Publications | David Acuna

Introspective X Training: Feedback Conditioning Improves Scaling Across all LLM Training Stages

Brandon Cui, Ximing Lu, Jaehun Jung, Syeda Nahida Akter, Hyunwoo Kim, Yuxiao Qu, David Acuna, Shrimai Prabhumoye, Yejin Choi, Prithviraj Ammanabrolu

PDF

How to Instruct Your Robot: Dense Language Annotations Power Robot Policy Learning

Bosung Kim, Ruiyi Wang, David Acuna, Jaehun Jung, Alexander Trevithick, Brandon Cui, Yejin Choi, Prithviraj Ammanabrolu

PDF

DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal Distillation

Jaehun Jung, Hyunwoo Kim, Brandon Cui, Ximing Lu, David Acuna, Prithviraj Ammanabrolu, Yejin Choi

PDF

Privasis: Synthesizing the Largest 'Public' Private Dataset from Scratch

Hyunwoo Kim, Niloofar Mireshghallah, Michael Duan, Rui Xin, Shuyue Stella Li, Jaehun Jung, David Acuna, Qi Pang, Hanshen Xiao, G. Edward Suh, Sewoong Oh, Yulia Tsvetkov, Pang Wei Koh, Yejin Choi

PDF Project

Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text

Ximing Lu, David Acuna, Jaehun Jung, Jian Hu, Di Zhang, Shizhe Diao, Yunheng Zou, Shaokun Zhang, Brandon Cui, Mingjie Liu, Hyunwoo Kim, Prithviraj Ammanabrolu, Jan Kautz, Yi Dong, Yejin Choi

PDF Dataset

Long Grounded Thoughts: Synthesizing Visual Problems and Reasoning Chains at Scale

David Acuna, Chao-Han Huck Yang, Yuntian Deng, Jaehun Jung, Ximing Lu, Prithviraj Ammanabrolu, Hyunwoo Kim, Yuan-Hong Liao, Yejin Choi

PDF Dataset

Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction

Yong Lin, Shange Tang, Bohan Lyu, Ziran Yang, Jui-Hui Chung, Haoyu Zhao, Lai Jiang, Yihan Geng, Jiawei Ge, Jingruo Sun, Jiayun Wu, Jiri Gesi, Ximing Lu, David Acuna, Kaiyu Yang, Hongzhou Lin, Yejin Choi, Danqi Chen, Sanjeev Arora, Chi Jin

PDF Code Project

Socratic-MCTS: Test-Time Visual Reasoning by Asking the Right Questions

David Acuna *, Ximing Lu *, Jaehun Jung *, Hyunwoo Kim *, Amlan Kar, Sanja Fidler, Yejin Choi

PDF

Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning

Jaehun Jung, Seungju Han *, Ximing Lu *, Skyler Hallinan, David Acuna, Shrimai Prabhumoye, Mostafa Patwary, Mohammad Shoeybi, Bryan Catanzaro, Yejin Choi

PDF

LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception

Yuan-Hong Liao, Sven Elflein, Liu He, Laura Leal-Taixe, Yejin Choi, Sanja Fidler, David Acuna

PDF Code Dataset

Retro-Search: Exploring Untaken Paths for Deeper and Efficient Reasoning

Ximing Lu *, Seungju Han *, David Acuna *, Hyunwoo Kim *, Jaehun Jung *, Shrimai Prabhumoye, Niklas Muennighoff, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro, Yejin Choi

Preprint

Can Large Vision-Language Models Correct Grounding Errors and Reason By Themselves?

Yuan-Hong Liao, Rafid Mahmood, Sanja Fidler, David Acuna

Preprint

Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models

Yuan-Hong Liao, Rafid Mahmood, Sanja Fidler, David Acuna

PDF Project

Photorealistic Object Insertion with Diffusion-Guided Inverse Rendering

Ruofan Liang, Zan Gojcic, Merlin Nimier-David, David Acuna, Nandita Vijaykumar, Sanja Fidler, Zian Wang

PDF Project

RefFusion: Reference Adapted Diffusion Models for 3D Scene Inpainting

Ashkan Mirzaei, Riccardo De Lutio, Seung Wook Kim, David Acuna, Jonathan Kelly, Sanja Fidler, Igor Gilitschensk, Zan Gojcic

