JD
Jia Deng
cs.CVcs.LGcs.AIstat.MLcs.ROcs.CLcs.LOcomputer visioncs.GRdeep learning
On Valency
published · living versionsW_eeq3w9uy·v1 · currentpublished
Multiscale Policy Optimization for Long-Horizon LLM Agents
with Tao Ren, Hui Yang, Tingyang Chen, Qiyao Wang +14
1 version
Preprints & journals
99 papers in the corpus · 2014–2026Good Memory Has ECC: Evaluating the Memory of Vision-Language Models Beyond Accuracy2609.00103v2 · Shmuel Berman, Jia Deng2026 · 0 citationsarXiv
InFlux++: Real and Synthetic Data for Estimating Dynamic Camera Intrinsics2607.05389v2 · Erich Liang, Caleb Kha-Uong, Chinmaya Saran et al.2026 · 0 citationsarXiv
GraspGen-X: Cross-Embodiment 6-DOF Diffusion-based Grasping2606.00998v1 · Beining Han, Yu-Wei Chao, Erwin Coumans et al.2026 · 0 citationsarXiv
SeeGroup: Multi-Layer Depth Estimation of Transparent Surfaces via Self-Determined Grouping2605.28735v1 · Hongyu Wen, Jia Deng2026 · 0 citationsarXiv
ProcFunc: Function-Oriented Abstractions for Procedural 3D Generation in Python2604.26943v2 · Alexander Raistrick, Karhan Kayan, Jack Nugent et al.2026 · 0 citationsarXiv
SimpleProc: Fully Procedural Synthetic Data from Simple Rules for Multi-View Stereo2604.04925v3 · Zeyu Ma, Alexander Raistrick, Jia Deng2026 · 0 citationsarXiv
Zero-Shot Depth from Defocus2603.26658v2 · Yiming Zuo, Hongyu Wen, Venkat Subramanian et al.2026 · 1 citationarXiv
WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching2603.24836v3 · Yihan Wang, Jia Deng2026 · 0 citationsarXiv
InFlux: A Benchmark for Self-Calibration of Dynamic Intrinsics of Video Cameras2510.23589v1 · Erich Liang, Roma Bhattacharjee, Sreemanti Dey et al.2025 · 1 citationarXiv
Toward A Better Understanding of Monocular Depth Evaluation2510.19814v3 · Siyang Wu, Jack Nugent, Willow Yang et al.2025 · 0 citationsarXiv
Temporally Smooth Mesh Extraction for Procedural Scenes with Long-Range Camera Trajectories using Spacetime Octrees2509.13306v3 · Zeyu Ma, Adam Finkelstein, Jia Deng2025 · 1 citationarXiv
VLMs have Tunnel Vision: Evaluating Nonlocal Visual Reasoning in Leading VLMs2507.13361v2 · Shmuel Berman, Jia Deng2025 · 0 citationsAdvances in Neural Information Processing Systems 38 (NeurIPS 2025)
Evaluating Robustness of Monocular Depth Estimation with Procedural Scene Perturbations2507.00981v2 · Jack Nugent, Siyang Wu, Zeyu Ma et al.2025 · 1 citationarXiv
WAFT: Warping-Alone Field Transforms for Optical Flow2506.21526v3 · Yihan Wang, Jia Deng2025 · 2 citationsarXiv
Princeton365: A Diverse Dataset with Accurate Camera Pose2506.09035v2 · Karhan Kayan, Stamatis Alexandropoulos, Rishabh Jain et al.2025 · 0 citationsarXiv
AnyBody: A Benchmark Suite for Cross-Embodiment Manipulation2505.14986v1 · Meenal Parakh, Alexandre Kirchmeyer, Beining Han et al.2025 · 0 citationsarXiv
Procedural Generation of Articulated Simulation-Ready Assets2505.10755v3 · Abhishek Joshi, Beining Han, Jack Nugent et al.2025 · 0 citationsarXiv
Zero-shot Sim2Real Transfer for Magnet-Based Tactile Sensor on Insertion Tasks2505.02915v2 · Beining Han, Abhishek Joshi, Jia Deng2025 · 0 citationsarXiv
What Makes Good Synthetic Training Data for Zero-Shot Stereo Matching?2504.16930v3 · David Yan, Alexander Raistrick, Jia Deng2025 · 0 citationsarXiv
Seeing and Seeing Through the Glass: Real and Synthetic Data for Multi-Layer Depth Estimation2503.11633v2 · Hongyu Wen, Yiming Zuo, Venkat Subramanian et al.2025 · 1 citationarXiv
OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integration2411.19278v2 · Yiming Zuo, Willow Yang, Zeyu Ma et al.2024 · 6 citationsarXiv
Towards Foundation Models for 3D Vision: How Close Are We?2410.10799v2 · Yiming Zuo, Karhan Kayan, Maggie Wang et al.2024 · 2 citationsarXiv
