WorldSculpt: Generating Compositional Worlds from Grounded Videos Paper • 2609.05416 • Published Sep 4 • 24
Reasmory: 3D Reconstruction as Explicit Memory for VLMs Spatial Reasoning Paper • 2606.00963 • Published May 31
$R^2$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding Paper • 2404.00801 • Published Mar 31, 2024 • 1
See, Hear, and Understand: Benchmarking Audiovisual Human Speech Understanding in Multimodal Large Language Models Paper • 2512.02231 • Published Dec 1, 2025 • 9
LASER: Lip Landmark Assisted Speaker Detection for Robustness Paper • 2501.11899 • Published Jan 21, 2025
See, Hear, and Understand: Benchmarking Audiovisual Human Speech Understanding in Multimodal Large Language Models Paper • 2512.02231 • Published Dec 1, 2025 • 9
UniTalk: Towards Universal Active Speaker Detection in Real World Scenarios Paper • 2505.21954 • Published May 28, 2025 • 1
Affordance-Aware Object Insertion via Mask-Aware Dual Diffusion Paper • 2412.14462 • Published Dec 19, 2024 • 14