RULER-Bench evaluates video-generation rule reasoning; SOTA reaches only 48.87% rule coherence.

Xuming He, Zehao Fan, Hengjia Li et al.

Proposed Temporal Dynamics Enhancer boosts SNNs' temporal modeling, achieving 57.7% and 47.6% mAP50-95.

Fan Luo, Zeyu Gao, Xinhao Luo et al.

SPARK combines VLMs, DiT, and differentiable kinematics for single-image sim-ready reconstruction, reaching 0.3959 Chamfer Distance.

Yumeng He, Ying Jiang, Jiayin Lu et al.

FRAMER utilizes frequency-aligned self-distillation with diffusion priors to enhance image super-resolution, significantly improving PSNR and SSIM.

Seungho Choi, Jeahun Sung, Jihyong Oh

FR-TTS uses filling-based reward to improve NTP image generation, significantly boosting quality.

Hang Xu, Linjiang Huang, Feng Zhao

SpaceMind employs camera-guided modality fusion, achieving SOTA in RGB-based 3D spatial reasoning benchmarks.

Ruosen Zhao, Zhikang Zhang, Jialei Xu et al.

Proposed STVG-o1 framework uses reinforcement fine-tuning with chain-of-thought bounding box reasoning, improving HCSTVG-v1 m tIoU by 7.3%.

Xin Gu, Haoji Zhang, Qihang Fan et al.

∞-RoPE uses block-relative rotation and KV flush to enable infinite-length, controllable video generation.

Hidir Yesiltepe, Tuna Han Salih Meral, Adil Kaan Akan et al.

iMontage adapts pre-trained video models for multi-input/output image generation with enhanced dynamic range.

Zhoujie Fu, Xianfang Zeng, Jinghong Lan et al.

ReaDe employs a 'reason-then-describe' framework with two-stage training, achieving significant improvements in instruction fidelity and controllable video generation.

Shengqiong Wu, Weicai Ye, Yuanxing Zhang et al.

DinoLizer leverages DINOv2 with LoRA fine-tuning to detect VAE and diffusion artifacts, achieving 20% higher IoU on forgery localization.

Minh Thong Doi, Vincent Itier, Jan Butora et al.

Proposes Cross-Modal Verification to build VeriSciQA, a dataset with 20,272 high-quality scientific visual QA pairs.

Yuyi Li, Daoyuan Chen, Zhen Wang et al.

GigaWorld-0 combines large-scale video synthesis and 3D reconstruction as a data engine, significantly enhancing embodied AI generalization.

GigaWorld Team, Angen Ye, Boyuan Wang et al.

Proposes min-Sliced Transport Plans (min-STP) for scalable, transferable optimal transport, achieving near-OT accuracy with reduced computation.

Xinran Liu, Elaheh Akbari, Rocio Diaz Martin et al.

Zhang et al. propose IF-Edit, a tuning-free framework leveraging pretrained video diffusion models for zero-shot image editing, excelling in non-rigid and reasoning tasks.

Zechuan Zhang, Zhenyuan Chen, Zongxin Yang et al.

COVT introduces continuous visual tokens into VLMs, boosting spatial reasoning by up to 16% on benchmarks.

Yiming Qin, Bomin Wei, Jiaxin Ge et al.

LAST integrates visual tools to enhance spatial-temporal reasoning, boosting VLMs' performance on 3D and long video understanding by 15.8% and 8.3% respectively.

Shuai Wang, Daoan Zhang, Tianyi Bai et al.

ViCoDR introduces multi-view consistency regularization, significantly improving 3D coherence in diffusion-based video generation.

Duolikun Danier, Ge Gao, Steven McDonagh et al.

Proposes self-adaptive visual bases using Orthogonal Filtering to reduce visual tokens for efficient representation learning.

Shawn Young, Xingyu Zeng, Lijian Xu

InfiniBench uses LLM-guided, cluster-based layout and task-aware camera planning to generate infinite customizable 3D scenes, enhancing spatial reasoning benchmarks.

Haoming Wang, Qiyao Xue, Wei Gao