13 citations · 52 across the 48 of their papers we have counts for
15 papers · 1 filter
DTDD: Divergence-Triggered Dynamic Distillation for Reliable On-Policy Supervision
Qijia He, Zequn Li, Spencer Luo +6
On-policy distillation (OPD) provides dense token-level supervision on student rollouts, but this supervision can become unreliable when the student and teacher diverge, either bec…
Reflex: Visually Grounded Reactive Humanoid Control
Taoyang Jia, Weikai Huang, Linxin Song +6
Humans effortlessly react to the world; they adeptly return a tennis shot, catch a falling cup, step aside from a passing cart, or pass a box tossed during truck unloading. These e…
Grounded Action Model: 3D Grounding as a Foundation for Robotics
Gehao Zhang, Weikai Huang, Shailesh Shailesh +3
Manipulation policies must know which objects matter and where they are, yet the pretrained backbones that current robot foundation models build on, from language in vision-languag…
HumanCLAW: Can Vision-Language Models Act Through a Body?
Li Siyao, Jiawei Gu, Shuai Liu +15
Evaluating whether a vision-language model (VLM) can act through a physical body is challenging. The outcome of an action couples the VLM's decision with motor control. When a task…
JobBench: Aligning Agent Work With Human Will
Yuetai Li, Yichen Feng, Zhangchen Xu +21
Current benchmarks for occupational AI agents are scoped primarily by economic values, telling a replacement story. We introduce JobBench, which evaluates AI agents on the workflow…
MolmoAct2: Action Reasoning Models for Real-world Deployment
Haoquan Fang, Jiafei Duan, Donovan Clay +26
Vision-Language-Action (VLA) models aim to provide a single generalist controller for robots, but today's systems fall short on the criteria that matter for real-world deployment.…
VideoNet: A Large-Scale Dataset for Domain-Specific Action Recognition
Tanush Yadav, Mohammadreza Salehi, Jae Sung Park +6
Videos are unique in their ability to capture actions which transcend multiple frames. Accordingly, for many years action recognition was the quintessential task for video understa…
vla-eval: A Unified Evaluation Harness for Vision-Language-Action Models
Suhwan Choi, Yunsung Lee, Yubeen Park +4
Vision-Language-Action (VLA) models are increasingly evaluated across multiple simulation benchmarks, yet adding each benchmark to an evaluation pipeline requires resolving incompa…
MolmoWeb: Open Visual Web Agent and Open Data for the Open Web
Tanmay Gupta, Piper Wolters, Zixian Ma +13
Web agents--autonomous systems that navigate and execute tasks on the web on behalf of users--have the potential to transform how people interact with the digital world. However, t…
MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation
Abhay Deshpande, Maya Guru, Rose Hendrix +23
A prevailing view in robot learning is that simulation alone is not enough; effective sim-to-real transfer is widely believed to require at least some real-world data collection or…
When Rubrics Fail: Error Enumeration as Reward in Reference-Free RL Post-Training for Virtual Try-On
Wisdom Ikezogwo, Mehmet Saygin Seyfioglu, Ranjay Krishna +1
Reinforcement learning with verifiable rewards (RLVR) and Rubrics as Rewards (RaR) have driven strong gains in domains with clear correctness signals and even in subjective domains…
MolmoSpaces: A Large-Scale Open Ecosystem for Robot Navigation and Manipulation
Yejin Kim, Wilbert Pumacay, Omar Rayyan +23
Deploying robots at scale demands robustness to the long tail of everyday situations. The countless variations in scene layout, object geometry, and task specifications that charac…
Recurrent-Depth VLA: Implicit Test-Time Compute Scaling of Vision-Language-Action Models via Latent Iterative Reasoning
Yalcin Tur, Jalal Naghiyev, Haoquan Fang +4
Current Vision-Language-Action (VLA) models rely on fixed computational depth, expending the same amount of compute on simple adjustments and complex multi-step manipulation. While…
VLS: Steering Pretrained Robot Policies via Vision-Language Models
Shuo Liu, Ishneet Sukhvinder Singh, Yiqing Xu +2
Why do pretrained diffusion or flow-matching policies fail when the same task is performed near an obstacle, on a shifted support surface, or amid mild clutter? Such failures rarel…
TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics
Shirui Chen, Cole Harrison, Ying-Chun Lee +6
General-purpose robot learning requires dense, instruction-conditioned feedback that can distinguish meaningful task progress from stalled, failed, or partially completed behavior.…