R. Ashley, Wenyi Wang, Dmitrii Khizbullin, Yunyang Xiong, Zechun Liu, Ernie Chang, Raghuraman Krishnamoorthi, Yuandong Tian, Yangyang Shi, Vikas Chandra, Jürgen Schmidhuber
2024 J jnl
Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping.
CoRR
Lucas Lehnert, Sainbayar Sukhbaatar, Paul McVay, Michael Rabbat, Yuandong Tian
2024 J jnl
Composing Global Optimizers to Reasoning Tasks via Algebraic Objects in Neural Nets.
CoRR
Yuandong Tian
2024 A* conf
Contrastive Predict-and-Search for Mixed Integer Linear Programs.
ICML
Taoan Huang, Aaron M. Ferber, Arman Zharmagambetov, Yuandong Tian, Bistra Dilkina
2024 J jnl
Diffusion World Model.
CoRR
Zihan Ding, Amy Zhang, Yuandong Tian, Qinqing Zheng
2024 J jnl
Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces.
CoRR
DiJia Su, Sainbayar Sukhbaatar, Michael Rabbat, Yuandong Tian, Qinqing Zheng
2024 A* conf
Efficient Streaming Language Models with Attention Sinks.
ICLR
Guangxuan Xiao, Yuandong Tian, Beidi Chen, Song Han, Mike Lewis
2024 J jnl
From GaLore to WeLore: How Low-Rank Weights Non-uniformly Emerge from Low-Rank Gradients.
CoRR
Ajay Jaiswal, Lu Yin, Zhenyu Zhang, Shiwei Liu, Jiawei Zhao, Yuandong Tian, Zhangyang Wang
2024 A* conf
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection.
ICML
Jiawei Zhao, Zhenyu Zhang, Beidi Chen, Zhangyang Wang, Anima Anandkumar, Yuandong Tian
2024 J jnl
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection.
CoRR
Jiawei Zhao, Zhenyu Zhang, Beidi Chen, Zhangyang Wang, Anima Anandkumar, Yuandong Tian
2024 A* conf
GenCO: Generating Diverse Designs with Combinatorial Constraints.
ICML
Aaron M. Ferber, Arman Zharmagambetov, Taoan Huang, Bistra Dilkina, Yuandong Tian
2024 A* conf
H-GAP: Humanoid Control with a Generalist Planner.
ICLR
Zhengyao Jiang, Yingchen Xu, Nolan Wagener, Yicheng Luo, Michael Janner, Edward Grefenstette, Tim Rocktäschel, Yuandong Tian
2024 J jnl
Holding the Line: A Study of Writers' Attitudes on Co-creativity with AI.
CoRR
Morteza Behrooz, Yuandong Tian, William Ngan, Yael Yungster, Justin Wong, David Zax
2024 J jnl
Image Classifier Based Generative Method for Planar Antenna Design.
CoRR
Yang Zhong, Weiping Dou, Andrew Cohen, Dia'a Bisharat, Yuandong Tian, Jiang Zhu, Qing Huo Liu
2024 A* conf
JoMA: Demystifying Multilayer Transformers via Joint Dynamics of MLP and Attention.
ICLR
Yuandong Tian, Yiping Wang, Zhenyu Zhang, Beidi Chen, Simon Shaolei Du
2024 A* conf
Learning Personalized Alignment for Evaluating Open-ended Text Generation.
EMNLP
Danqing Wang, Kevin Yang, Hanlin Zhu, Xiaomeng Yang, Andrew Cohen, Lei Li, Yuandong Tian
2024 A* conf
LoCoCo: Dropping In Convolutions for Long Context Compression.
ICML
Ruisi Cai, Yuandong Tian, Zhangyang Wang, Beidi Chen
2024 J jnl
LoCoCo: Dropping In Convolutions for Long Context Compression.
CoRR
Ruisi Cai, Yuandong Tian, Zhangyang Wang, Beidi Chen
2024 J jnl
MagicPIG: LSH Sampling for Efficient LLM Generation.
CoRR
Zhuoming Chen, Ranajoy Sadhukhan, Zihao Ye, Yang Zhou, Jianyu Zhang, Niklas Nolte, Yuandong Tian, Matthijs Douze, Léon Bottou, Zhihao Jia, Beidi Chen
2024 J jnl
Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge.
CoRR
Tianhao Wu, Weizhe Yuan, Olga Golovneva, Jing Xu, Yuandong Tian, Jiantao Jiao, Jason Weston, Sainbayar Sukhbaatar
2024 A* conf
MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases.
ICML
Zechun Liu, Changsheng Zhao, Forrest N. Iandola, Chen Lai, Yuandong Tian, Igor Fedorov, Yunyang Xiong, Ernie Chang, Yangyang Shi, Raghuraman Krishnamoorthi, Liangzhen Lai, Vikas Chandra
2024 J jnl
MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases.
CoRR
Zechun Liu, Changsheng Zhao, Forrest N. Iandola, Chen Lai, Yuandong Tian, Igor Fedorov, Yunyang Xiong, Ernie Chang, Yangyang Shi, Raghuraman Krishnamoorthi, Liangzhen Lai, Vikas Chandra
2024 A* conf
On the Surprising Effectiveness of Attention Transfer for Vision Transformers.
NeurIPS
Alexander C. Li, Yuandong Tian, Beidi Chen, Deepak Pathak, Xinlei Chen
2024 J jnl
On the Surprising Effectiveness of Attention Transfer for Vision Transformers.
CoRR
Alexander C. Li, Yuandong Tian, Beidi Chen, Deepak Pathak, Xinlei Chen
2024 J jnl
Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.
CoRR
Zhenyu Zhang, Ajay Jaiswal, Lu Yin, Shiwei Liu, Jiawei Zhao, Yuandong Tian, Zhangyang Wang
2024 A* conf
RLCD: Reinforcement Learning from Contrastive Distillation for LM Alignment.
ICLR
Kevin Yang, Dan Klein, Asli Celikyilmaz, Nanyun Peng, Yuandong Tian
2024 J jnl
Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking.
