activity
20242026
collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2026

STAR-VLM: Spatiotemporal Grounding Vision-Language Models for Motion and Velocity Estimation via Automotive Radar Supervision

Pou-Chun Kung, Aryaman Rao, Utkrisht Sahai +4

Vision-language models (VLMs) are emerging as a key component of embodied intelligence, with growing applications in auto-labeling and end-to-end autonomous driving. However, exist…

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.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.CV2025

CoST: Efficient Collaborative Perception From Unified Spatiotemporal Perspective

Zongheng Tang, Yi Liu, Yifan Sun +4

Collaborative perception shares information among different agents and helps solving problems that individual agents may face, e.g., occlusions and small sensing range. Prior metho…

cs.CV2025

CycleVAR: Repurposing Autoregressive Model for Unsupervised One-Step Image Translation

Yi Liu, Shengqian Li, Zuzeng Lin +2

The current conditional autoregressive image generation methods have shown promising results, yet their potential remains largely unexplored in the practical unsupervised image tra…

cs.CV2024

Knowledge Distillation via Query Selection for Detection Transformer

Yi Liu, Luting Wang, Zongheng Tang +4

Transformers have revolutionized the object detection landscape by introducing DETRs, acclaimed for their simplicity and efficacy. Despite their advantages, the substantial size of…