This paper introduces GenCAD, integrating Transformer, contrastive learning, and diffusion models to generate editable CAD programs from images, outperforming SOTA methods.

Md Ferdous Alam, Faez Ahmed

POINTS improves vision-language models with perplexity-based data filtering and model weight fusion, achieving SOTA performance.

Yuan Liu, Zhongyin Zhao, Ziyuan Zhuang et al.

VILA-U employs a unified autoregressive framework integrating visual and language understanding and generation, achieving near state-of-the-art results.

Yecheng Wu, Zhuoyang Zhang, Junyu Chen et al.

Introduced MSQA, a large-scale multi-modal dataset with 251K QA pairs, leveraging 3D scene graphs and interleaved inputs for improved scene reasoning.

Xiongkun Linghu, Jiangyong Huang, Xuesong Niu et al.

ViewCrafter combines point cloud and video diffusion models for high-fidelity novel view synthesis from sparse images.

Wangbo Yu, Jinbo Xing, Li Yuan et al.

DC² framework enhances MLLM perception of 4K&8K images, improving accuracy by 6%.

Wenbin Wang, Liang Ding, Minyan Zeng et al.

Show-o is a unified transformer integrating autoregressive and discrete diffusion models, supporting multimodal understanding and generation with 1.3B parameters, achieving state-of-the-art performance.

Jinheng Xie, Weijia Mao, Zechen Bai et al.

Introduces GRAB, a synthetic graph analysis benchmark with 3284 questions, evaluating 20 LMMs; top score 21%, highlighting current limitations.

Jonathan Roberts, Kai Han, Samuel Albanie

TrackGo employs free masks and arrows for precise, efficient controllable video generation, integrating TrackAdapter into temporal self-attention layers for enhanced control.

Haitao Zhou, Chuang Wang, Rui Nie et al.

Train matting models without alpha labels using DDC loss, achieving excellent results on AM-2K and P3M-10K datasets.

Wenze Liu, Zixuan Ye, Hao Lu et al.

EEPPR uses 3D correlation on event streams to estimate periodic phenomena frequency with 0.1% error, outperforming existing methods.

Jakub Kolář, Radim Špetlík, Jiří Matas

DC3DO combines LION and diffusion models for zero-shot 3D shape classification, achieving 12.5% improvement over multi-view methods.

Nursena Koprucu, Meher Shashwat Nigam, Shicheng Xu et al.

Lumina-mGPT is a decoder-only multimodal autoregressive model achieving high-quality, flexible photorealistic image generation via multimodal pretraining and progressive fine-tuning.

Dongyang Liu, Shitian Zhao, Le Zhuo et al.

Unified framework categorizes data assessment into quality, diversity, importance; improves instruction tuning efficiency and performance.

Yulei Qin, Yuncheng Yang, Pengcheng Guo et al.

MiniCPM-V employs architecture optimization to enable GPT-4V-level performance on mobile devices, supports 30+ languages, and surpasses prior models in accuracy.

Yuan Yao, Tianyu Yu, Ao Zhang et al.

Lightweight coarse correspondence method boosts spatial-temporal reasoning in multimodal LLMs by 20%, no architecture change needed.

Benlin Liu, Yuhao Dong, Yiqin Wang et al.

SAM 2 employs streaming memory within a transformer framework for promptable image and video segmentation, achieving 3x fewer interactions and 6x faster speeds than prior models.

Nikhila Ravi, Valentin Gabeur, Yuan-Ting Hu et al.

Proposes MotionFix dataset and TMED diffusion model for text-driven 3D human motion editing, achieving significant improvements in editing accuracy.

Nikos Athanasiou, Alpár Cseke, Markos Diomataris et al.

RFNet+RFFT lift ad-image availability with RF1M, a 1M+ human-labeled dataset

Zhenbang Du, Wei Feng, Haohan Wang et al.

C3T method improves accuracy by at least 8% in unsupervised modality adaptation.

Abhi Kamboj, Anh Duy Nguyen, Minh N. Do