CoRR
Paria Rashidinejad, Yuandong Tian
2024 J jnl
SpinQuant: LLM quantization with learned rotations.
CoRR
Zechun Liu, Changsheng Zhao, Igor Fedorov, Bilge Soran, Dhruv Choudhary, Raghuraman Krishnamoorthi, Vikas Chandra, Yuandong Tian, Tijmen Blankevoort
2024 J jnl
The Perfect Blend: Redefining RLHF with Mixture of Judges.
CoRR
Tengyu Xu, Eryk Helenowski, Karthik Abinav Sankararaman, Di Jin, Kaiyan Peng, Eric Han, Shaoliang Nie, Chen Zhu, Hejia Zhang, Wenxuan Zhou, Zhouhao Zeng, Yun He, Karishma Mandyam, Arya Talabzadeh, Madian Khabsa, Gabriel Cohen, Yuandong Tian, Hao Ma, Sinong Wang, Han Fang
2024 — conf
To the Globe (TTG): Towards Language-Driven Guaranteed Travel Planning.
EMNLP (System Demonstrations)
Da Ju, Song Jiang, Andrew Cohen, Aaron Foss, Sasha Mitts, Arman Zharmagambetov, Brandon Amos, Xian Li, Justine T. Kao, Maryam Fazel-Zarandi, Yuandong Tian
2024 J jnl
To the Globe (TTG): Towards Language-Driven Guaranteed Travel Planning.
CoRR
Da Ju, Song Jiang, Andrew Cohen, Aaron Foss, Sasha Mitts, Arman Zharmagambetov, Brandon Amos, Xian Li, Justine T. Kao, Maryam Fazel-Zarandi, Yuandong Tian
2024 J jnl
Towards Full Delegation: Designing Ideal Agentic Behaviors for Travel Planning.
CoRR
Song Jiang, Da Ju, Andrew Cohen, Sasha Mitts, Aaron Foss, Justine T. Kao, Xian Li, Yuandong Tian
2024 A* conf
Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics.
NeurIPS
Hanlin Zhu, Baihe Huang, Shaolun Zhang, Michael I. Jordan, Jiantao Jiao, Yuandong Tian, Stuart J. Russell
2024 J jnl
Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics.
CoRR
Hanlin Zhu, Baihe Huang, Shaolun Zhang, Michael I. Jordan, Jiantao Jiao, Yuandong Tian, Stuart Russell
2024 J jnl
Training Large Language Models to Reason in a Continuous Latent Space.
CoRR
Shibo Hao, Sainbayar Sukhbaatar, DiJia Su, Xian Li, Zhiting Hu, Jason Weston, Yuandong Tian
2024 A* conf
TravelPlanner: A Benchmark for Real-World Planning with Language Agents.
ICML
Jian Xie, Kai Zhang, Jiangjie Chen, Tinghui Zhu, Renze Lou, Yuandong Tian, Yanghua Xiao, Yu Su
2024 J jnl
TravelPlanner: A Benchmark for Real-World Planning with Language Agents.
CoRR
Jian Xie, Kai Zhang, Jiangjie Chen, Tinghui Zhu, Renze Lou, Yuandong Tian, Yanghua Xiao, Yu Su
2024 J jnl
TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding.
CoRR
Hanshi Sun, Zhuoming Chen, Xinyu Yang, Yuandong Tian, Beidi Chen
2024 J jnl
You Only Use Reactive Attention Slice For Long Context Retrieval.
CoRR
Yun Joon Soh, Hanxian Huang, Yuandong Tian, Jishen Zhao
2023 J jnl
A Cookbook of Self-Supervised Learning.
CoRR
Randall Balestriero, Mark Ibrahim, Vlad Sobal, Ari Morcos, Shashank Shekhar, Tom Goldstein, Florian Bordes, Adrien Bardes, Grégoire Mialon, Yuandong Tian, Avi Schwarzschild, Andrew Gordon Wilson, Jonas Geiping, Quentin Garrido, Pierre Fernandez, Amir Bar, Hamed Pirsiavash, Yann LeCun, Micah Goldblum
2023 A* conf
AutoCAT: Reinforcement Learning for Automated Exploration of Cache-Timing Attacks.
HPCA
Mulong Luo, Wenjie Xiong, Geunbae Lee, Yueying Li, Xiaomeng Yang, Amy Zhang, Yuandong Tian, Hsien-Hsin S. Lee, G. Edward Suh
2023 — conf
DOC: Improving Long Story Coherence With Detailed Outline Control.
ACL (1)
Kevin Yang, Dan Klein, Nanyun Peng, Yuandong Tian
2023 A* conf
Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time.
ICML
Zichang Liu, Jue Wang, Tri Dao, Tianyi Zhou, Binhang Yuan, Zhao Song, Anshumali Shrivastava, Ce Zhang, Yuandong Tian, Christopher Ré, Beidi Chen
2023 J jnl
Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time.
CoRR
Zichang Liu, Jue Wang, Tri Dao, Tianyi Zhou, Binhang Yuan, Zhao Song, Anshumali Shrivastava, Ce Zhang, Yuandong Tian, Christopher Ré, Beidi Chen
2023 A conf
DyFormer : A Scalable Dynamic Graph Transformer with Provable Benefits on Generalization Ability.
SDM
Weilin Cong, Yanhong Wu, Yuandong Tian, Mengting Gu, Yinglong Xia, Chun-cheng Jason Chen, Mehrdad Mahdavi
2023 A* conf
Efficient Planning in a Compact Latent Action Space.
ICLR
Zhengyao Jiang, Tianjun Zhang, Michael Janner, Yueying Li, Tim Rocktäschel, Edward Grefenstette, Yuandong Tian
2023 J jnl
Efficient Streaming Language Models with Attention Sinks.
CoRR
Guangxuan Xiao, Yuandong Tian, Beidi Chen, Song Han, Mike Lewis
2023 J jnl
End-to-end Story Plot Generator.
CoRR
Hanlin Zhu, Andrew Cohen, Danqing Wang, Kevin Yang, Xiaomeng Yang, Jiantao Jiao, Yuandong Tian
2023 J jnl
Extending Context Window of Large Language Models via Positional Interpolation.
