4 citations · 5 across the 15 of their papers we have counts for
14 papers · 1 filter
DeXplicit: Making Physical State Explicit in Dexterous Manipulation World Models
Adam Lee, Mutian Xu, Yukang Cao +2
Before acting on an object, a robot needs to anticipate how its hand motion will change the physical world and what the resulting scene will look like. Existing approaches typicall…
DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling
Seongheon Park, Heecheol Kim, Shulin Tian +5
Scaling robot data and model capacity has improved Vision-Language-Action (VLA) policies, but further progress is constrained by the high cost of robotic data. Verifier-guided test…
EgoTools: Towards Tool-Centric Reasoning in Real-World Egocentric Videos
Shulin Tian, Junsu Kim, Shuai Liu +17
Real-world embodied tasks, from everyday activities to professional procedures, require agents to act under physical constraints while tracking evolving object and task states. Too…
Video-HopChain: Multi-Hop Questions and Confidence-Gated Exploration for Video Reasoning Models
Trung Nguyen Quang, Yuhao Dong, Shuo Sun +4
HopChain has shown on still images that multi-hop data synthesis improves vision-language reasoning, because long chain-of-thought reasoning exposes errors that compound across ste…
V-Rubrics: Visual Faithfulness via Rubric-Based Reinforcement Learning
Shulin Tian, Minglun Li, Yuhao Dong +6
Vision-language models can produce fluent answers that are insufficiently grounded in the visual evidence: a single unsupported object, chart value, or intermediate inference can u…
Open Evaluation Agent: Efficient and Promptable Evaluation of Visual Generative Models
Shulin Tian, Ziqi Huang, Fan Zhang +3
Recent advances in visual generative models have enabled high-quality image and video generation, but evaluating these models often demands sampling hundreds or thousands of images…
S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence
Yalun Dai, Hao Li, Shulin Tian +8
Real-world spatial intelligence requires reasoning over a continuous and evolving 3D world, yet existing VLMs and tool-augmented agents largely remain tied to static, stateless inf…
Apple-: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence
Runmao Yao, Kairui Hu, Yukang Cao +11
Modern video generation models are increasingly hailed as emerging world models with an internalized grasp of physical law. Yet existing benchmarks largely evaluate physical plausi…
FileGram: Grounding Agent Personalization in File-System Behavioral Traces
Shuai Liu, Shulin Tian, Kairui Hu +6
Coworking AI agents operating within local file systems are rapidly emerging as a paradigm in human-AI interaction; however, effective personalization remains limited by severe dat…
A Simple Baseline for Streaming Video Understanding
Yujiao Shen, Shulin Tian, Jingkang Yang +1
Recent streaming video understanding methods increasingly rely on complex memory mechanisms to handle long video streams. We challenge this trend with a simple finding: a sliding-w…
HippoCamp: Benchmarking Contextual Agents on Personal Computers
Zhe Yang, Shulin Tian, Kairui Hu +9
We present HippoCamp, a new benchmark designed to evaluate agents' capabilities on multimodal file management. Unlike existing agent benchmarks that focus on tasks like web interac…
PerceptionComp: A Video Benchmark for Complex Perception-Centric Reasoning
Shaoxuan Li, Zhixuan Zhao, Hanze Deng +9
We introduce PerceptionComp, a manually annotated benchmark for complex, long-horizon, perception-centric video reasoning. PerceptionComp is designed so that no single moment is su…
Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models
Yuhao Dong, Zuyan Liu, Shulin Tian +2
Large Language Models (LLMs) have achieved remarkable reliability and advanced capabilities through extended test-time reasoning. However, extending these capabilities to Multi-mod…
Demo-ICL: In-Context Learning for Procedural Video Knowledge Acquisition
Yuhao Dong, Shulin Tian, Shuai Liu +6
Despite the growing video understanding capabilities of recent Multimodal Large Language Models (MLLMs), existing video benchmarks primarily assess understanding based on models' s…