1.2k citations · 1.4k across the 49 of their papers we have counts for
52 papers
Action-Slot: Structured Action-Centric Representation Learning for Multi-Agent Atomic Activity Understanding
Yu-Ho Chang, Chi-Hsi Kung, Yi-Hsuan Tsai +1
Atomic activity understanding aims to recognize and localize structured traffic behaviors that jointly encode motion patterns and their grounding in road topology. Unlike conventio…
PhysCaP: Grounding Code-as-Policy Agent with Physics-Informed Exploration
Chen-Yu Lin, Jing-Wen Chen, Hsueh-En Chang +8
We present PhysCaP, a Physics-Informed Code-as-Policy agent system for active perception in robotic manipulation. While vision-language-action policies excel at imitating demonstra…
ECoSim: Data Efficient Fine-Tuning for Controllable Traffic Simulation
Yu-Hsiang Chen, Wei-Jer Chang, Yi-Ting Chen +1
Controllable traffic simulation is critical for testing autonomous driving systems, yet existing approaches often require retraining large generative models with extensive annotate…
Direct Action-Head Injection of A Grounded 3D Point Unlocks Spatial and Task Generalization
Shiang-Feng Tsai, Jin-Cheng Jhang, Yen-Ling Tai +6
Vision-Language-Action (VLA) models leverage large-scale vision-language pretraining for flexible robot manipulation, yet at test time they remain brittle to changed object positio…
Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini
Madhuri Shanbhogue, Zhe Li, Shanfeng Zhang +86
We introduce Gemini Embedding 2, a native multimodal embedding model that allows embedding video, audio, image, and text modalities in a unified representation space. We leverage t…
NudgeVAD: Language-Nudged End-to-End Driving via FiLM Residuals
Chieh-Chi Yang, Yu-Hsiang Chen, Yi-Ting Chen
Natural-language instructions promise controllable end-to-end driving, but their benefit can be hidden when planners already receive reliable high-level commands. We propose NudgeV…
ADAPT: Benchmarking Commonsense Planning under Unspecified Affordance Constraints
Pei-An Chen, Yong-Ching Liang, Jia-Fong Yeh +4
Intelligent embodied agents should not simply follow instructions, as real-world environments often involve unexpected conditions and exceptions. However, existing methods usually…
Uncertainty-Aware Vision-based Risk Object Identification via Conformal Risk Tube Prediction
Kai-Yu Fu, Yi-Ting Chen
We study object importance-based vision risk object identification (Vision-ROI), a key capability for hazard detection in intelligent driving systems. Existing approaches make dete…
Towards Driver Behavior Understanding: Weakly-Supervised Risk Perception in Driving Scenes
Nakul Agarwal, Yi-Ting Chen, Behzad Dariush
Achieving zero-collision mobility remains a key objective for intelligent vehicle systems, which requires understanding driver risk perception-a complex cognitive process shaped by…
HetroD: A High-Fidelity Drone Dataset and Benchmark for Autonomous Driving in Heterogeneous Traffic
Yu-Hsiang Chen, Wei-Jer Chang, Christian Kotulla +7
We present HetroD, a dataset and benchmark for developing autonomous driving systems in heterogeneous environments. HetroD targets the critical challenge of navi- gating real-world…
Affordance-Guided Coarse-to-Fine Exploration for Base Placement in Open-Vocabulary Mobile Manipulation
Tzu-Jung Lin, Jia-Fong Yeh, Hung-Ting Su +3
In open-vocabulary mobile manipulation (OVMM), task success often hinges on the selection of an appropriate base placement for the robot. Existing approaches typically navigate to…
EmbeddingGemma: Powerful and Lightweight Text Representations
Henrique Schechter Vera, Sahil Dua, Biao Zhang +86
We introduce EmbeddingGemma, a new lightweight, open text embedding model based on the Gemma 3 language model family. Our innovative training recipe strategically captures knowledg…
Controllable Collision Scenario Generation via Collision Pattern Prediction
Pin-Lun Chen, Chi-Hsi Kung, Che-Han Chang +2
Evaluating the safety of autonomous vehicles (AVs) requires diverse, safety-critical scenarios, with collisions being especially important yet rare and unsafe to collect in the rea…
GRITS: A Spillage-Aware Guided Diffusion Policy for Robot Food Scooping Tasks
Yen-Ling Tai, Yi-Ru Yang, Kuan-Ting Yu +2
Robotic food scooping is a critical manipulation skill for food preparation and service robots. However, existing robot learning algorithms, especially learn-from-demonstration met…
Task-Oriented Human Grasp Synthesis via Context- and Task-Aware Diffusers
An-Lun Liu, Yu-Wei Chao, Yi-Ting Chen
In this paper, we study task-oriented human grasp synthesis, a new grasp synthesis task that demands both task and context awareness. At the core of our method is the task-aware co…
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431
In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…
EgoVIS@CVPR: What Changed and What Could Have Changed? State-Change Counterfactuals for Procedure-Aware Video Representation Learning
Chi-Hsi Kung, Frangil Ramirez, Juhyung Ha +3
Understanding a procedural activity requires modeling both how action steps transform the scene, and how evolving scene transformations can influence the sequence of action steps,…
ArticuBot: Learning Universal Articulated Object Manipulation Policy via Large Scale Simulation
Yufei Wang, Ziyu Wang, Mino Nakura +5
This paper presents ArticuBot, in which a single learned policy enables a robotics system to open diverse categories of unseen articulated objects in the real world. This task has…
Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting
Shu-Wei Lu, Yi-Hsuan Tsai, Yi-Ting Chen
Bird's-eye view (BEV) perception has gained significant attention because it provides a unified representation to fuse multiple view images and enables a wide range of down-stream…
ATARS: An Aerial Traffic Atomic Activity Recognition and Temporal Segmentation Dataset
Zihao Chen, Hsuanyu Wu, Chi-Hsi Kung +2
Traffic Atomic Activity which describes traffic patterns for topological intersection dynamics is a crucial topic for the advancement of intelligent driving systems. However, exist…
What Changed and What Could Have Changed? State-Change Counterfactuals for Procedure-Aware Video Representation Learning
Chi-Hsi Kung, Frangil Ramirez, Juhyung Ha +3
Understanding a procedural activity requires modeling both how action steps transform the scene, and how evolving scene transformations can influence the sequence of action steps,…
Mitigating Cross-Modal Distraction and Ensuring Geometric Feasibility via Affordance-Guided and Self-Consistent MLLMs for Task Planning in Instruction-Following Manipulation
Yu-Hong Shen, Chuan-Yu Wu, Yi-Ru Yang +2
We investigate the use of Multimodal Large Language Models (MLLMs) with in-context learning for closed-loop task planning in instruction-following manipulation. We identify four es…
Potential Field as Scene Affordance for Behavior Change-Based Visual Risk Object Identification
Pang-Yuan Pao, Shu-Wei Lu, Ze-Yan Lu +1
We study behavior change-based visual risk object identification (Visual-ROI), a critical framework designed to detect potential hazards for intelligent driving systems. Existing m…
Shared-unique Features and Task-aware Prioritized Sampling on Multi-task Reinforcement Learning
Po-Shao Lin, Jia-Fong Yeh, Yi-Ting Chen +1
We observe that current state-of-the-art (SOTA) methods suffer from the performance imbalance issue when performing multi-task reinforcement learning (MTRL) tasks. While these meth…