POTATR is a lightweight 29M-parameter image-to-graph model that significantly improves page-level table extraction accuracy and efficiency.

Brandon Smock, Libin Liang, Max Sokolov et al.

Combining P2 enhancement and quantum-inspired algorithms, the method improves UAV small-object detection AP by 31.10%.

Wuming Lei, Yanbin Gao, Mingyan Sun et al.

Proposes ATM: an action-consistency transfer matrix for diagnosing latent world models, enabling over 100× speedup in evaluation.

Jiaheng Chen

Imagine-OPD enhances efficiency and accuracy in visual reasoning through a self-distillation framework.

Yishuo Cai, Jiahui Liu, Yuanxin Liu et al.

BLUE method enhances efficiency in vision-language-action models for autonomous driving with a lightweight gating mechanism, achieving an 8.9% success rate improvement.

George Ling, Lijin Yang, Hao Yang et al.

Proposes Streaming-Train-248K dataset and Streaming Harness system, enhancing vision-language models for proactive, long-term, real-time streaming understanding.

Dingyu Yao, Shuhuan Gu, Qingyi Si et al.

Test-Time Scaling enhances multimodal foundation models in generation and reasoning, categorized into sampling, feedback, and search strategies.

Cong Wan, Ying He, Zhongzhan Huang et al.

TEVI leverages sparse autoencoders with text conditioning to refine image embeddings, significantly improving vision-language alignment and retrieval accuracy.

Sweta Mahajan, Sukrut Rao, Jiahao Xie et al.

This paper introduces a unified framework based on watching, remembering, and reasoning, significantly advancing long video understanding with multimodal LLMs.

Jiahao Meng, Yue Tan, Qi Xu et al.

AnchorWorld combines 3D human motion and view-based anchors for customizable, self-evolving egocentric scene simulation.

Yu Li, Menghan Xia, Gongye Liu et al.

GuideCAD employs prefix embeddings to efficiently fuse visual-textual data, enabling lightweight 3D CAD model generation with only a quarter of the parameters of fine-tuning methods.

Minseong Kim, Jinyeong Park, Sungho Park et al.

PAR3D introduces part-aware 3D multimodal large language models, significantly enhancing fine-grained scene understanding via the ScenePart dataset.

Shaohui Dai, Yansong Qu, You Shen et al.

Proposes Complexity-Balanced Diffusion Splitting (CBS), using Dirichlet energy and trajectory acceleration to estimate local complexity, improving synthesis quality by ~35%.

Noam Issachar, Dani Lischinski, Raanan Fattal

Proposes Astra framework combining RL-trained VLM policy with Bagel-based world simulator for imagination-driven spatial reasoning, improving MMSI-Bench accuracy from 45.1% to 49.5%.

Chenming Zhu, Jingli Lin, Yilin Long et al.

Proposes MedReCo, an entity-aware vision-language framework with over 690,000 images for clinical case retrieval and change description.

Tengfei Zhang, Ziheng Zhao, Lisong Dai et al.

HomeWorld introduces a hierarchical, multimodal framework trained on 300K real floorplans, using LLMs and diffusion models to generate controllable, diverse, and realistic whole-home scenes.

Wenbo Li, Xiaoliang Ju, Zipeng Qin et al.

Proposes a knowledge refinement framework using automatic rule mining and ASP-based abductive reasoning, improving scene graph generation with +4-8% F1@50 across benchmarks.

Maëlic Neau, Salim Baloch, Jakob Suchan et al.

GMBFormer integrates NDVI-guided global memory with Transformer for urban green-space extraction, achieving a mean IoU of 89.25%.

Hao Lei, Xi Cheng, Chenlu Shu et al.

Proposes PhaseLock, a training-free framework that extracts motion priors from 2-step inference, improving physical consistency by 6.2 points on average.

Woojung Han, Seil Kang, Youngjun Jun et al.

Proposes Style-CCL with multi-stage curriculum learning and SC-DiT for content-preserving style transfer, achieving state-of-the-art in style similarity, content consistency, and aesthetics.

Shiwen Zhang, Haoyuan Wang, Xianghao Zang et al.