REG method entangles high-level class tokens with low-level latents, boosting diffusion training 63× faster with improved quality.

Ge Wu, Shen Zhang, Ruijing Shi et al.

UniGlyph uses pixel-level text masks and adaptive guidance to improve high-fidelity visual text synthesis in Chinese and English, surpassing prior methods by 15%.

Yuanrui Wang, Cong Han, Yafei Li et al.

Proposes a Transformer-based framework for whole-body grasping motion generation, excelling on the GRAB dataset.

Edward Effendy, Kuan-Wei Tseng, Rei Kawakami

World4Drive employs an intention-aware latent world model, reducing L2 error by 18.1%, collision rate by 46.7%, without perception annotations, achieving state-of-the-art results.

Yupeng Zheng, Pengxuan Yang, Zebin Xing et al.

Proposed Inf-Bench framework evaluates spatial deformation reasoning in VLMs, revealing poor 3D task performance.

Jiahuan Zhang, Shunwen Bai, Tianheng Wang et al.

Proposed an efficient depth- and spatially-varying image simulation method, enhancing 12MP real-world deblur performance.

Xinge Yang, Chuong Nguyen, Wenbin Wang et al.

MOVi-MC-AC supplies 5.8M instances across six-camera videos for amodal segmentation, content completion, and cross-view re-identification.

Alexander Moore, Amar Saini, Kylie Cancilla et al.

NavMorph employs a self-evolving world model with continuous latent space and scene memory, boosting VLN-CE performance and online adaptation.

Xuan Yao, Junyu Gao, Changsheng Xu

OmniVCus employs a diffusion Transformer with multimodal control, enabling multi-subject video customization without labels, using LE and TAE mechanisms.

Yuanhao Cai, He Zhang, Xi Chen et al.

VolumetricSMPL achieves 10x faster inference using Neural Blend Weights.

Marko Mihajlovic, Siwei Zhang, Gen Li et al.

DIVE employs iterative reasoning with semantic decomposition, achieving 81.44% accuracy on CVRR-ES, winning the challenge.

Umihiro Kamoto, Tatsuya Ishibashi, Noriyuki Kugo

TR²C combines MCR² and temporal continuity, reaching 97.96% ACC and 98.96% NMI across five HMS benchmarks.

Xianghan Meng, Zhengyu Tong, Zhiyuan Huang et al.

DFVEdit uses Conditional Delta Flow Vectors for zero-shot video editing, achieving 20× speed-up and 85% memory reduction, maintaining state-of-the-art quality.

Lingling Cai, Kang Zhao, Hangjie Yuan et al.

AdaDeDup combines density clustering and model feedback for adaptive data pruning, reducing 20% data with minimal performance loss.

Feiyang Kang, Nadine Chang, Maying Shen et al.

Proposes Surfel-Indexed View Memory (VMem) for long-term scene consistency, reducing computational cost while maintaining scene coherence.

Runjia Li, Philip Torr, Andrea Vedaldi et al.

This study introduces wavelet-based frequency augmentation to improve AI-generated video detection, boosting cross-model accuracy by over 12%.

Riccardo Corvi, Davide Cozzolino, Ekta Prashnani et al.

Proposes OpenBench for evaluating open-vocabulary segmentation, with OVSNet achieving SOTA, outperforming existing methods by ~10%.

Yong Liu, SongLi Wu, Sule Bai et al.

This paper uncovers emergent symbolic mechanisms in VLMs using spatial indexing (position IDs) to solve the binding problem, validated via causal mediation.

Rim Assouel, Declan Campbell, Yoshua Bengio et al.

Show-o2 model enhances multimodal understanding and generation via autoregressive modeling and flow matching.

Jinheng Xie, Zhenheng Yang, Mike Zheng Shou

Proposed a multi-scale Transformer with frequency fusion, achieving PSNR 25.90 on WSRD+ dataset.

Florin-Alexandru Vasluianu, Tim Seizinger, Zhuyun Zhou et al.