112 citations · 304 across the 149 of their papers we have counts for
163 papers
FACT: A Multimodal Force-Action-Track Foundation Model for Human-to-Robot Dexterity
Zhi Cao, Yining Hong, Jiaolong Yang +4
Human demonstrations offer a scalable alternative to costly robot data collection for dexterous manipulation, but most human datasets lack force measurements. Dexterous manipulatio…
I3L: Iterative Interactive Imitation Learning for Whole-Body Mobile Manipulation
Wensi Ai, Christopher Luey, Karthik Dharmarajan +7
Policies trained offline from teleoperated demonstrations can degrade outside their training distribution. This gap is particularly acute in long-horizon whole-body mobile manipula…
The Human--VLA Communication Gap: What Humans Leave Implicit and What Policies Cannot Recover
Yiqing Xu, Jiajun Wu
A robot may know how to perform a task yet fail when a human asks for it naturally. We study this human--VLA communication gap by separating an \emph{information gap}, where task s…
Coarse-Grained Predictive Resource Allocation Framework enabling In-Premise XR Collaborations
Sourav Mondal, Elaine Wong
Immersive extended reality (XR) applications are key enablers of human-centric connectivity in next-generation networks. However, meeting their high-throughput, ultra-low-latency,…
The Norm Spectrum of Barnes-Wall Lattices Below Twice the Minimum
Yuhang Cao, Sihuang Hu, Hexiang Huang +1
Let be the Barnes-Wall lattice of dimension , normalized to have minimum squared norm . We determine its complete norm spectrum strictly between and…
MindTopo: Can Foundation Models Reason in Topological Space?
Yunfei Ge, Anbang Liu, Qineng Wang +9
Spatial reasoning depends not only on metric properties such as distance, angle, and shape, but also on topological relations that remain invariant under continuous deformation. Co…
One Demonstration, Many Objects: Generalizing Manipulation via Local Contact Geometry
Satvik Sharma, Samrat Sahoo, Huang Huang +4
Dexterous manipulation with multi-fingered robot hands promises human-level dexterity, but collecting large-scale dexterous robot hand data remains difficult. Learning from human d…
TrAct: Bridging Robot Control and Visual Prediction with Visual Tracks
Zhi Cao, Howard Ji, Kevin Zhang +4
Robot actions are inherently embodiment-specific and only weakly aligned with image-space visual changes, limiting their effectiveness as conditioning signals for robot world model…
CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild
Jian Yang, Haau-Sing Li, Shawn Guo +10
As large language models (LLMs) continue to advance in coding capabilities, their potential in cybersecurity has drawn increasing research attention, with closed-source LLMs (e.g.,…
WebWorld: The Browser as a World Model for Self-Improving Web Code
Jiajun Wu, Jian Yang, Yaxin Du +7
VLM-driven self-improvement of web code has a structural flaw: the model that proposes the repair is the model that judges it, and visual plausibility under that judge is a poor pr…
FL-MAESTRO: Multi-Agent LLM Orchestration for Resource-Constrained Federated Learning
Jiajun Wu, Zirui Wang, Jiayu Zhou +2
In Federated Learning (FL), the communication topology is a runtime variable rather than a fixed design choice, since links and edge devices drop in and out during training. Each r…
Masked Visual Actions for Unified World Modeling
Hadi Alzayer, Wenlong Huang, Haonan Chen +8
Video models absorb rich priors over how the visual world moves, interacts, and responds to contact, making them promising substrates for robotic world modeling. The central challe…
LOTAPO: Leave-One-Turn Attribution for Self-Generated Process Rewards in Multi-Turn Search Reasoning
Qiang Zhu, Jiajun Wu, Longyi Wang
Reinforcement learning for multi-turn search reasoning typically relies on terminal outcome rewards, which cannot distinguish useful, redundant, and harmful intermediate interactio…
A vision foundation model for single-cell biology via spatial gene cartography
Ridvan Yesiloglu, Sakib Mostafa, James Zou +5
Most single-cell foundation models are adapted from language models, representing each cell as a sequence of gene tokens. This discards the relationships among genes and often the…
APIVOT: Adaptive Planning with Interleaved Vision-Language Thoughts
Emily Jin, Joy Hsu, Yiqing Xu +3
Long-horizon robot planning requires jointly reasoning over semantic task structure and geometric feasibility. To successfully execute a task, a robot must decompose goals, select…
Planning with the Views
Kangrui Wang, Linjie Li, Zhengyuan Yang +7
Can VLMs predict how each camera move changes the view, and plan many such moves ahead? We call this capability view planning, requiring (1)understanding how a single action transf…
CoStream: Composing Simple Behaviors for Generalizable Complex Manipulation
Haonan Chen, Yuxiang Ma, Stephen Tian +7
Long-horizon, contact-rich complex manipulation tasks, such as seating a GPU into a PCIe slot, demand both millimeter high precision and out-of-the-box generalization to new tasks.…
HarmVideoBench: Benchmarking Harmful Video Understanding in Large Multimodal Models
Jiajun Wu, Haoyu Kang, Yining Sun +13
Large vision-language models (LVLMs) have recently shown immense potential in automated content moderation, sparking growing interest in developing harmful-video benchmarks. Howeve…
VPA-Guard: Defending and Benchmarking Image-to-Video Generation Against Visual Prompt Attacks
Yining Sun, Haoyu Kang, Jiajun Wu +7
Recent advancements in Image-to-Video (I2V) generation have transformed input images from simple appearance references into interactive control interfaces where visual cues such as…
InSight: Self-Guided Skill Acquisition via Steerable VLAs
Maggie Wang, Lars Osterberg, Stephen Tian +5
Vision-language-action (VLA) models excel at robot manipulation via imitation learning, but adapting them to new tasks often requires additional human demonstrations, which can be…
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling
Jian Yang, Shawn Guo, Wei Zhang +16
Looped Transformers scale latent computation by repeatedly applying shared blocks, but sequential looping increases latency and KV-cache memory with the loop count. Parallel loop T…
DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners?
Jadelynn Dao, Milan Ganai, Yasmina Abukhadra +7
Vision-Language Models (VLMs) are increasingly deployed as high-level planners for embodied agents, with an emerging strategy of scaling test-time compute to improve capability. Ho…
Aggregating LLM-Based Weak Verifiers for Spatial Layout Generation
Sharon Zhang, R. Kenny Jones, Jiajun Wu +1
We present a pipeline for building and aggregating task-specific, LLM-generated weak (imperfect) verifiers into a strong verifier for spatial layout domains. Given a task descripti…
StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception
Evans Han, Yunfan Jiang, Yingke Wang +6
Recent advances in robot imitation learning have produced powerful visuomotor policies that manipulate diverse objects from visual inputs. However, monocular observations lack dept…