CoxKAN integrates Kolmogorov-Arnold networks with symbolic regression for interpretable, high-performance survival analysis, validated on multiple datasets.

William Knottenbelt, William McGough, Rebecca Wray et al.

This study evaluates LLMs' ability to generate novel research ideas, finding they outperform experts in novelty (p<0.05) but are slightly weaker in feasibility.

Chenglei Si, Diyi Yang, Tatsunori Hashimoto

Proposes a unified framework combining tensor decomposition and automatic rank search, achieving high compression of pre-trained neural networks.

Ali Aghababaei-Harandi, Massih-Reza Amini

Visual prompting in MLLMs enhances visual understanding and reasoning capabilities.

Junda Wu, Zhehao Zhang, Yu Xia et al.

xLAM models outperform GPT-4 on the Berkeley Function-Calling Leaderboard, enhancing AI agent task performance.

Jianguo Zhang, Tian Lan, Ming Zhu et al.

RoboTwin leverages generative digital twins and large language models to enhance dual-arm robot training data diversity and evaluation.

Yao Mu, Tianxing Chen, Shijia Peng et al.

Reveals MDMs are essentially time-agnostic masked models, introduces efficient first-hitting sampling, questions their superiority.

Kaiwen Zheng, Yongxin Chen, Hanzi Mao et al.

Introduces MMMU-Pro, a more rigorous benchmark with filtering, option augmentation, and vision-only input, causing performance drops of 16.8%-26.9%, enhancing evaluation robustness.

Xiang Yue, Tianyu Zheng, Yuansheng Ni et al.

Sorbet combines PTsoftmax and BSPN to enable energy-efficient transformer-based SNN language models suitable for neuromorphic hardware, achieving 27× energy savings.

Kaiwen Tang, Zhanglu Yan, Weng-Fai Wong

Comparative analysis of gradient-based optimization methods (e.g., Newton, BFGS) via 3D surface visualization and initial point sensitivity, highlighting efficiency and robustness.

Saeed Asadi, Sonia Gharibzadeh, Hajar Kazemi Naeini 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.

OLMoE uses sparse Mixture-of-Experts, activating only 1B of 7B parameters, outperforming larger models.

Niklas Muennighoff, Luca Soldaini, Dirk Groeneveld 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.

Combines parameter-efficient prompt tuning with flow matching for multi-task robot manipulation, improving stability and inference speed.

Fan Zhang, Michael Gienger

Proposed algorithm identifies and analyzes attractor basins in concurrent systems using safe Petri nets framework.

Giann Karlo Aguirre Samboni, Stefan Haar, Loic Paulevé et al.

ToolACE employs self-evolution synthesis of 26,507 APIs, enabling high-performance function calling with only 8B parameters, rivaling GPT-4.

Weiwen Liu, Xu Huang, Xingshan Zeng et al.

MMT-BERT combines Multitrack Music Transformer and MusicBERT for chord-aware symbolic music generation, achieving 99.73% PCES.

Jinlong Zhu, Keigo Sakurai, Ren Togo et al.

Proposes a Nash welfare-based fair reciprocal recommendation algorithm balancing total matches and opportunity envy-freeness.

Yoji Tomita, Tomohiki Yokoyama

TinyAgent fine-tunes small open-source LLMs with high-quality datasets, surpassing GPT-4-Turbo in function calling, deploying efficiently on edge devices with tool retrieval and quantization.

Lutfi Eren Erdogan, Nicholas Lee, Siddharth Jha et al.

PALO leverages vision-language models for task decomposition, enabling few-shot adaptation of robot policies with only five demonstrations, outperforming traditional fine-tuning.

Vivek Myers, Bill Chunyuan Zheng, Oier Mees et al.