TD
Trevor Darrell
cs.CVcs.LGcs.AIcs.CLcs.ROstat.MLcs.NEcs.MMcs.CYcs.GR
On Valency
published · living versionsW_99thjnpz·v1 · currentpublished
W_tse9bvhc·v1published
W_5sy9upy2·v1published
W_ber6cpqu·v1published
W_3r7ynunz·v1published
W_ssszqkn3·v1published
W_kmjwgbm3·v1published
Preprints & journals
371 papers in the corpus · 2007–2026Agentic World Action Models2610.30136v1 · Zhuoyang Liu, Dantong Niu, Botong Zhang et al.2026 · 0 citationsarXivon Valency
Train An Imaginative Agent2610.26845v1 · Jiaxin Ge, Junyi Zhang, Tianning Chai et al.2026 · 0 citationsarXivon Valency
Robota-Embed: Unified VLA Embeddings for Robot In-Context Learning and Evolution2610.19495v1 · Yunze Liu, Jing Wang, Shenrui Wu et al.2026 · 0 citationsarXiv
World Motion Models: Flexible Sequence Modeling of SE(3) Trajectories2610.01742v1 · Jiahui Lei, Qianqian Wang, Trevor Darrell et al.2026 · 0 citationsarXiv
OmniTaskonomy: When Does Visual Generation Improve Visual Understanding?2609.38079v1 · Jiaxin Ge, Yiming Qin, Ji Xie et al.2026 · 0 citationsarXiv
DexTacWAM: A Visuo-Tactile World-Action Model for Dexterous Manipulation2609.24976v1 · Haoran Yuan, Zekai Wang, Boning Shao et al.2026 · 0 citationsarXiv
Discriminative World Models for Web Agents2609.02885v1 · Kelvin Li, Dhruv Pendharkar, Anish Pahilajani et al.2026 · 0 citationsarXivon Valency
CoVA-SFT: A Large-Scale Dataset for Chain of Visual Abstractions2608.28958v1 · Tsung-Han Wu, Heekyung Lee, Anya Ji et al.2026 · 0 citationsarXiv
Open-Ended CT Volume Segmentation with Weak Supervision from Language2607.25860v1 · Sanjay Subramanian, Junwei Yu, Zirui Wang et al.2026 · 0 citationsarXiv
When Does Continual Learning Require Learning2607.07847v1 · Anne Harrington, Nayan Saxena, Michael Murphy et al.2026 · 0 citationsarXiv
Playful Agentic Robot Learning2606.19419v1 · Junyi Zhang, Jiaxin Ge, Hanjun Yoo et al.2026 · 0 citationsarXiv
Neural Tree Reconstruction for the Open Forest Observatory2606.18153v1 · Marissa Ramirez de Chanlatte, Arjun Rewari, Trevor Darrell et al.2026 · 0 citationsarXiv
T-Rex: Tactile-Reactive Dexterous Manipulation2606.17055v2 · Dantong Niu, Zhuoyang Liu, Zekai Wang et al.2026 · 0 citationsarXiv
Contrastive Action-Image Pre-training for Visuomotor Control2606.17256v1 · Yuvan Sharma, Dantong Niu, Anirudh Pai et al.2026 · 0 citationsarXiv
Stateful Visual Encoders for Vision-Language Models2606.04433v1 · Zirui Wang, Junwei Yu, Adam Yala et al.2026 · 0 citationsarXiv
Lifting Embodied World Models for Planning and Control2604.26182v2 · Alex N. Wang, Trevor Darrell, Pavel Izmailov et al.2026 · 0 citationsarXiv
Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing2603.12254v1 · Baifeng Shi, Stephanie Fu, Long Lian et al.2026 · 0 citationsarXiv
LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory2603.03269v2 · Junyi Zhang, Charles Herrmann, Junhwa Hur et al.2026 · 0 citationsarXiv
EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data2602.16710v1 · Ruijie Zheng, Dantong Niu, Yuqi Xie et al.2026 · 0 citationsarXiv
Learning a Generative Meta-Model of LLM Activations2602.06964v1 · Grace Luo, Jiahai Feng, Trevor Darrell et al.2026 · 0 citationsarXiv
Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning2601.11109v3 · Shaofeng Yin, Jiaxin Ge, Zora Zhiruo Wang et al.2026 · 3 citationsarXiv
It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Models2601.00090v2 · Anne Harrington, A. Sophia Koepke, Shyamgopal Karthik et al.2025 · 0 citationsarXiv
Latent Implicit Visual Reasoning2512.21218v2 · Kelvin Li, Chuyi Shang, Leonid Karlinsky et al.2025 · 0 citationsarXiv
DAVE: A VLM Vision Encoder for Document Understanding and Web Agents2512.17221v3 · Brandon Huang, Hang Hua, Zhuoran Yu et al.2025 · 0 citationsarXiv
Visually Prompted Benchmarks Are Surprisingly Fragile2512.17875v2 · Haiwen Feng, Long Lian, Lisa Dunlap et al.2025 · 0 citationsarXiv
