Proposes CP-GS framework combining pre-trained image-to-3D models and LoRA fine-tuning to achieve multi-view consistent 3D scene personalization from a single image, outperforming SOTA.

Yuxuan Wang, Xuanyu Yi, Qingshan Xu et al.

LLINBO combines LLMs and GPs to enhance reliability in Bayesian optimization, especially for 3D printing.

Chih-Yu Chang, Milad Azvar, Chinedum Okwudire et al.

Sparc3D combines sparse deformable Marching Cubes and a novel sparse convolutional VAE for high-res 3D shape reconstruction.

Zhihao Li, Yufei Wang, Heliang Zheng et al.

Proposed an adaptive estimator for transition density in controlled Markov chains without relying on smoothness parameters.

Imon Banerjee, Vinayak Rao, Harsha Honnappa

UniVG-R1 employs reasoning and reinforcement learning, achieving 9.1% performance gain on universal visual grounding tasks.

Sule Bai, Mingxing Li, Yong Liu et al.

ADASAP combines randomized Nyström approximation and sketch-and-project for scalable large-scale GP inference, outperforming state-of-the-art methods.

Pratik Rathore, Zachary Frangella, Sachin Garg et al.

MeanFlow introduces average velocity for one-step generation, achieving FID 3.43, outperforming prior methods.

Zhengyang Geng, Mingyang Deng, Xingjian Bai et al.

Proposes Pensieve's two-stage training for high-quality novel view synthesis without calibration, achieving PSNR 26.53 on RealEstate10K.

Ruoyu Wang, Yi Ma, Shenghua Gao

MM-PRM uses MCTS to create 700k+ step labels, raising multimodal math accuracy by up to 12.06 points.

Lingxiao Du, Fanqing Meng, Zongkai Liu et al.

Introduces SAKURA benchmark to evaluate large audio-language models' multi-hop reasoning; finds models struggle with audio information integration, highlighting a key bottleneck.

Chih-Kai Yang, Neo Ho, Yen-Ting Piao et al.

CoSeP uses class-separability space clustering to automatically determine layer-wise pruning ratios, improving efficiency without sacrificing accuracy.

David Levin, Gonen Singer

PI-VAD enhances RGB features with multi-modal inputs, achieving state-of-the-art accuracy in video anomaly detection across three datasets.

Snehashis Majhi, Giacomo D'Amicantonio, Antitza Dantcheva et al.

Fractured Sampling method reduces token usage while improving Pass@k accuracy.

Baohao Liao, Hanze Dong, Yuhui Xu et al.

Text2midi-InferAlign enhances symbolic music generation by inference-time alignment, significantly improving text-audio consistency.

Abhinaba Roy, Geeta Puri, Dorien Herremans

BusterX leverages MLLM and reinforcement learning to detect AI-generated videos, utilizing a 200K high-quality dataset and producing interpretable reasoning chains, significantly improving accuracy and explainability.

Haiquan Wen, Yiwei He, Zhenglin Huang et al.

Proposes Self-Evolutionary Reinforcement Learning for GUI grounding, achieving 47.3% accuracy with only 3K samples on a 7B model.

Xinbin Yuan, Jian Zhang, Kaixin Li et al.

Robust planning for autonomous driving via mixed adversarial diffusion predictions, enhancing safety.

Albert Zhao, Stefano Soatto

Semi-supervised model alignment using conditional flow matching with inter-modal bridge cost achieves effective cross-modal distribution mapping with limited paired data.

Ali Gholamzadeh, Noor Sajid

LogicOCR evaluates large multimodal models' logical reasoning on text-rich images using automated image generation and cropping, achieving 73% success rate.

Maoyuan Ye, Haibin He, Qihuang Zhong et al.

Proposed MobileIPL with iterative preference learning significantly improves mobile GUI reasoning, outperforming SOTA models by over 10% on key benchmarks.

Kun Huang, Weikai Xu, Yuxuan Liu et al.