activity
20242026
collaborators

7 papers

cs.RO2026

Zero-Human Demonstration End-to-end Autonomous Driving with Trajectory Scorer

Zhenxin Li, Nadine Chang, Wenhao Yao +9

Human demonstrations are widely considered the cornerstone of end-to-end (E2E) autonomous driving despite human demonstration's scarcity for long-tail and safety-critical scenarios…

cs.CV2026

CRISP: A Spatiotemporal Camera-Radar Backbone for Driving via Forecasting-Based World-Model Pretraining

Jingyu Song, Yi Liu, Katherine A. Skinner

Camera-radar (CR) fusion is a practical sensing configuration for autonomous driving, but existing models are typically trained with task-specific supervision, limiting reusable re…

cs.CV2026

DriveCritic: Towards Context-Aware, Human-Aligned Evaluation for Autonomous Driving with Vision-Language Models

Jingyu Song, Zhenxin Li, Shiyi Lan +6

Benchmarking autonomous driving planners to align with human judgment remains a critical challenge, as state-of-the-art metrics like the Extended Predictive Driver Model Score (EPD…

cs.LG2025

CHyLL: Learning Continuous Neural Representations of Hybrid Systems

Sangli Teng, Hang Liu, Jingyu Song +1

Learning the flows of hybrid systems that have both continuous and discrete time dynamics is challenging. The existing method learns the dynamics in each discrete mode, which suffe…

cs.CV2025

FishDetector-R1: Unified MLLM-Based Framework with Reinforcement Fine-Tuning for Weakly Supervised Fish Detection, Segmentation, and Counting

Yi Liu, Jingyu Song, Vedanth Kallakuri +1

Analyzing underwater fish imagery is critical for ecological monitoring but remains difficult due to visual degradation and costly annotations. We introduce FishDetector-R1, a unif…

cs.RO2025

OceanSim: A GPU-Accelerated Underwater Robot Perception Simulation Framework

Jingyu Song, Haoyu Ma, Onur Bagoren +3

Underwater simulators offer support for building robust underwater perception solutions. Significant work has recently been done to develop new simulators and to advance the perfor…