activity
20242026
collaborators

7 papers

cs.CV2026

StreamCacheVGGT: Streaming Visual Geometry Transformers with Robust Scoring and Hybrid Cache Compression

Xuanyi Liu, Chunan Yu, Deyi Ji +6

Reconstructing dense 3D geometry from continuous video streams requires stable inference under a constant memory budget. Existing frameworks primarily rely on a ``pure evict…

cs.CV2026

Robust 4D Visual Geometry Transformer with Uncertainty-Aware Priors

Ying Zang, Yidong Han, Chaotao Ding +8

Reconstructing dynamic 4D scenes is an important yet challenging task. While 3D foundation models like VGGT excel in static settings, they often struggle with dynamic sequences whe…

cs.CV2026

Beyond Binary Preference: Aligning Diffusion Models to Fine-grained Criteria by Decoupling Attributes

Chenye Meng, Zejian Li, Zhongni Liu +9

Post-training alignment of diffusion models relies on simplified signals, such as scalar rewards or binary preferences. This limits alignment with complex human expertise, which is…

cs.CV2025

Inversion-DPO: Precise and Efficient Post-Training for Diffusion Models

Zejian Li, Yize Li, Chenye Meng +7

Recent advancements in diffusion models (DMs) have been propelled by alignment methods that post-train models to better conform to human preferences. However, these approaches typi…

cs.CV2025

Diffusion Distillation With Direct Preference Optimization For Efficient 3D LiDAR Scene Completion

An Zhao, Shengyuan Zhang, Ling Yang +6

The application of diffusion models in 3D LiDAR scene completion is limited due to diffusion's slow sampling speed. Score distillation accelerates diffusion sampling but with perfo…

cs.CV2024

LAION-SG: An Enhanced Large-Scale Dataset for Training Complex Image-Text Models with Structural Annotations

Zejian Li, Chenye Meng, Yize Li +9

Recent advances in text-to-image (T2I) generation have shown remarkable success in producing high-quality images from text. However, existing T2I models show decayed performance in…