Yihao Wu

AR-Nav Benchmark: Augmented Reality Navigation with Vision and Language

Augmented Reality (AR) navigation has emerged as a transformative tool for spatial intelligence, enabling users to interactively explore complex environments through wearable and mobile AR devices. However, current AR navigation systems struggle with low indoor localization accuracy, weak semantic u

EVALUATING BIAS IN SPOKEN DIALOGUE LLMS FOR REAL-WORLD DECISIONS AND RECOMMENDATIONS

While biases in large language models (LLMs), such as stereotypes and cultural tendencies in outputs, have been examined and identified, their presence and characteristics in spoken dialogue models (SDMs) with audio input and output remain largely unexplored. Paralinguistic features, such as age, ge…

Offline Reinforced Finetuning for Chunk-Based VLA Via Real-World RL Policy Distillation with Vision-Guided Copilot

MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix

We introduce MMAR, a new benchmark designed to evaluate the deep reasoning capabilities of Audio-Language Models (ALMs) across massive multi-disciplinary tasks. MMAR comprises 1,000 meticulously curated audio-question-answer triplets, collected from real-world internet videos and refined through ite…

Autonomous Vision-Guided Two-Arm Collaborative Microassembly Using Learned Manipulation Model

This letter presents an integrated micromanipulation system suited for precise assembly of micro-parts in intricate environments. By embedding the Global Attention Mechanism (GAM) into YOLOv8, the system not only enhances its performance but also accurately identifies target keypoints, pinpointing t