CoRR
Shouyuan Chen, Sherman Wong, Liangjian Chen, Yuandong Tian
2023 J jnl
GenCO: Generating Diverse Solutions to Design Problems with Combinatorial Nature.
CoRR
Aaron M. Ferber, Arman Zharmagambetov, Taoan Huang, Bistra Dilkina, Yuandong Tian
2023 J jnl
H
CoRR
Zhenyu Zhang, Ying Sheng, Tianyi Zhou, Tianlong Chen, Lianmin Zheng, Ruisi Cai, Zhao Song, Yuandong Tian, Christopher Ré, Clark W. Barrett, Zhangyang Wang, Beidi Chen
2023 J jnl
H-GAP: Humanoid Control with a Generalist Planner.
CoRR
Zhengyao Jiang, Yingchen Xu, Nolan Wagener, Yicheng Luo, Michael Janner, Edward Grefenstette, Tim Rocktäschel, Yuandong Tian
2023 A* conf
H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.
NeurIPS
Zhenyu Zhang, Ying Sheng, Tianyi Zhou, Tianlong Chen, Lianmin Zheng, Ruisi Cai, Zhao Song, Yuandong Tian, Christopher Ré, Clark W. Barrett, Zhangyang Wang, Beidi Chen
2023 J jnl
JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention.
CoRR
Yuandong Tian, Yiping Wang, Zhenyu Zhang, Beidi Chen, Simon S. Du
2023 A* conf
Klotski: Efficient and Safe Network Migration of Large Production Datacenters.
SIGCOMM
Yihao Zhao, Xiaoxiang Zhang, Hang Zhu, Ying Zhang, Zhaodong Wang, Yuandong Tian, Alex Nikulkov, Joao Ferreira, Xuanzhe Liu, Xin Jin
2023 A* conf
Landscape Surrogate: Learning Decision Losses for Mathematical Optimization Under Partial Information.
NeurIPS
Arman Zharmagambetov, Brandon Amos, Aaron M. Ferber, Taoan Huang, Bistra Dilkina, Yuandong Tian
2023 J jnl
Landscape Surrogate: Learning Decision Losses for Mathematical Optimization Under Partial Information.
CoRR
Arman Zharmagambetov, Brandon Amos, Aaron M. Ferber, Taoan Huang, Bistra Dilkina, Yuandong Tian
2023 A* conf
Learning Compiler Pass Orders using Coreset and Normalized Value Prediction.
ICML
Youwei Liang, Kevin Stone, Ali Shameli, Chris Cummins, Mostafa Elhoushi, Jiadong Guo, Benoit Steiner, Xiaomeng Yang, Pengtao Xie, Hugh James Leather, Yuandong Tian
2023 J jnl
Learning Compiler Pass Orders using Coreset and Normalized Value Prediction.
CoRR
Youwei Liang, Kevin Stone, Ali Shameli, Chris Cummins, Mostafa Elhoushi, Jiadong Guo, Benoit Steiner, Xiaomeng Yang, Pengtao Xie, Hugh Leather, Yuandong Tian
2023 J jnl
Learning Personalized Story Evaluation.
CoRR
Danqing Wang, Kevin Yang, Hanlin Zhu, Xiaomeng Yang, Andrew Cohen, Lei Li, Yuandong Tian
2023 B conf
Local Branching Relaxation Heuristics for Integer Linear Programs.
CPAIOR
Taoan Huang, Aaron M. Ferber, Yuandong Tian, Bistra Dilkina, Benoit Steiner
2023 A* conf
MACTA: A Multi-agent Reinforcement Learning Approach for Cache Timing Attacks and Detection.
ICLR
Jiaxun Cui, Xiaomeng Yang, Mulong Luo, Geunbae Lee, Peter Stone, Hsien-Hsin S. Lee, Benjamin Lee, G. Edward Suh, Wenjie Xiong, Yuandong Tian
2023 J jnl
Modeling Scattering Coefficients using Self-Attentive Complex Polynomials with Image-based Representation.
CoRR
Andrew Cohen, Weiping Dou, Jiang Zhu, Slawomir Koziel, Peter Renner, Jan-Ove Mattsson, Xiaomeng Yang, Beidi Chen, Kevin Stone, Yuandong Tian
2023 — conf
Pre-train and Search: Efficient Embedding Table Sharding with Pre-trained Neural Cost Models.
MLSys
Daochen Zha, Louis Feng, Liang Luo, Bhargav Bhushanam, Zirui Liu, Yusuo Hu, Jade Nie, Yuzhen Huang, Yuandong Tian, Arun Kejariwal, Xia Hu
2023 J jnl
Pre-train and Search: Efficient Embedding Table Sharding with Pre-trained Neural Cost Models.
CoRR
Daochen Zha, Louis Feng, Liang Luo, Bhargav Bhushanam, Zirui Liu, Yusuo Hu, Jade Nie, Yuzhen Huang, Yuandong Tian, Arun Kejariwal, Xia Hu
2023 J jnl
RLCD: Reinforcement Learning from Contrast Distillation for Language Model Alignment.
CoRR
Kevin Yang, Dan Klein, Asli Celikyilmaz, Nanyun Peng, Yuandong Tian
2023 A* conf
Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer.
NeurIPS
Yuandong Tian, Yiping Wang, Beidi Chen, Simon S. Du
2023 J jnl
Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer.
CoRR
Yuandong Tian, Yiping Wang, Beidi Chen, Simon S. Du
2023 A* conf
Searching Large Neighborhoods for Integer Linear Programs with Contrastive Learning.
ICML
Taoan Huang, Aaron M. Ferber, Yuandong Tian, Bistra Dilkina, Benoit Steiner
2023 J jnl
Searching Large Neighborhoods for Integer Linear Programs with Contrastive Learning.
CoRR
Taoan Huang, Aaron M. Ferber, Yuandong Tian, Bistra Dilkina, Benoit Steiner
2023 A* conf
SurCo: Learning Linear SURrogates for COmbinatorial Nonlinear Optimization Problems.