LayeredFlow: A Real-World Benchmark for Non-Lambertian Multi-Layer Optical Flow2409.05688v1 · Hongyu Wen, Erich Liang, Jia Deng2024 · 5 citationsarXiv
Deep Patch Visual SLAM2408.01654v1 · Lahav Lipson, Zachary Teed, Jia Deng2024 · 51 citationsarXiv
OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterations2406.11711v1 · Yiming Zuo, Jia Deng2024 · 20 citationsarXiv
FetchBench: A Simulation Benchmark for Robot Fetching2406.11793v2 · Beining Han, Meenal Parakh, Derek Geng et al.2024 · 0 citationsarXiv
Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation2406.11824v1 · Alexander Raistrick, Lingjie Mei, Karhan Kayan et al.2024 · 48 citationsarXiv
SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow2405.14793v1 · Yihan Wang, Lahav Lipson, Jia Deng2024 · 87 citationsarXiv
Multi-Session SLAM with Differentiable Wide-Baseline Pose Optimization2404.15263v1 · Lahav Lipson, Jia Deng2024 · 3 citationsarXiv
View-Dependent Octree-based Mesh Extraction in Unbounded Scenes for Procedural Synthetic Data2312.08364v1 · Zeyu Ma, Alexander Raistrick, Lahav Lipson et al.2023 · 0 citationsarXiv
Llemma: An Open Language Model For Mathematics2310.10631v3 · Zhangir Azerbayev, Hailey Schoelkopf, Keiran Paster et al.2023 · 32 citationsarXiv
Convolutional Networks with Oriented 1D Kernels2309.15812v1 · Alexandre Kirchmeyer, Jia Deng2023 · 7 citationsarXiv
Infinite Photorealistic Worlds using Procedural Generation2306.09310v2 · Alexander Raistrick, Lahav Lipson, Zeyu Ma et al.2023 · 89 citationsarXiv
Siamese Masked Autoencoders2305.14344v1 · Agrim Gupta, Jiajun Wu, Jia Deng et al.2023 · 29 citationsarXiv
Label-Free Synthetic Pretraining of Object Detectors2208.04268v1 · Hei Law, Jia Deng2022 · 2 citationsarXiv
Deep Patch Visual Odometry2208.04726v2 · Zachary Teed, Lahav Lipson, Jia Deng2022 · 106 citationsarXiv
Generating Natural Language Proofs with Verifier-Guided Search2205.12443v3 · Kaiyu Yang, Jia Deng, Danqi Chen2022 · 29 citationsarXiv
View Synthesis with Sculpted Neural Points2205.05869v2 · Yiming Zuo, Jia Deng2022 · 10 citationsarXiv
Multiview Stereo with Cascaded Epipolar RAFT2205.04502v1 · Zeyu Ma, Zachary Teed, Jia Deng2022 · 42 citationsarXiv
Coupled Iterative Refinement for 6D Multi-Object Pose Estimation2204.12516v1 · Lahav Lipson, Zachary Teed, Ankit Goyal et al.2022 · 68 citationsarXiv
IFOR: Iterative Flow Minimization for Robotic Object Rearrangement2202.00732v1 · Ankit Goyal, Arsalan Mousavian, Chris Paxton et al.2022 · 35 citationsarXiv
Learning Symbolic Rules for Reasoning in Quasi-Natural Language2111.12038v1 · Kaiyu Yang, Jia Deng2021 · 8 citationsarXiv
Non-deep Networks2110.07641v1 · Ankit Goyal, Alexey Bochkovskiy, Jia Deng et al.2021 · 2 citationsarXiv
RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching2109.07547v1 · Lahav Lipson, Zachary Teed, Jia Deng2021 · 568 citationsarXiv
DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras2108.10869v2 · Zachary Teed, Jia Deng2021 · 345 citationsarXiv
Dynamically Grown Generative Adversarial Networks2106.08505v1 · Lanlan Liu, Yuting Zhang, Jia Deng et al.2021 · 15 citationsarXiv
Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline2106.05304v1 · Ankit Goyal, Hei Law, Bowei Liu et al.2021 · 155 citationsarXiv
Tangent Space Backpropagation for 3D Transformation Groups2103.12032v2 · Zachary Teed, Jia Deng2021 · 37 citationsarXiv
A Study of Face Obfuscation in ImageNet2103.06191v3 · Kaiyu Yang, Jacqueline Yau, Li Fei-Fei et al.2021 · 87 citationsarXiv
Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D2012.01634v1 · Ankit Goyal, Kaiyu Yang, Dawei Yang et al.2020 · 14 citationsarXiv
Career total: 177 works. 99 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.