IGOFormer adds geometry-aware decoding and momentum matching, reaching 78.00 AP50 on DOTA-V1.0 with Swin-T.

Junpeng Zhang, Zewei Yang, Jie Feng et al.

CoPE-VideoLM leverages codec primitives (motion vectors, residuals) to reduce token usage by 93% and TTFT by 86%, enabling efficient long-term video understanding.

Sayan Deb Sarkar, Rémi Pautrat, Ondrej Miksik et al.

FireRed-Image-Edit employs a diffusion transformer with 1.6B samples, achieving state-of-the-art instruction-based image editing.

Super Intelligence Team, Changhao Qiao, Chao Hui et al.

DreamID-Omni framework achieves controllable human-centric audio-video generation, surpassing existing commercial models.

Xu Guo, Fulong Ye, Qichao Sun et al.

FAIL employs adversarial imitation learning with pathwise and policy gradient algorithms, improving image generation with only 13,000 samples, surpassing traditional preference methods.

Yeyao Ma, Chen Li, Xiaosong Zhang et al.

AssetFormer uses autoregressive Transformer to generate modular 3D assets, enhancing UGC content creation quality.

Lingting Zhu, Shengju Qian, Haidi Fan et al.

Integrating lightweight learned depth priors into VINS-Mono reduces ATE by up to 28.3%, improving robustness in low-texture environments.

Arda Alniak, Sinan Kalkan, Mustafa Mert Ankarali et al.

C2RoPE introduces spatio-temporal continuous positional encoding and Chebyshev causal masking, improving 3D multimodal reasoning by addressing RoPE limitations.

Guanting Ye, Qiyan Zhao, Wenhao Yu et al.

Proposes Separable Causal Diffusion (SCD) architecture, revealing early layers' feature redundancy and deep layers' local focus, boosting video generation efficiency.

Xingjian Bai, Guande He, Zhengqi Li et al.

Proposes two training-free trajectory smoothing methods (Look-Ahead and Look-Back) to improve image generation stability and quality in flow-based models.

Yan Luo, Henry Huang, Todd Y. Zhou et al.

UI-Venus-1.5 achieves 77.6% success rate in AndroidWorld navigation via model merging and online reinforcement learning.

Venus Team, Changlong Gao, Zhangxuan Gu et al.

MotionCrafter employs a 4D VAE to jointly reconstruct dense geometry and scene flow from monocular videos, achieving 38.64% geometry and 25% motion improvements.

Ruijie Zhu, Jiahao Lu, Wenbo Hu et al.

VideoVeritas combines perception pretraining and fact-based reasoning, using the MintVid dataset to detect deepfake videos with 85.7% accuracy.

Hao Tan, Jun Lan, Senyuan Shi et al.

Instance-disentangled attention improves multi-region editing in flow matching models, reducing attribute leakage and enhancing local control.

Carmine Zaccagnino, Fabio Quattrini, Enis Simsar et al.

Inspiration Seeds leverages CLIP sparse autoencoders for unsupervised visual feature decomposition, enabling diverse non-literal image combinations without text prompts.

Kfir Goldberg, Elad Richardson, Yael Vinker

E-VAds-R1 achieves 109.2% improvement in commercial intent reasoning using MG-GRPO reward design.

Xianjie Liu, Yiman Hu, Liang Wu et al.

ViCA employs vision-only cross-attention, reducing visual computation to 4% while maintaining 98% accuracy, greatly improving efficiency.

Wenjie Liu, Hao Wu, Xin Qiu et al.

ZoomDet introduces offset prediction and corner-aligned box transformation for UAV small-object detection, achieving 8.4% mAP gain with minimal latency.

Tao Wang, Chenyu Lin, Chenwei Tang et al.

Introduced an Integer Linear Programming approach for geometrically consistent partial-partial shape matching, significantly improving matching accuracy.

Viktoria Ehm, Paul Roetzer, Florian Bernard et al.

DriveWorld-VLA unifies vision-language-action with world models in latent space, achieving 91.3 PDMS on NAVSIMv1 and 0.16 collision rate on nuScenes.

Feiyang jia, Lin Liu, Ziying Song et al.