Docling integrates DocLayNet and TableFormer for fast, resource-efficient multi-format document parsing with high accuracy.

Nikolaos Livathinos, Christoph Auer, Maksym Lysak et al.

BORA combines LLM and Bayesian optimization to enhance high-dimensional experimental design efficiency.

Abdoulatif Cissé, Xenophon Evangelopoulos, Vladimir V. Gusev et al.

Proposes Parametric RAG, embedding external knowledge into model parameters for improved efficiency and performance.

Weihang Su, Yichen Tang, Qingyao Ai et al.

ClearSight utilizes a bioinspired dual-drive hybrid network for event-based motion deblurring, outperforming existing methods.

Xiaopeng Lin, Yulong Huang, Hongwei Ren et al.

This review summarizes self-supervised learning methods for time series anomaly detection, introduces a taxonomy, and discusses future challenges.

Aitor Sánchez-Ferrera, Borja Calvo, Jose A. Lozano

Introduced LoTbench framework to evaluate creativity of multimodal LLMs using Oogiri game, finding the gap with humans is small.

Zhongzhan Huang, Shanshan Zhong, Pan Zhou et al.

HLE introduces a 2,500-question multi-modal academic benchmark, exposing current LLM limitations in complex reasoning and cross-disciplinary understanding.

Long Phan, Alice Gatti, Ziwen Han et al.

This work introduces human-preference-guided reinforcement learning for video generation, leveraging VideoReward to improve flow-based models, achieving significant quality gains.

Jie Liu, Gongye Liu, Jiajun Liang et al.

Analyzed 28 Indian language-supporting LLMs; found significant performance disparities, especially in low-resource languages.

Aatman Vaidya, Tarunima Prabhakar, Denny George et al.

GUI-Bee employs autonomous exploration with Q-ICRL to collect environment-specific data, improving GUI action grounding in novel environments.

Yue Fan, Handong Zhao, Ruiyi Zhang et al.

CuriousBot uses an actionable 3D relational graph for mobile interaction, achieving 82% average task success and outperforming 2D VLM baselines.

Yixuan Wang, Leonor Fermoselle, Tarik Kelestemur et al.

VideoLLaMA3 employs a vision-centric multi-stage training framework, significantly improving image and video understanding performance.

Boqiang Zhang, Kehan Li, Zesen Cheng et al.

Proposed EHPC leverages evaluator heads for prompt compression, reducing input length and inference latency by up to 40%.

Weizhi Fei, Xueyan Niu, Guoqing Xie et al.

VRank leverages self-consistency and chain-of-thought reasoning to improve Verilog code generation accuracy by 10.5% on average, using multiple candidate sampling and clustering.

Zhuorui Zhao, Ruidi Qiu, Ing-Chao Lin et al.

Paradigm-based HDL code generation with LLMs improves correctness by 14.7% on Pass@10, using task decomposition and multi-round validation.

Wenhao Sun, Bing Li, Grace Li Zhang et al.

UniRestore combines diffusion prior with encoder features for unified perceptual and task-oriented image restoration.

I-Hsiang Chen, Wei-Ting Chen, Yu-Wei Liu et al.

Kimi k1.5 scales LLMs with RL, achieving 77.5 on AIME and other top scores.

Kimi Team, Angang Du, Bofei Gao et al.

Using DiverseAR dataset, VLMs like GPT achieve 93% TPR in AR scene recognition.

Lin Duan, Yanming Xiu, Maria Gorlatova

InternLM-XComposer2.5-Reward enhances LVLMs' generation quality with a multi-modal reward model, achieving 70% accuracy.

Yuhang Zang, Xiaoyi Dong, Pan Zhang et al.

Introduced MCNI method for uncertainty quantification in neural networks, outperforming baseline models.

Xueqiong Yuan, Jipeng Li, Ercan Engin Kuruoglu