ICML
Aaron M. Ferber, Taoan Huang, Daochen Zha, Martin Schubert, Benoit Steiner, Bistra Dilkina, Yuandong Tian
2023 J jnl
Understanding Curriculum Learning in Policy Optimization for Online Combinatorial Optimization.
Trans. Mach. Learn. Res.
Runlong Zhou, Zelin He, Yuandong Tian, Yi Wu, Simon Shaolei Du
2023 A* conf
Understanding the Role of Nonlinearity in Training Dynamics of Contrastive Learning.
ICLR
Yuandong Tian
2022 J jnl
AutoCAT: Reinforcement Learning for Automated Exploration of Cache Timing-Channel Attacks.
CoRR
Mulong Luo, Wenjie Xiong, Geunbae Lee, Yueying Li, Xiaomeng Yang, Amy Zhang, Yuandong Tian, Hsien-Hsin S. Lee, G. Edward Suh
2022 A* conf
AutoShard: Automated Embedding Table Sharding for Recommender Systems.
KDD
Daochen Zha, Louis Feng, Bhargav Bhushanam, Dhruv Choudhary, Jade Nie, Yuandong Tian, Jay Chae, Yinbin Ma, Arun Kejariwal, Xia Hu
2022 J jnl
AutoShard: Automated Embedding Table Sharding for Recommender Systems.
CoRR
Daochen Zha, Louis Feng, Bhargav Bhushanam, Dhruv Choudhary, Jade Nie, Yuandong Tian, Jay Chae, Yinbin Ma, Arun Kejariwal, Xia Hu
2022 A conf
CompilerGym: Robust, Performant Compiler Optimization Environments for AI Research.
CGO
Chris Cummins, Bram Wasti, Jiadong Guo, Brandon Cui, Jason Ansel, Sahir Gomez, Somya Jain, Jia Liu, Olivier Teytaud, Benoit Steiner, Yuandong Tian, Hugh Leather
2022 J jnl
DOC: Improving Long Story Coherence With Detailed Outline Control.
CoRR
Kevin Yang, Dan Klein, Nanyun Peng, Yuandong Tian
2022 J jnl
Deep Contrastive Learning is Provably (almost) Principal Component Analysis.
CoRR
Yuandong Tian
2022 A* conf
Denoised MDPs: Learning World Models Better Than the World Itself.
ICML
Tongzhou Wang, Simon S. Du, Antonio Torralba, Phillip Isola, Amy Zhang, Yuandong Tian
2022 J jnl
Denoised MDPs: Learning World Models Better Than the World Itself.
CoRR
Tongzhou Wang, Simon S. Du, Antonio Torralba, Phillip Isola, Amy Zhang, Yuandong Tian
2022 A* conf
DreamShard: Generalizable Embedding Table Placement for Recommender Systems.
NeurIPS
Daochen Zha, Louis Feng, Qiaoyu Tan, Zirui Liu, Kwei-Herng Lai, Bhargav Bhushanam, Yuandong Tian, Arun Kejariwal, Xia Hu
2022 J jnl
DreamShard: Generalizable Embedding Table Placement for Recommender Systems.
CoRR
Daochen Zha, Louis Feng, Qiaoyu Tan, Zirui Liu, Kwei-Herng Lai, Bhargav Bhushanam, Yuandong Tian, Arun Kejariwal, Xia Hu
2022 J jnl
Efficient Planning in a Compact Latent Action Space.
CoRR
Zhengyao Jiang, Tianjun Zhang, Michael Janner, Yueying Li, Tim Rocktäschel, Edward Grefenstette, Yuandong Tian
2022 J jnl
EurNet: Efficient Multi-Range Relational Modeling of Spatial Multi-Relational Data.
CoRR
Minghao Xu, Yuanfan Guo, Yi Xu, Jian Tang, Xinlei Chen, Yuandong Tian
2022 A* conf
Learning Bounded Context-Free-Grammar via LSTM and the Transformer: Difference and the Explanations.
AAAI
Hui Shi, Sicun Gao, Yuandong Tian, Xinyun Chen, Jishen Zhao
2022 J jnl
Local Branching Relaxation Heuristics for Integer Linear Programs.
CoRR
Taoan Huang, Aaron M. Ferber, Yuandong Tian, Bistra Dilkina, Benoit Steiner
2022 A* conf
Multi-objective Optimization by Learning Space Partition.
ICLR
Yiyang Zhao, Linnan Wang, Kevin Yang, Tianjun Zhang, Tian Guo, Yuandong Tian
2022 A* conf
NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet Training.
ICLR
Chengyue Gong, Dilin Wang, Meng Li, Xinlei Chen, Zhicheng Yan, Yuandong Tian, Qiang Liu, Vikas Chandra
2022 A* conf
On the Importance of Asymmetry for Siamese Representation Learning.
CVPR
Xiao Wang, Haoqi Fan, Yuandong Tian, Daisuke Kihara, Xinlei Chen
2022 J jnl
On the Importance of Asymmetry for Siamese Representation Learning.
CoRR
Xiao Wang, Haoqi Fan, Yuandong Tian, Daisuke Kihara, Xinlei Chen
2022 A conf
Provably Efficient Policy Optimization for Two-Player Zero-Sum Markov Games.
AISTATS
Yulai Zhao, Yuandong Tian, Jason D. Lee, Simon S. Du
2022 B conf
Q-gym: An Equality Saturation Framework for DNN Inference Exploiting Weight Repetition.
PACT
Cheng Fu, Hanxian Huang, Bram Wasti, Chris Cummins, Riyadh Baghdadi, Kim M. Hazelwood, Yuandong Tian, Jishen Zhao, Hugh Leather
2022 A* conf
Re3: Generating Longer Stories With Recursive Reprompting and Revision.
EMNLP
Kevin Yang, Yuandong Tian, Nanyun Peng, Dan Klein
2022 J jnl
Re3: Generating Longer Stories With Recursive Reprompting and Revision.
CoRR
Kevin Yang, Yuandong Tian, Nanyun Peng, Dan Klein
2022 J jnl
Sample-Efficient Neural Architecture Search by Learning Actions for Monte Carlo Tree Search.
IEEE Trans. Pattern Anal. Mach. Intell.
