PaliGemma 2 integrates SigLIP-So400m and Gemma 2, employing a three-stage training process across multiple scales, achieving state-of-the-art transfer performance on diverse tasks.

Andreas Steiner, André Susano Pinto, Michael Tschannen et al.

Proposes BTimer, a real-time monocular dynamic scene reconstruction model using bullet-time representation, achieving 150ms high-quality scene synthesis.

Hanxue Liang, Jiawei Ren, Ashkan Mirzaei et al.

HunyuanVideo is an open-source large-scale video generation model with over 1.3 billion parameters, matching or surpassing top industry closed-source models.

Weijie Kong, Qi Tian, Zijian Zhang et al.

Dual-exposure stereo extends dynamic range for improved 3D depth estimation accuracy.

Juhyung Choi, Jinnyeong Kim, Seokjun Choi et al.

SceneFactor employs factored latent diffusion models for controllable large-scale 3D scene generation and editing, enabling intuitive object manipulation with minimal clicks.

Alexey Bokhovkin, Quan Meng, Shubham Tulsiani et al.

LamRA leverages large multimodal models with two-stage training and lightweight LoRA modules to unify multi-task retrieval and reranking, achieving strong zero-shot performance.

Yikun Liu, Pingan Chen, Jiayin Cai et al.

Proposes Structured LATent (SLAT) for scalable 3D generation, integrating sparse grids with multiview features, enabling multi-format outputs with up to 2 billion parameters.

Jianfeng Xiang, Zelong Lv, Sicheng Xu et al.

DynSUP uses two unposed images to achieve dynamic Gaussian splatting, significantly enhancing dynamic scene synthesis.

Weihang Li, Weirong Chen, Shenhan Qian et al.

Proposes Video-3D LLM, integrating 3D position encoding into video representations, achieving SOTA on 5 3D scene benchmarks with 58.1% [email protected] on ScanRefer.

Duo Zheng, Shijia Huang, Liwei Wang

AMO sampler enhances text rendering in diffusion models by adaptive overshooting, improving accuracy by 35.9% without extra training.

Xixi Hu, Keyang Xu, Bo Liu et al.

Trajectory attention explicitly models pixel trajectories, boosting fine-grained camera motion control with improved long-range consistency.

Zeqi Xiao, Wenqi Ouyang, Yifan Zhou et al.

FonTS employs a two-stage DiT pipeline with parameter-efficient fine-tuning and style adapters to achieve precise word-level typography and style control, significantly improving text rendering quality.

Wenda Shi, Yiren Song, Dengming Zhang et al.

AC3D leverages spectral analysis and model optimization to enable precise 3D camera control in video diffusion transformers, improving visual quality by 10% and training speed by 15%.

Sherwin Bahmani, Ivan Skorokhodov, Guocheng Qian et al.

Introduces VDMini, accelerating video diffusion models by pruning and consistency loss, achieving 2.5x speedup.

Yiming Wu, Zhenghao Chen, Huan Wang et al.

ChatRex enhances multimodal LLM perception with decoupled design, achieving 72.8% recall on COCO dataset.

Qing Jiang, Gen Luo, Yuqin Yang et al.

Type-R employs post-processing to automatically correct typos in text-to-image outputs, significantly improving text accuracy without degrading image quality.

Wataru Shimoda, Naoto Inoue, Daichi Haraguchi et al.

CHOICE benchmark systematically evaluates 23 remote sensing tasks for large vision-language models, revealing strengths and gaps in perception and reasoning, with 10,507 problems across 50 cities.

Xiao An, Jiaxing Sun, Zihan Gui et al.

This study conducts a hierarchical attention analysis in VLMs, revealing how middle layers facilitate cross-modal information flow and global feature storage.

Omri Kaduri, Shai Bagon, Tali Dekel

ConsisID introduces a tuning-free, frequency-based control scheme for identity-preserving text-to-video generation using DiT, achieving high fidelity without fine-tuning.

Shenghai Yuan, Jinfa Huang, Xianyi He et al.

PreF3R is a pose-free, feed-forward 3D Gaussian reconstruction method achieving 20FPS for real-time novel-view synthesis.

Zequn Chen, Jiezhi Yang, Heng Yang