Lin Ma

15

Papers

129

Total Citations

Papers (15)

Making Large Language Models Better Planners with Reasoning-Decision Alignment

AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning

ColNeRF: Collaboration for Generalizable Sparse Input Neural Radiance Field

UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection

RoboTron-Mani: All-in-One Multimodal Large Model for Robotic Manipulation

RoboTron-Drive: All-in-One Large Multimodal Model for Autonomous Driving

CO-MOT: Boosting End-to-end Transformer-based Multi-Object Tracking via Coopetition Label Assignment and Shadow Sets

Towards Efficient Foundation Model for Zero-shot Amodal Segmentation

RoboTron-Nav: A Unified Framework for Embodied Navigation Integrating Perception, Planning, and Prediction

RoboTron-Sim: Improving Real-World Driving via Simulated Hard-Case

Instance-Aware Multi-Camera 3D Object Detection with Structural Priors Mining and Self-Boosting Learning

Affordances-Oriented Planning Using Foundation Models for Continuous Vision-Language Navigation

DisTime: Distribution-based Time Representation for Video Large Language Models

Misalignment-Robust Frequency Distribution Loss for Image Transformation

InstaGen: Enhancing Object Detection by Training on Synthetic Dataset