Showing 2026Show all
2 papers · 1 filter
cs.CV2026
Unlocking Dense Metric Depth Estimation in VLMs
Hanxun Yu, Xuan Qu, Yuxin Wang +2
Vision-Language Models (VLMs) excel at 2D tasks such as grounding and captioning, yet remain limited in 3D understanding. A key limitation is their text-only supervision paradigm,…
cs.CV2026
JAEGER: Joint 3D Audio-Visual Grounding and Reasoning in Simulated Physical Environments
Zhan Liu, Changli Tang, Yuxin Wang +7
Current audio-visual large language models (AV-LLMs) are predominantly restricted to 2D perception, relying on RGB video and monaural audio. This design choice introduces a fundame…