Papers
Dense2MoE: Restructuring Diffusion Transformer to MoE for Efficient Text-to-Image Generation
Youwei Zheng, Yuxi Ren, Xin Xia et al.
Unraveling the Effects of Synthetic Data on End-to-End Autonomous Driving
Junhao Ge, Zuhong Liu, Longteng Fan et al.
GeoFormer: Geometry Point Encoder for 3D Object Detection with Graph-based Transformer
Xin Jin, Haisheng Su, Cong Ma et al.
Dual-Expert Consistency Model for Efficient and High-Quality Video Generation
Zhengyao Lv, Chenyang Si, Tianlin Pan et al.
Dirichlet-Constrained Variational Codebook Learning for Temporally Coherent Video Face Restoration
Baoyou Chen, Ce Liu, Weihao Yuan et al.
Task Vector Quantization for Memory-Efficient Model Merging
Youngeun Kim, Seunghwan Lee, Aecheon Jung et al.
FusionPhys: A Flexible Framework for Fusing Complementary Sensing Modalities in Remote Physiological Measurement
Chenhang Ying, Huiyu Yang, Jieyi Ge et al.
MistSense: Versatile Online Detection of Procedural and Execution Mistakes
Constantin Patsch, Yuankai Wu, Marsil Zakour et al.
MUSE-VL: Modeling Unified VLM through Semantic Discrete Encoding
Rongchang Xie, Chen Du, Ping Song et al.
Multi-Object Sketch Animation by Scene Decomposition and Motion Planning
Jingyu Liu, Zijie Xin, Yuhan Fu et al.
TOGA: Temporally Grounded Open-Ended Video QA with Weak Supervision
Ayush Gupta, Anirban Roy, Rama Chellappa et al.
Trial-Oriented Visual Rearrangement
Yuyi Liu, Xinhang Song, Tianliang Qi et al.
ReMP-AD: Retrieval-enhanced Multi-modal Prompt Fusion for Few-Shot Industrial Visual Anomaly Detection
Hongchi Ma, Guanglei Yang, Debin Zhao et al.
MagicHOI: Leveraging 3D Priors for Accurate Hand-object Reconstruction from Short Monocular Video Clips
Shibo Wang, Haonan He, Maria Parelli et al.
VisualCloze: A Universal Image Generation Framework via Visual In-Context Learning
Zhong-Yu Li, Ruoyi Du, Juncheng Yan et al.
Backdooring Self-Supervised Contrastive Learning by Noisy Alignment
Tuo Chen, Jie Gui, Minjing Dong et al.
SemiVisBooster: Boosting Semi-Supervised Learning for Fine-Grained Classification through Pseudo-Label Semantic Guidance
Wenjin Zhang, Xinyu Li, Chenyang Gao et al.
Multi-scenario Overlapping Text Segmentation with Depth Awareness
Yang Liu, Xudong Xie, Yuliang Liu et al.
Contrastive Flow Matching
George Stoica, Vivek Ramanujan, Xiang Fan et al.
Generalizable Non-Line-of-Sight Imaging with Learnable Physical Priors
Shida Sun, Yue Li, Yueyi Zhang et al.
Enhancing Prompt Generation with Adaptive Refinement for Camouflaged Object Detection
Xuehan Chen, Guangyu Ren, Tianhong Dai et al.
DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation
Jiazhe Guo, Yikang Ding, Xiwu Chen et al.
Lay-Your-Scene: Natural Scene Layout Generation with Diffusion Transformers
Divyansh Srivastava, Xiang Zhang, He Wen et al.
SCFlow: Implicitly Learning Style and Content Disentanglement with Flow Models
Pingchuan Ma, Xiaopei Yang, Yusong Li et al.
Calibrating MLLM-as-a-judge via Multimodal Bayesian Prompt Ensembles
Eric Slyman, Mehrab Tanjim, Kushal Kafle et al.