Search papers, labs, and topics across Lattice.
The paper introduces EgoPoint-Bench, a new benchmark to evaluate how well MLLMs understand pointing gestures in egocentric vision, revealing that current models often hallucinate referents based on proximity or saliency. They found that state-of-the-art MLLMs struggle with egocentric pointing, exhibiting "Referential Hallucination." However, fine-tuning on their synthetic data significantly improves performance and generalization from simulation to real-world scenarios.
MLLMs often *hallucinate* the referent of a pointing gesture, latching onto nearby or salient objects instead of truly understanding spatial semantics.
Egocentric AI agents, such as smart glasses, rely on pointing gestures to resolve referential ambiguities in natural language commands. However, despite advancements in Multimodal Large Language Models (MLLMs), current systems often fail to precisely ground the spatial semantics of pointing. Instead, they rely on spurious correlations with visual proximity or object saliency, a phenomenon we term"Referential Hallucination."To address this gap, we introduce EgoPoint-Bench, a comprehensive question-answering benchmark designed to evaluate and enhance multimodal pointing reasoning in egocentric views. Comprising over 11k high-fidelity simulated and real-world samples, the benchmark spans five evaluation dimensions and three levels of referential complexity. Extensive experiments demonstrate that while state-of-the-art proprietary and open-source models struggle with egocentric pointing, models fine-tuned on our synthetic data achieve significant performance gains and robust sim-to-real generalization. This work highlights the importance of spatially aware supervision and offers a scalable path toward precise egocentric AI assistants. Project page: https://guyyyug.github.io/EgoPoint-Bench/
Tsinghua AI