1 citations · 4 across the 37 of their papers we have counts for
32 papers · 1 filter
Are We Overthinking One-Step Generation?
Woobin Park, Jaeyeon Kim, Yilun Du +2
Diffusion and flow matching are now dominant frameworks for generative modeling in continuous domains, but they typically require multiple network evaluations at inference. This ha…
InSight: A Mobile Assistant Helping Visually Impaired People Navigate Unfamiliar Environment
Junwei Zheng, Jiale Wei, Di Wen +6
Navigating unfamiliar outdoor environments is one of the most demanding everyday tasks for people with visual impairments (PVI). However, existing navigation systems cannot simulta…
VL-DocIR: A Benchmark for Vision-Based Long Document Information Retrieval
Simon Ott, Yufan Chen, Ruiping Liu +6
Vision-based document retrieval has improved rapidly, but current evaluation settings still emphasize short documents and single relevant pages. This leaves an important gap betwee…
OmniAct3D: Leveraging Foundation Geometry and Evidence-Grounded Reasoning for Panoramic 3D Detection
Runtong Wu, Fei Teng, Di Wen +3
Accurate 3D detection is essential for mobile embodied agents, while Vision Foundation Models (VFMs) offer transferable visual and geometric priors. Yet existing VFM-based 3D detec…
FUSEye: Training-Light Fisheye Detection with Overlapping Views and Zero-Initialized Adapters
Wenya Su, Kai Luo, Di Wen +5
Fisheye cameras give mobile robots a single-sensor, low-cost view of their surroundings, yet the COCO-pretrained detectors that practitioners routinely reuse fail on them: strong r…
HEIR: Learning Human-Entity Interactions with Functional Roles
Di Wen, Wenhao Guo, Yuedong Tan +15
Understanding human-entity interactions requires recovering each person-action event's participants, roles, and shared identities. This structure can support embodied agents by cla…
Do LiDAR Language Models Really Understand Spatio-temporal Relationships?
Runyi Yang, Murat Akkoyun, Di Wen +8
Recent 4D LiDAR language models aim to reason about objects and their evolving spatial relationships. Yet, in our evaluation, always selecting the same option nearly matches the mu…
Algebraic Consistency Alone Does Not Certify Temporal Structure in Latent Action Models
Di Wen, Ruodi Zhang, Kailun Yang +1
Latent action models infer a code for the transition between two frames of action-free video. Recent methods regularise this code to compose additively and reverse antisymmetricall…
FOCAL-VLA: Subtask-Guided Geometry Distillation and Implicit World Modeling for Vision-Language-Action Models
Zhiyuan Gao, Di Wen, Yanxiang Zhan +4
Vision-language-action (VLA) models built on pretrained vision-language models have demonstrated strong performance across diverse robotic manipulation tasks. However, VLA models t…
Hand-Aware Transition Modeling for Bimanual Procedural Anomaly Detection
Di Wen, Jimmy Weissert, Luc Maria Scherrer +7
Procedural anomaly detection in bimanual assembly requires judging each hand action against the execution so far. A corrective action may look unusual in isolation, while a visuall…
PROVIA: Procedure State Tracking for Online Mistake Detection in Egocentric Videos
Di Wen, Kailun Yang, Jimmy Weissert +7
An assistant watching egocentric video should notice a mistake from past frames alone, before the next step begins, and keep working once the person recovers. A mistake changes the…
INSPECT: Learning Robot View Selection from Assistant Use
Di Wen, Kailun Yang, Wenhao Guo +7
Robots inspecting an assembly must determine which parts are present and whether they are correctly installed. During egocentric assembly assistance, head motion and workpiece hand…
CoRef-GS: Cooperative Referring Gaussian Splatting for Multi-Agent Scene Understanding
Zhikun Zhou, Kunyu Peng, Runyi Yang +7
Referring scene understanding for embodied robots requires grounding object- and relation-centric language queries from a designated viewpoint. While a local semantic Gaussian map…
RoboFind: Multi-Agent Personalized Object Search for People Who Are Blind or Have Low Vision
Ruiping Liu, Shaofang Quan, Qian Yin +10
Blind and low-vision users often need to locate a specific personal object rather than an arbitrary instance of the same category. The task calls for a robot that can move through…
GuideFetch: A Task Coordination Framework for Concurrent Navigation and Object Retrieval in Assistive Robot Dogs
Qian Yin, Ruiping Liu, Kunyu Peng +7
Consider one robot guide dog escorting a blind user to a seat while a second retrieves and delivers an object. We introduce \textsc{GuideFetch}, a framework for coordinating this c…
HGeo-TopoMap: Boosting Topological Mapping with Hierarchical Geometric Priors
Siyu Li, Kunyu Peng, Di Wen +3
Topological maps are key outputs of autonomous driving perception systems, delivering essential road information for path planning. They identify instances such as centerlines and…
Hand-centric Human-to-Robot Trajectory Transfer from Video Demonstrations via Object Category-agnostic Temporal Localization
Yitian Shi, Di Wen, Zhengqi Han +6
Human videos provide a scalable source of demonstrations for robot imitation learning. However, converting them into executable and semantically aligned robot trajectories requires…
Seeing Together: Multi-Robot Cooperative Egocentric Spatial Reasoning with Multimodal Large Language Models
Kunyu Peng, Zhikun Zhou, Kailun Yang +9
Multimodal Large Language Models (MLLMs) have made substantial progress in egocentric video understanding, but their ability to reason cooperatively from multiple embodied viewpoin…
IMPACT-Scribe: Interactive Temporal Action Segmentation with Boundary Scribbles and Query Planning
Qian Yin, Di Wen, Kunyu Peng +11
Dense temporal annotation of procedural activity videos is vital for action understanding and embodied intelligence but remains labor-intensive due to reactive tools. Each correcti…
IMPACT-HOI: Supervisory Control for Onset-Anchored Partial HOI Event Construction
Haoshen Zhang, Di Wen, Kunyu Peng +12
We present IMPACT-HOI, a mixed-initiative framework for annotating egocentric procedural video by constructing structured event graphs for Human-Object Interactions (HOI), motivate…
EgoExoMem: Cross-View Memory Reasoning over Synchronized Egocentric and Exocentric Videos
Ruiping Liu, Junwei Zheng, Yufan Chen +7
Egocentric memory is widely used in embodied intelligence, but it may be insufficient for comprehensive spatial-temporal reasoning. Inspired by human recall from both field and obs…
IMPACT-CYCLE: A Contract-Based Multi-Agent System for Claim-Level Supervisory Correction of Long-Video Semantic Memory
Weitong Kong, Di Wen, Kunyu Peng +10
Correcting errors in long-video understanding is disproportionately costly: existing multimodal pipelines produce opaque, end-to-end outputs that expose no intermediate state for i…
IMPACT: A Dataset for Multi-Granularity Human Procedural Action Understanding in Industrial Assembly
Di Wen, Zeyun Zhong, David Schneider +18
We introduce IMPACT, a synchronized five-view RGB-D dataset for deployment-oriented industrial procedural understanding, built around real assembly and disassembly of a commercial…
Rethinking Video Human-Object Interaction: Set Prediction over Time for Unified Detection and Anticipation
Yuanhao Luo, Di Wen, Kunyu Peng +5
Video-based human-object interaction (HOI) understanding requires both detecting ongoing interactions and anticipating their future evolution. However, existing methods usually tre…