16 papers
BARD: Bridging AutoRegressive and Diffusion Vision-Language Models Via Highly Efficient Progressive Block Merging and Stage-Wise Distillation
Baoyou Chen, Hanchen Xia, Peng Tu +5
Autoregressive vision-language models (VLMs) deliver strong multimodal capability, but their token-by-token decoding imposes a fundamental inference bottleneck. Diffusion VLMs offe…
Glob3R: Global Structure-from-Motion with 3D Foundation Models
Junyuan Deng, Heng Li, Kejie Qiu +7
Recent 3D geometric foundation models, such as VGGT, provide robust feed-forward 3D reconstruction by directly predicting camera poses and 3D scene points from input images. Howeve…
3DThinkVLA: Endowing Vision-Language-Action Models with Latent 3D Priors via 3D-Thinking-Guided Co-training
Jiaxin Shi, Xidong Zhang, Fucai Zhu +3
We propose a 3D-thinking-guided co-training framework that enables vision-language-action (VLA) models to perform 3D spatial reasoning implicitly during action prediction. Our core…
FocusVLA: Focused Visual Utilization for Vision-Language-Action Models
Yichi Zhang, Weihao Yuan, Yizhuo Zhang +2
Vision-Language-Action (VLA) models improve action generation by conditioning policies on rich vision-language information. However, current auto-regressive policies are constraine…
LHM++: An Efficient Large Human Reconstruction Model for Pose-free Images to 3D
Lingteng Qiu, Peihao Li, Heyuan Li +9
Reconstructing animatable 3D humans from casually captured images of articulated subjects without camera or pose information is highly practical but remains challenging due to view…
ViSA: 3D-Aware Video Shading for Real-Time Upper-Body Avatar Creation
Fan Yang, Heyuan Li, Peihao Li +9
Generating high-fidelity upper-body 3D avatars from one-shot input image remains a significant challenge. Current 3D avatar generation methods, which rely on large reconstruction m…