Picture for Jun Ma

Jun Ma

The Hong Kong University of Science and Technology, The Hong Kong University of Science and Technology

LOVON: Legged Open-Vocabulary Object Navigator

Add code
Jul 09, 2025
Viaarxiv icon

Exploring the Design Space of 3D MLLMs for CT Report Generation

Add code
Jun 26, 2025
Viaarxiv icon

NetRoller: Interfacing General and Specialized Models for End-to-End Autonomous Driving

Add code
Jun 17, 2025
Viaarxiv icon

Abstract, Align, Predict: Zero-Shot Stance Detection via Cognitive Inductive Reasoning

Add code
Jun 16, 2025
Viaarxiv icon

PhyBlock: A Progressive Benchmark for Physical Understanding and Planning via 3D Block Assembly

Add code
Jun 10, 2025
Viaarxiv icon

Any Large Language Model Can Be a Reliable Judge: Debiasing with a Reasoning-based Bias Detector

Add code
May 21, 2025
Viaarxiv icon

LD-Scene: LLM-Guided Diffusion for Controllable Generation of Adversarial Safety-Critical Driving Scenarios

Add code
May 16, 2025
Viaarxiv icon

DSDrive: Distilling Large Language Model for Lightweight End-to-End Autonomous Driving with Unified Reasoning and Planning

Add code
May 08, 2025
Viaarxiv icon

ApexNav: An Adaptive Exploration Strategy for Zero-Shot Object Navigation with Target-centric Semantic Fusion

Add code
Apr 22, 2025
Viaarxiv icon

IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMs

Add code
Apr 21, 2025
Viaarxiv icon