Holo-World employs a unified control framework with residual subspaces to generate videos from a single image, enabling precise camera, object, and weather manipulation, trained on HoloStateData.

Xiangchen Yin, Wenzhang Sun, Jiahui Yuan et al.

The study reveals the hidden evolution of visual tokens in LLMs, comparing in-context and layer-wise injection methods.

Wish Suharitdamrong, Tony Alex, Xiatian Zhu et al.

CARE optimizes reasoning length in video-MLLMs via competence-aware reward shaping, enhancing accuracy and efficiency.

Chengwen Liu, Hao Peng, Jisheng Dang et al.

Occ-VLM achieves state-of-the-art multi-view occupancy prediction using a single 2D encoder for indoor scene understanding.

Jianing Li, Zhou Fang, Yijiang Liu et al.

ImageWAM uses image editing to replace video generation, enhancing robot action prediction efficiency and reducing FLOPs to 1/6.

Yuyang Zhang, Wenyao Zhang, Zekun Qi et al.

ScreenAnnotator tool enhances annotation efficiency for vision-language models using unified annotation atoms and Bayesian verifier.

Like Zhang, Runliang Niu, Shiqi Wang et al.

UniTemp enables bidirectional video generation via joint distillation, addressing boundary flickering caused by causal 3D VAE, with strong performance on short and long videos.

Lin Zhang, Sicheng Mo, Zefan Cai et al.

CHIEF is a creator-driven video loop that extends student-made films from 1 to 10 minutes.

Denis Savytski, Aiden Lei, Heding Liu et al.

Introduces CF-GRPO framework to enhance video reasoning performance with Consensus Frame Reward, significantly improving multiple benchmarks.

Chengwen Liu, Zhe Huang, Jisheng Dang et al.

UniAR introduces a unified autoregressive framework with a single discrete visual tokenizer, achieving state-of-the-art results in image generation and understanding.

Wujian Peng, Lingchen Meng, Yuxuan Cai et al.

EventDrive integrates event cameras with vision-language models, significantly improving perception, understanding, prediction, and planning in autonomous driving.

Dongyue Lu, Rong Li, Ao Liang et al.

ActWorld adds action-aware memory to a 100K-video world model, enabling both navigation and mid-rollout object interaction.

Zhexiao Xiong, Yizhi Song, Hao Kang et al.

Pareto LoRA improves multimodal model balance by Pareto-optimal gradient integration, achieving 44.9% better image quality.

Xiwen Wei, Mark Nutter, Madhusudhanan Srinivasan et al.

Proposes Qwen-RobotWorld, a language-conditioned video world model using double-stream MMDiT and 8.6M embodied video-text pairs, achieving top performance on multiple benchmarks.

Jie Zhang, Xiaoyue Chen, Anzhe Chen et al.

MeshLoom is a feed-forward non-rigid mesh registration network that reconstructs vertex deformations across sequences within seconds, outperforming state-of-the-art methods.

Jianqi Chen, Jiraphon Yenphraphai, Xiangjun Tang et al.

Semantic Flip synthesizes out-of-distribution samples to improve embodied refusal, achieving an F1 of 0.9559 on spatial localization.

Dongbin Na, Chanwoo Kim, Giyun Choi et al.

GraphBEV++ integrates LocalAlign-v2 and GlobalAlign-v2 modules, systematically mitigating sensor calibration errors to enhance multi-modal perception robustness.

Ziying Song, Caiyan Jia, Lin Liu et al.

SelectStream enhances streaming video understanding with selective memory, achieving 82.67% on StreamingBench.

Haonan Ge, Yiwei Wang, Hang Wu et al.

GraphWorld leverages latent world models for end-to-end autonomous driving, reducing collision rates by 19.5% on nuScenes 6s horizon.

Ziying Song, Caiyan Jia, Lin Liu et al.

VinQA introduces two visual encoding methods, significantly improving visual citation accuracy in long-form multimodal document QA.

Young Rok Jang, Hyesoo Kong, Kyunghwan An et al.