SGC metric quantifies 3D geometric consistency in dynamic videos using camera pose divergence, outperforming existing methods.

Weijia Dou, Wenzhao Zheng, Weiliang Chen et al.

MoRI employs reinforcement learning with entropy-aware information gain and semantic contrast to enhance scientific ideation depth and validity.

Chenyang Gu, Jiahao Cheng, Meicong Zhang et al.

Fast interpretable autoregressive estimation using neural network backpropagation, achieving 12.6x speedup.

Anaísa Lucena, Ana Martins, Armando J. Pinho et al.

RADIUS evaluates survey simulation alignment via ranking and distribution metrics with statistical significance, improving robustness over traditional methods.

Weronika Łajewska, Paul Missault, George Davidson et al.

OmniAnomaly and PCA perform comparably on the SMD dataset, especially without point adjustment.

Bruna Alves, Ana Martins, Armando J. Pinho et al.

The paper introduces a maximum-entropy exploration method using future state-action visitation measures, improving feature visitation and convergence speed.

Adrien Bolland, Gaspard Lambrechts, Damien Ernst

GHOST uses Gaussian Splatting for fast hand-object interaction reconstruction from RGB videos, achieving 10x speedup.

Ahmed Tawfik Aboukhadra, Marcel Rogge, Nadia Robertini et al.

Using BERT Score and expert evaluation, this study analyzes ChatGPT-4o, GeminiAI, and Perplexity AI's performance in generating Telugu maternal health responses, with Gemini leading.

Anagani Bhanusree, Sai Divya Vissamsetty, K VenkataKrishna Rao et al.

Motion-o enhances video reasoning by making motion explicit, improving trajectory consistency.

Bishoy Galoaa, Shayda Moezzi, Xiangyu Bai et al.

This study employs multi-modal prompt engineering and multi-agent generate-critique-revise frameworks to analyze and mitigate dialect-induced biases in LLM outputs, demonstrating significant bias reduction.

Martina Ullasci, Marco Rondina, Riccardo Coppola et al.

SCALe method enhances reasoning and answer accuracy in vision-language models through dynamic weight adjustment.

Shaked Perek, Ben Wiesel, Avihu Dekel et al.

Proposed Cross-Modal Context Learning method improves audio-video generation quality with reduced resource requirements.

Bingqi Ma, Linlong Lang, Ming Zhang et al.

Proposes a reference-free simulation framework by training independent user and recommender simulators for more realistic dialogues.

Jerome Ramos, Feng Xia, Xi Wang et al.

Recover sparse neural connectivity from partial measurements using a covariance-based method with Granger-causality refinement.

Quilee Simeon

AS2 achieves end-to-end differentiable reasoning with softened ASP operators, reaching 99.89% accuracy on Visual Sudoku.

Wael AbdAlmageed

Inst4DGS introduces instance-decomposed 4D Gaussian splatting with differentiable Sinkhorn for multi-view consistent tracking, achieving PSNR 28.36 and mIoU 0.9129.

Yonghan Lee, Dinesh Manocha

Understanding DNNs through differential equations to enhance performance and applications.

Hongjue Zhao, Yizhuo Chen, Yuchen Wang et al.

DriveVLM-RL uses dual-path VLM rewards in CARLA, cutting collision severity to 1.75 km/h.

Zilin Huang, Zihao Sheng, Zhengyang Wan et al.

ChoiceEval framework reveals geographic bias in LLM brand and cultural preferences, notably favoring US entities.

Jasmine Rienecker, Katarina Mpofu, Naman Goel et al.

ALIGN uses adversarial learning to enhance cross-session generalization in speech neuroprostheses, significantly reducing phoneme and word error rates.

Zhanqi Zhang, Shun Li, Bernardo L. Sabatini et al.