PDF

DreamTeacher: Pretraining Image Backbones with Deep Generative Models

Daiqing Li, Huan Ling, Amlan Kar, David Acuna, Seung Wook Kim, Karsten Kreis, Antonio Torralba, Sanja Fidler

Project

Bridging the Sim2Real gap with CARE: Supervised Detection Adaptation with Conditional Alignment and Reweighting

Viraj Prabhu, David Acuna, Rafid Mahmood, Marc T. Law , Yuan-Hong Liao , Judy Hoffman, Sanja Fidler, James Lucas

PDF

Visual Learning using Synthetic Data

David Acuna

PDF

Neural Light Field Estimation for Street Scenes with Differentiable Virtual Object Insertion

Zian Wang, Wenzheng Chen, David Acuna, Jan Kautz, Sanja Fidler

Project

How much more data do I need? Estimating requirements for downstream tasks

Rafid Mahmood, James Lucas, David Acuna, Daiqing Li, Jonah Philion, Jose M Alvarez, Zhiding Yu, Sanja Fidler, Marc T Law

Preprint PDF

Domain Adversarial Training: A Game Perspective

David Acuna , Marc T. Law , Guojun Zhang , Sanja Fidler

PDF Poster

Complex Momentum for Optimization in Games

Jonathan Lorraine, David Acuna , Paul Vicol , David Duvenaud

PDF

Federated Learning with Heterogeneous Architectures using Graph HyperNetworks

Or Litany , Haggai Maron , David Acuna , Jan Kautz , Gal Chechik, Sanja Fidler

PDF

Towards Optimal Strategies for Training Self-Driving Perception Models in Simulation

David Acuna* , Jonah Philion* , Sanja Fidler

PDF Project

Scalable Neural Data Server: A Data Recommender for Transfer Learning

Tianshi Cao* , Sasha Doubov* , David Acuna , Sanja Fidler

PDF

f-Domain-Adversarial Learning: Theory and Algorithms

David Acuna , Guojun Zhang , Marc T. Law , Sanja Fidler

PDF Project Code

Variational Amodal Object Completion

Huan Ling , David Acuna , Karsten Kreis , Seung Wook Kim , Sanja Fidler

PDF Project

Neural Data Server: A Large-Scale Search Engine for Transfer Learning Data

Xi Yan* , David Acuna* , Sanja Fidler
* denotes equal contribution

PDF Code Project

Gated-SCNN: Gated Shape CNNs for Semantic Segmentation

Towaki Takikawa* , David Acuna* , Varun Jampani , Sanja Fidler
* denotes equal contribution

PDF Code Project Video

Neural Turtle Graphics for Modeling City Road Layouts

Hang Chu , Daiqing Li, David Acuna, Amlan Kar , Maria Shugrina , Xinkai Wei, Ming-Yu Liu , Antonio Torralba , Sanja Fidler

PDF Project

Meta-Sim: Learning to Generate Synthetic Datasets

Amlan Kar , Aayush Prakash , Ming-Yu Liu , Eric Cameracci , Justin Yuan , Matt Rusiniak , David Acuna, Antonio Torralba , Sanja Fidler

PDF Project Video

Devil is in the Edges: Learning Semantic Boundaries from Noisy Annotations

David Acuna, Amlan Kar , Sanja Fidler

PDF Code Project Video Oral

Object Instance Annotation with Deep Extreme Level Set Evolution

Zian Wang, David Acuna *, Huan Ling * , Amlan Kar , Sanja Fidler
* denotes equal contribution

PDF

Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Data

Aayush Prakash, Shaad Boochoon, Mark Brophy, David Acuna, Eric Cameracci, Gavriel State, Omer Shapira, Stan Birchfield

PDF Video

Efficient Interactive Annotation of Segmentation Dataset with Polygon-RNN ++

David Acuna *, Huan Ling * , Amlan Kar * , Sanja Fidler
* denotes equal contribution

PDF Code Project Video

Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization

Jonathan Tremblay * , Aayush Prakash *, David Acuna * , Mark Brophy *, Varun Jampani, Cem Anil, Thang To, Eric Cameracci, Shaad Boochoon, Stan Birchfield
* denotes equal contribution

PDF

Direct Optimization of the Latent Representation for Fast Conditional Generation

David Acuna, David Duvenaud

PDF

Generating Class-conditional Images with Gradient-based Inference

Bowen Xu, David Acuna, David Duvenaud

PDF Poster