Linnan Wang, Saining Xie, Teng Li, Rodrigo Fonseca, Yuandong Tian
2022 J jnl
SurCo: Learning Linear Surrogates For Combinatorial Nonlinear Optimization Problems.
CoRR
Aaron M. Ferber, Taoan Huang, Daochen Zha, Martin Schubert, Benoit Steiner, Bistra Dilkina, Yuandong Tian
2022 J jnl
Understanding Curriculum Learning in Policy Optimization for Solving Combinatorial Optimization Problems.
CoRR
Runlong Zhou, Yuandong Tian, Yi Wu, Simon S. Du
2022 A* conf
Understanding Deep Contrastive Learning via Coordinate-wise Optimization.
NeurIPS
Yuandong Tian
2022 A* conf
Understanding Dimensional Collapse in Contrastive Self-supervised Learning.
ICLR
Li Jing, Pascal Vincent, Yann LeCun, Yuandong Tian
2022 J jnl
Understanding the Role of Nonlinearity in Training Dynamics of Contrastive Learning.
CoRR
Yuandong Tian
2021 J jnl
CompilerGym: Robust, Performant Compiler Optimization Environments for AI Research.
CoRR
Chris Cummins, Bram Wasti, Jiadong Guo, Brandon Cui, Jason Ansel, Sahir Gomez, Somya Jain, Jia Liu, Olivier Teytaud, Benoit Steiner, Yuandong Tian, Hugh Leather
2021 J jnl
Dynamic Graph Representation Learning via Graph Transformer Networks.
CoRR
Weilin Cong, Yanhong Wu, Yuandong Tian, Mengting Gu, Yinglong Xia, Mehrdad Mahdavi, Chun-cheng Jason Chen
2021 A* conf
FBNetV3: Joint Architecture-Recipe Search Using Predictor Pretraining.
CVPR
Xiaoliang Dai, Alvin Wan, Peizhao Zhang, Bichen Wu, Zijian He, Zhen Wei, Kan Chen, Yuandong Tian, Matthew Yu, Peter Vajda, Joseph E. Gonzalez
2021 A* conf
FP-NAS: Fast Probabilistic Neural Architecture Search.
CVPR
Zhicheng Yan, Xiaoliang Dai, Peizhao Zhang, Yuandong Tian, Bichen Wu, Matt Feiszli
2021 A* conf
Few-Shot Neural Architecture Search.
ICML
Yiyang Zhao, Linnan Wang, Yuandong Tian, Rodrigo Fonseca, Tian Guo
2021 A* conf
Latent Execution for Neural Program Synthesis Beyond Domain-Specific Languages.
NeurIPS
Xinyun Chen, Dawn Song, Yuandong Tian
2021 J jnl
Latent Execution for Neural Program Synthesis Beyond Domain-Specific Languages.
CoRR
Xinyun Chen, Dawn Song, Yuandong Tian
2021 A* conf
Learn-to-Share: A Hardware-friendly Transfer Learning Framework Exploiting Computation and Parameter Sharing.
ICML
Cheng Fu, Hanxian Huang, Xinyun Chen, Yuandong Tian, Jishen Zhao
2021 J jnl
Learning Bounded Context-Free-Grammar via LSTM and the Transformer: Difference and Explanations.
CoRR
Hui Shi, Sicun Gao, Yuandong Tian, Xinyun Chen, Jishen Zhao
2021 A* conf
Learning Space Partitions for Path Planning.
NeurIPS
Kevin Yang, Tianjun Zhang, Chris Cummins, Brandon Cui, Benoit Steiner, Linnan Wang, Joseph E. Gonzalez, Dan Klein, Yuandong Tian
2021 J jnl
Learning Space Partitions for Path Planning.
CoRR
Kevin Yang, Tianjun Zhang, Chris Cummins, Brandon Cui, Benoit Steiner, Linnan Wang, Joseph E. Gonzalez, Dan Klein, Yuandong Tian
2021 A* conf
MADE: Exploration via Maximizing Deviation from Explored Regions.
NeurIPS
Tianjun Zhang, Paria Rashidinejad, Jiantao Jiao, Yuandong Tian, Joseph E. Gonzalez, Stuart Russell
2021 J jnl
MADE: Exploration via Maximizing Deviation from Explored Regions.
CoRR
Tianjun Zhang, Paria Rashidinejad, Jiantao Jiao, Yuandong Tian, Joseph Gonzalez, Stuart Russell
2021 J jnl
Multi-objective Optimization by Learning Space Partitions.
CoRR
Yiyang Zhao, Linnan Wang, Kevin Yang, Tianjun Zhang, Tian Guo, Yuandong Tian
2021 A* conf
Network planning with deep reinforcement learning.
SIGCOMM
Hang Zhu, Varun Gupta, Satyajeet Singh Ahuja, Yuandong Tian, Ying Zhang, Xin Jin
2021 A* conf
NovelD: A Simple yet Effective Exploration Criterion.
NeurIPS
Tianjun Zhang, Huazhe Xu, Xiaolong Wang, Yi Wu, Kurt Keutzer, Joseph E. Gonzalez, Yuandong Tian
2021 J jnl
Planning in Learned Latent Action Spaces for Generalizable Legged Locomotion.
IEEE Robotics Autom. Lett.
Tianyu Li, Roberto Calandra, Deepak Pathak, Yuandong Tian, Franziska Meier, Akshara Rai
2021 J jnl
Provably Efficient Policy Gradient Methods for Two-Player Zero-Sum Markov Games.
CoRR
Yulai Zhao, Yuandong Tian, Jason D. Lee, Simon S. Du
2021 J jnl
Towards Demystifying Representation Learning with Non-contrastive Self-supervision.
CoRR
Xiang Wang, Xinlei Chen, Simon S. Du, Yuandong Tian
2021 J jnl
Understanding Dimensional Collapse in Contrastive Self-supervised Learning.
CoRR
Li Jing, Pascal Vincent, Yann LeCun, Yuandong Tian
2021 A conf
Understanding Robustness in Teacher-Student Setting: A New Perspective.