FoundationMotion: Auto-Labeling and Reasoning about Spatial Movement in Videos2512.10927v1 · Yulu Gan, Ligeng Zhu, Dandan Shan et al.2025 · 0 citationsarXiv
From Generated Human Videos to Physically Plausible Robot Trajectories2512.05094v2 · James Ni, Zekai Wang, Wei Lin et al.2025 · 0 citationsarXiv
Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations2511.22697v1 · Chancharik Mitra, Yusen Luo, Raj Saravanan et al.2025 · 0 citationsarXiv
Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens2511.19418v3 · Yiming Qin, Bomin Wei, Jiaxin Ge et al.2025 · 3 citationsarXiv
ThreadWeaver: Adaptive Threading for Efficient Parallel Reasoning in Language Models2512.07843v2 · Long Lian, Sida Wang, Felix Juefei-Xu et al.2025 · 0 citationsarXiv
Pillar-0: A New Frontier for Radiology Foundation Models2511.17803v1 · Kumar Krishna Agrawal, Longchao Liu, Long Lian et al.2025 · 1 citationarXiv
UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity2511.13714v2 · Junwei Yu, Trevor Darrell, XuDong Wang2025 · 0 citationsTransactions on Machine Learning Research, 2026
Constantly Improving Image Models Need Constantly Improving Benchmarks2510.15021v1 · Jiaxin Ge, Grace Luo, Heekyung Lee et al.2025 · 0 citationsarXiv
Learning to Grasp Anything by Playing with Random Toys2510.12866v2 · Dantong Niu, Yuvan Sharma, Baifeng Shi et al.2025 · 0 citationsarXiv
Are Large Reasoning Models Interruptible?2510.11713v4 · Tsung-Han Wu, Mihran Miroyan, David M. Chan et al.2025 · 1 citationarXiv
Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models2510.03721v2 · Leander Girrbach, Stephan Alaniz, Genevieve Smith et al.2025 · 0 citationsarXiv
Discovering Divergent Representations between Text-to-Image Models2509.08940v1 · Lisa Dunlap, Joseph E. Gonzalez, Trevor Darrell et al.2025 · 1 citationarXiv
Reconstruction Alignment Improves Unified Multimodal Models2509.07295v4 · Ji Xie, Trevor Darrell, Luke Zettlemoyer et al.2025 · 0 citationsarXiv
Do What? Teaching Vision-Language-Action Models to Reject the Impossible2508.16292v1 · Wen-Han Hsieh, Elvis Hsieh, Dantong Niu et al.2025 · 0 citationsarXiv
The Sound of Simulation: Learning Multimodal Sim-to-Real Robot Policies with Generative Audio2507.02864v2 · Renhao Wang, Haoran Geng, Tingle Li et al.2025 · 0 citationsarXiv
Activation Reward Models for Few-Shot Model Alignment2507.01368v1 · Tianning Chai, Chancharik Mitra, Brandon Huang et al.2025 · 0 citationsarXiv
Whole-Body Conditioned Egocentric Video Prediction2506.21552v1 · Yutong Bai, Danny Tran, Amir Bar et al.2025 · 2 citationsarXiv
LeVERB: Humanoid Whole-Body Control with Latent Vision-Language Instruction2506.13751v3 · Haoru Xue, Xiaoyu Huang, Dantong Niu et al.2025 · 1 citationarXiv
Hidden in plain sight: VLMs overlook their visual representations2506.08008v1 · Stephanie Fu, Tyler Bonnen, Devin Guillory et al.2025 · 1 citationarXiv
Search Arena: Analyzing Search-Augmented LLMs2506.05334v2 · Mihran Miroyan, Tsung-Han Wu, Logan King et al.2025 · 1 citationarXiv
Dual-Process Image Generation2506.01955v1 · Grace Luo, Jonathan Granskog, Aleksander Holynski et al.2025 · 2 citationsarXiv
REOrdering Patches Improves Vision Models2505.23751v3 · Declan Kutscher, David M. Chan, Yutong Bai et al.2025 · 2 citationsarXiv
Puzzled by Puzzles: When Vision-Language Models Can't Take a Hint2505.23759v2 · Heekyung Lee, Jiaxin Ge, Tsung-Han Wu et al.2025 · 0 citationsarXiv
Visual Imitation Enables Contextual Humanoid Control2505.03729v5 · Arthur Allshire, Hongsuk Choi, Junyi Zhang et al.2025 · 0 citationsarXiv
LISAT: Language-Instructed Segmentation Assistant for Satellite Imagery2505.02829v1 · Jerome Quenum, Wen-Han Hsieh, Tsung-Han Wu et al.2025 · 2 citationsarXiv
Career total: 953 works. 371 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.