Evidential NeRF introduces a probabilistic framework for joint aleatoric and epistemic uncertainty estimation from a single forward pass, enhancing scene reconstruction fidelity and reliability.

Ruxiao Duan, Alex Wong

Proposes RaWMPC, a risk-aware predictive control framework that learns safety without expert supervision, improving autonomous driving generalization.

Jiangxin Sun, Feng Xue, Teng Long et al.

ToProVAR achieves 3.4x acceleration via tri-dimensional entropy-aware semantic analysis and sparsity optimization.

Jiayu Chen, Ruoyu Lin, Zihao Zheng et al.

LegoOcc uses 3D language-embedded Gaussians for monocular open-vocabulary indoor occupancy, achieving 59.50 IoU and 21.05 mIoU, surpassing previous methods.

Changqing Zhou, Yueru Luo, Han Zhang et al.

PhysicEdit models physical state transitions with 38K video trajectories, improving realism by 5.9%.

Liangbing Zhao, Le Zhuo, Sayak Paul et al.

LongVideo-R1 employs hierarchical reasoning and goal-directed navigation, reducing computational costs while maintaining high QA accuracy on long videos.

Jihao Qiu, Lingxi Xie, Xinyue Huo et al.

SimLBR employs Latent Blending Regularization to define tight decision boundaries around real images, achieving up to +24.85% accuracy and +69.62% recall, with superior cross-generator generalization.

Aayush Dhakal, Subash Khanal, Srikumar Sastry et al.

MeanFuser uses Gaussian Mixture Noise and MeanFlow for one-step multi-modal trajectory generation, boosting efficiency and robustness in autonomous driving.

Junli Wang, Yinan Zheng, Xueyi Liu et al.

JavisDiT++ achieves high-quality audio-video generation using MS-MoE and TA-RoPE, surpassing existing methods.

Kai Liu, Yanhao Zheng, Kai Wang et al.

SymPL framework significantly enhances spatial reasoning in vision-language models, especially for allocentric perspectives.

Jaeyun Jang, Seunghui Shin, Taeho Park et al.

UniMatch achieves cross-category 3D shape matching via coarse-to-fine language guidance, significantly improving matching accuracy.

Qinfeng Xiao, Guofeng Mei, Bo Yang et al.

SafeDrive integrates sparse world modeling with fine-grained safety reasoning, achieving a PDMS of 91.6% and collision rate of 0.5% in autonomous driving.

Jungho Kim, Jiyong Oh, Seunghoon Yu et al.

VETime achieves zero-shot time series anomaly detection through visual-temporal alignment and dynamic fusion, significantly improving localization precision.

Yingyuan Yang, Tian Lan, Yifei Gao et al.

Proposes Self-Supervised Semantic Bridge (SSB), integrating external semantic priors into diffusion models for spatially faithful unpaired image translation, outperforming prior methods.

Jiaming Liu, Felix Petersen, Yunhe Gao et al.

The study reveals limitations in VLMs' spatial reasoning for non-textual elements, with text-recognition pathways outperforming visual pathways.

Yuval Levental

Study reveals visual preferences of vision-language models using visual prompt optimization; experiments show significant shifts in choice probabilities.

Manuel Cherep, Pranav M R, Pattie Maes et al.

EditCtrl achieves real-time video editing with local/global control modules, improving efficiency by 10x.

Yehonathan Litman, Shikun Liu, Dario Seyb et al.

AnchorWeave significantly improves long-term video generation consistency using retrieved local spatial memories.

Zun Wang, Han Lin, Jaehong Yoon et al.

DriveFine integrates masked diffusion with self-correction, achieving robust and precise autonomous driving decisions, with PDMS reaching 91.8 and EPDMS 89.7 on benchmarks.

Chenxu Dang, Sining Ang, Yongkang Li et al.

Proposes multi-scale dynamics and Gaussian sequences for monocular 4D scene reconstruction, achieving state-of-the-art results with 17.07 dB PSNR.

Can Li, Jie Gu, Jingmin Chen et al.