AISTATS
Zhuolin Yang, Zhaoxi Chen, Tiffany Cai, Xinyun Chen, Bo Li, Yuandong Tian
2021 J jnl
Understanding Robustness in Teacher-Student Setting: A New Perspective.
CoRR
Zhuolin Yang, Zhaoxi Chen, Tiffany Cai, Xinyun Chen, Bo Li, Yuandong Tian
2021 J jnl
Understanding self-supervised Learning Dynamics without Contrastive Pairs.
CoRR
Yuandong Tian, Xinlei Chen, Surya Ganguli
2021 A* conf
Understanding self-supervised learning dynamics without contrastive pairs.
ICML
Yuandong Tian, Xinlei Chen, Surya Ganguli
2020 J jnl
BeBold: Exploration Beyond the Boundary of Explored Regions.
CoRR
Tianjun Zhang, Huazhe Xu, Xiaolong Wang, Yi Wu, Kurt Keutzer, Joseph E. Gonzalez, Yuandong Tian
2020 A* conf
Deep Symbolic Superoptimization Without Human Knowledge.
ICLR
Hui Shi, Yang Zhang, Xinyun Chen, Yuandong Tian, Jishen Zhao
2020 J jnl
Enhancing Model Parallelism in Neural Architecture Search for Multidevice System.
IEEE Micro
Cheng Fu, Huili Chen, Zhenheng Yang, Farinaz Koushanfar, Yuandong Tian, Jishen Zhao
2020 A* conf
FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions.
CVPR
Alvin Wan, Xiaoliang Dai, Peizhao Zhang, Zijian He, Yuandong Tian, Saining Xie, Bichen Wu, Matthew Yu, Tao Xu, Kan Chen, Peter Vajda, Joseph E. Gonzalez
2020 J jnl
FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions.
CoRR
Alvin Wan, Xiaoliang Dai, Peizhao Zhang, Zijian He, Yuandong Tian, Saining Xie, Bichen Wu, Matthew Yu, Tao Xu, Kan Chen, Peter Vajda, Joseph E. Gonzalez
2020 J jnl
FBNetV3: Joint Architecture-Recipe Search using Neural Acquisition Function.
CoRR
Xiaoliang Dai, Alvin Wan, Peizhao Zhang, Bichen Wu, Zijian He, Zhen Wei, Kan Chen, Yuandong Tian, Matthew Yu, Peter Vajda, Joseph E. Gonzalez
2020 J jnl
FP-NAS: Fast Probabilistic Neural Architecture Search.
CoRR
Zhicheng Yan, Xiaoliang Dai, Peizhao Zhang, Yuandong Tian, Bichen Wu, Matt Feiszli
2020 J jnl
Few-shot Neural Architecture Search.
CoRR
Yiyang Zhao, Linnan Wang, Yuandong Tian, Rodrigo Fonseca, Tian Guo
2020 A* conf
Joint Policy Search for Multi-agent Collaboration with Imperfect Information.
NeurIPS
Yuandong Tian, Qucheng Gong, Yu Jiang
2020 J jnl
Joint Policy Search for Multi-agent Collaboration with Imperfect Information.
CoRR
Yuandong Tian, Qucheng Gong, Tina Jiang
2020 A* conf
Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search.
NeurIPS
Linnan Wang, Rodrigo Fonseca, Yuandong Tian
2020 J jnl
Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search.
CoRR
Linnan Wang, Rodrigo Fonseca, Yuandong Tian
2020 J jnl
Multi-Agent Collaboration via Reward Attribution Decomposition.
CoRR
Tianjun Zhang, Huazhe Xu, Xiaolong Wang, Yi Wu, Kurt Keutzer, Joseph E. Gonzalez, Yuandong Tian
2020 A* conf
Neural Architecture Search Using Deep Neural Networks and Monte Carlo Tree Search.
AAAI
Linnan Wang, Yiyang Zhao, Yuu Jinnai, Yuandong Tian, Rodrigo Fonseca
2020 J jnl
Planning in Learned Latent Action Spaces for Generalizable Legged Locomotion.
CoRR
Tianyu Li, Roberto Calandra, Deepak Pathak, Yuandong Tian, Franziska Meier, Akshara Rai
2020 A* conf
Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP.
ICLR
Haonan Yu, Sergey Edunov, Yuandong Tian, Ari S. Morcos
2020 J jnl
Real-world Video Adaptation with Reinforcement Learning.
CoRR
Hongzi Mao, Shannon Chen, Drew Dimmery, Shaun Singh, Drew Blaisdell, Yuandong Tian, Mohammad Alizadeh, Eytan Bakshy
2020 A* conf
Student Specialization in Deep Rectified Networks With Finite Width and Input Dimension.
ICML
Yuandong Tian
2020 A* conf
Towards Automated Neural Interaction Discovery for Click-Through Rate Prediction.
KDD
Qingquan Song, Dehua Cheng, Hanning Zhou, Jiyan Yang, Yuandong Tian, Xia Hu
2020 J jnl
Towards Automated Neural Interaction Discovery for Click-Through Rate Prediction.
CoRR
Qingquan Song, Dehua Cheng, Hanning Zhou, Jiyan Yang, Yuandong Tian, Xia Hu
2020 J jnl
Understanding Self-supervised Learning with Dual Deep Networks.
CoRR
Yuandong Tian, Lantao Yu, Xinlei Chen, Surya Ganguli
2019 J jnl
A Neural-based Program Decompiler.
CoRR
Cheng Fu, Huili Chen, Haolan Liu, Xinyun Chen, Yuandong Tian, Farinaz Koushanfar, Jishen Zhao
2019 — conf
Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees.
ICLR (Poster)
Yuping Luo, Huazhe Xu, Yuanzhi Li, Yuandong Tian, Trevor Darrell, Tengyu Ma
2019 J jnl
AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Search.
CoRR
Linnan Wang, Yiyang Zhao, Yuu Jinnai, Yuandong Tian, Rodrigo Fonseca
2019 A* conf
Bayesian Relational Memory for Semantic Visual Navigation.
ICCV
Yi Wu, Yuxin Wu, Aviv Tamar, Stuart Russell, Georgia Gkioxari, Yuandong Tian
2019 J jnl
Bayesian Relational Memory for Semantic Visual Navigation.
CoRR
Yi Wu, Yuxin Wu, Aviv Tamar, Stuart Russell, Georgia Gkioxari, Yuandong Tian
2019 — conf
CoDraw: Collaborative Drawing as a Testbed for Grounded Goal-driven Communication.
ACL (1)
Jin-Hwa Kim, Nikita Kitaev, Xinlei Chen, Marcus Rohrbach, Byoung-Tak Zhang, Yuandong Tian, Dhruv Batra, Devi Parikh
2019 A* conf
Coda: An End-to-End Neural Program Decompiler.
NeurIPS
Cheng Fu, Huili Chen, Haolan Liu, Xinyun Chen, Yuandong Tian, Farinaz Koushanfar, Jishen Zhao
2019 J jnl
ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero.
CoRR
Yuandong Tian, Jerry Ma, Qucheng Gong, Shubho Sengupta, Zhuoyuan Chen, James Pinkerton, C. Lawrence Zitnick
2019 A* conf
ELF OpenGo: an analysis and open reimplementation of AlphaZero.
ICML
Yuandong Tian, Jerry Ma, Qucheng Gong, Shubho Sengupta, Zhuoyuan Chen, James Pinkerton, Larry Zitnick
2019 A* conf
FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search.
CVPR
Bichen Wu, Xiaoliang Dai, Peizhao Zhang, Yanghan Wang, Fei Sun, Yiming Wu, Yuandong Tian, Peter Vajda, Yangqing Jia, Kurt Keutzer
2019 A* conf
Hierarchical Decision Making by Generating and Following Natural Language Instructions.
NeurIPS
Hengyuan Hu, Denis Yarats, Qucheng Gong, Yuandong Tian, Mike Lewis
2019 J jnl
Hierarchical Decision Making by Generating and Following Natural Language Instructions.
CoRR
Hengyuan Hu, Denis Yarats, Qucheng Gong, Yuandong Tian, Mike Lewis
2019 A* conf
Learning to Perform Local Rewriting for Combinatorial Optimization.
NeurIPS
Xinyun Chen, Yuandong Tian
2019 J jnl
Luck Matters: Understanding Training Dynamics of Deep ReLU Networks.
CoRR
Yuandong Tian, Tina Jiang, Qucheng Gong, Ari S. Morcos
2019 — conf
M^3RL: Mind-aware Multi-agent Management Reinforcement Learning.
ICLR (Poster)
Tianmin Shu, Yuandong Tian
2019 A* conf
One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers.
NeurIPS
Ari S. Morcos, Haonan Yu, Michela Paganini, Yuandong Tian
2019 J jnl
One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers.
CoRR
Ari S. Morcos, Haonan Yu, Michela Paganini, Yuandong Tian
2019 J jnl
Over-parameterization as a Catalyst for Better Generalization of Deep ReLU network.
CoRR
Yuandong Tian
2019 J jnl
Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP.
CoRR
Haonan Yu, Sergey Edunov, Yuandong Tian, Ari S. Morcos
2019 J jnl
Sample-Efficient Neural Architecture Search by Learning Action Space.
CoRR
Linnan Wang, Saining Xie, Teng Li, Rodrigo Fonseca, Yuandong Tian
2018 J jnl
3D Interpreter Networks for Viewer-Centered Wireframe Modeling.
CoRR
Jiajun Wu, Tianfan Xue, Joseph J. Lim, Yuandong Tian, Joshua B. Tenenbaum, Antonio Torralba, William T. Freeman
2018 J jnl
3D Interpreter Networks for Viewer-Centered Wireframe Modeling.
Int. J. Comput. Vis.
Jiajun Wu, Tianfan Xue, Joseph J. Lim, Yuandong Tian, Joshua B. Tenenbaum, Antonio Torralba, William T. Freeman
2018 J jnl
A theoretical framework for deep locally connected ReLU network.
CoRR
Yuandong Tian
2018 J jnl
Algorithmic Framework for Model-based Reinforcement Learning with Theoretical Guarantees.
CoRR
Huazhe Xu, Yuanzhi Li, Yuandong Tian, Trevor Darrell, Tengyu Ma
2018 — conf
Building Generalizable Agents with a Realistic and Rich 3D Environment.
ICLR (Workshop)
Yi Wu, Yuxin Wu, Georgia Gkioxari, Yuandong Tian
2018 J jnl
Building Generalizable Agents with a Realistic and Rich 3D Environment.
CoRR
Yi Wu, Yuxin Wu, Georgia Gkioxari, Yuandong Tian
2018 A conf
Channel-Recurrent Autoencoding for Image Modeling.
WACV
Wenling Shang, Kihyuk Sohn, Yuandong Tian
2018 J jnl
FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search.
CoRR
Bichen Wu, Xiaoliang Dai, Peizhao Zhang, Yanghan Wang, Fei Sun, Yiming Wu, Yuandong Tian, Peter Vajda, Yangqing Jia, Kurt Keutzer
2018 A* conf
Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima.
ICML
Simon S. Du, Jason D. Lee, Yuandong Tian, Aarti Singh, Barnabás Póczos
2018 J jnl
Guest Editorial Special Issue on Deep/Reinforcement Learning and Games.
IEEE Trans. Games
I-Chen Wu, Chang-Shing Lee, Yuandong Tian, Martin Müller
2018 J jnl
Learning and Planning with a Semantic Model.
CoRR
Yi Wu, Yuxin Wu, Aviv Tamar, Stuart Russell, Georgia Gkioxari, Yuandong Tian
2018 J jnl
Learning to Progressively Plan.
CoRR
Xinyun Chen, Yuandong Tian
2018 J jnl
M^3RL: Mind-aware Multi-agent Management Reinforcement Learning.
CoRR
Tianmin Shu, Yuandong Tian
2018 J jnl
Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search.
CoRR
Bichen Wu, Yanghan Wang, Peizhao Zhang, Yuandong Tian, Peter Vajda, Kurt Keutzer
2018 — conf
When is a Convolutional Filter Easy to Learn?
ICLR (Poster)
Simon S. Du, Jason D. Lee, Yuandong Tian
2017 A* conf
An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis.
ICML
Yuandong Tian
2017 J jnl
An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis.
CoRR
Yuandong Tian
2017 J jnl
Channel-Recurrent Variational Autoencoders.
CoRR
Wenling Shang, Kihyuk Sohn, Zeynep Akata, Yuandong Tian
2017 J jnl
CoDraw: Visual Dialog for Collaborative Drawing.
CoRR
Jin-Hwa Kim, Devi Parikh, Dhruv Batra, Byoung-Tak Zhang, Yuandong Tian
2017 — conf
ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games.
NIPS
Yuandong Tian, Qucheng Gong, Wenling Shang, Yuxin Wu, C. Lawrence Zitnick
2017 J jnl
ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games.
CoRR
Yuandong Tian, Qucheng Gong, Wenling Shang, Yuxin Wu, Larry Zitnick
2017 J jnl
Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima.
CoRR
Simon S. Du, Jason D. Lee, Yuandong Tian, Barnabás Póczos, Aarti Singh
2017 A* conf
Semantic Amodal Segmentation.
CVPR
Yan Zhu, Yuandong Tian, Dimitris N. Metaxas, Piotr Dollár
2017 — conf
Symmetry-Breaking Convergence Analysis of Certain Two-layered Neural Networks with ReLU nonlinearity.
ICLR (Workshop)
Yuandong Tian
2017 — conf
Training Agent for First-Person Shooter Game with Actor-Critic Curriculum Learning.
ICLR (Poster)
Yuxin Wu, Yuandong Tian
2017 J jnl
When is a Convolutional Filter Easy To Learn?
CoRR
Simon S. Du, Jason D. Lee, Yuandong Tian
2016 A* conf
Better Computer Go Player with Neural Network and Long-term Prediction.
ICLR (Poster)
Yuandong Tian, Yan Zhu
2016 — conf
Single Image 3D Interpreter Network.
ECCV (6)
Jiajun Wu, Tianfan Xue, Joseph J. Lim, Yuandong Tian, Joshua B. Tenenbaum, Antonio Torralba, William T. Freeman
2016 J jnl
Single Image 3D Interpreter Network.
CoRR
Jiajun Wu, Tianfan Xue, Joseph J. Lim, Yuandong Tian, Joshua B. Tenenbaum, Antonio Torralba, William T. Freeman
2015 J jnl
Scale-invariant learning and convolutional networks.
CoRR
Soumith Chintala, Marc'Aurelio Ranzato, Arthur Szlam, Yuandong Tian, Mark Tygert, Wojciech Zaremba
2015 J jnl
Semantic Amodal Segmentation.
CoRR
Yan Zhu, Yuandong Tian, Dimitris N. Metaxas, Piotr Dollár
2015 J jnl
Simple Baseline for Visual Question Answering.
CoRR
Bolei Zhou, Yuandong Tian, Sainbayar Sukhbaatar, Arthur Szlam, Rob Fergus
2015 J jnl
Theory and Practice of Hierarchical Data-driven Descent for Optimal Deformation Estimation.
Int. J. Comput. Vis.
Yuandong Tian, Srinivasa G. Narasimhan
2013 A* conf
Hierarchical Data-Driven Descent for Efficient Optimal Deformation Estimation.
ICCV
Yuandong Tian, Srinivasa G. Narasimhan
2013 A conf
Integrating Perceptual Learning with External World Knowledge in a Simulated Student.
AIED
Nan Li, Yuandong Tian, William W. Cohen, Kenneth R. Koedinger
2013 — —
Theory and Practice of Globally Optimal Deformation Estimation.
Yuandong Tian
2012 J jnl
A Combined Theory of Defocused Illumination and Global Light Transport.
Int. J. Comput. Vis.
Mohit Gupta, Yuandong Tian, Srinivasa G. Narasimhan, Li Zhang
2012 A* conf
Depth from optical turbulence.
CVPR
Yuandong Tian, Srinivasa G. Narasimhan, Alan Van Nevel
2012 — conf
Exploring the Spatial Hierarchy of Mixture Models for Human Pose Estimation.
ECCV (5)
Yuandong Tian, C. Lawrence Zitnick, Srinivasa G. Narasimhan
2012 J jnl
Globally Optimal Estimation of Nonrigid Image Distortion.
Int. J. Comput. Vis.
Yuandong Tian, Srinivasa G. Narasimhan
2012 A* conf
Learning from crowds in the presence of schools of thought.
KDD
Yuandong Tian, Jun Zhu
2011 A* conf
Local isomorphism to solve the pre-image problem in kernel methods.
CVPR
Dong Huang, Yuandong Tian, Fernando De la Torre
2011 A* conf
Rectification and 3D reconstruction of curved document images.
CVPR
Yuandong Tian, Srinivasa G. Narasimhan
2010 A* conf
A globally optimal data-driven approach for image distortion estimation.
CVPR
Yuandong Tian, Srinivasa G. Narasimhan
2009 A* conf
(De) focusing on global light transport for active scene recovery.
CVPR
Mohit Gupta, Yuandong Tian, Srinivasa G. Narasimhan, Li Zhang
2009 A* conf
Seeing through water: Image restoration using model-based tracking.
ICCV
Yuandong Tian, Srinivasa G. Narasimhan
2008 A* conf
Easytoon: an easy and quick tool to personalize a cartoon storyboard using family photo album.
ACM Multimedia
Shifeng Chen, Yuandong Tian, Fang Wen, Ying-Qing Xu, Xiaoou Tang
2007 A* conf
A Face Annotation Framework with Partial Clustering and Interactive Labeling.
CVPR
Yuandong Tian, Wei Liu, Rong Xiao, Fang Wen, Xiaoou Tang
2007 A* conf
EasyAlbum: an interactive photo annotation system based on face clustering and re-ranking.
CHI
Jingyu Cui, Fang Wen, Rong Xiao, Yuandong Tian, Xiaoou Tang
2006 — conf
Joint Boosting Feature Selection for Robust Face Recognition.
CVPR (2)
Rong Xiao, Wu-Jun Li, Yuandong Tian, Xiaoou Tang