Using a two-dimensional graded response model on survey data (N=2499), the study quantifies user receptivity to conversational AI in online dating, revealing high correlation between deployment and encounter roles.

Daria Leshchikova, Valentina V. Kuskova, Dmitry Zaytsev et al.

MeanFlow-Transfer and CAMF achieve fast domain adaptation with limited data, improving FID by 29%.

Yara Bahram, Zahra Dehghani, Mélodie Desbos et al.

Proposes telemetry-guided adaptive compression for edge RAG, reducing GPU energy by up to 53.2% and SoC energy by 48.2%, with negligible quality loss.

Zlatan Feric, Amir Taherin, Yanzhi Wang et al.

Using Falcon-7B-Instruct with FAISS-based RAG, achieving ROUGE-1 scores over 0.33 and outperforming Lead-3 in financial news summarization.

Pranav Chandaliya

Introduces a formal semantic-block model and execution-judged benchmark to enhance specification quality assessment independence.

Oleg Grynets, Dmytro Kostetskyi, Vasyl Lyashkevych

HiRA-CAM enhances CNN explanations by hierarchical region agreement, outperforming LayerCAM and Grad-CAM with more stable, fine-grained saliency maps.

Manasi Nerurkar, Ali A. Minai

Proposes fairness-aware network embeddings, categorized into spectral, random walk, GNNs, addressing societal biases.

Ella Has, Harshith Kumar Yadav, Gaurav Dixit et al.

SPADE employs self-play with a single LLM generating and optimizing executable environments, achieving an average 5.3% improvement across benchmarks.

Bo Liu, Simon Yu, Yiding Jiang et al.

PartialBiGrasp leverages convolutional occupancy networks to infer hidden local geometry from partial point clouds, enabling stable dual-arm grasping with 55.16% force-closure rate and 67.87% success on DG16M.

Ayush Kaura, Vignesh Vembar, Md Faizal Karim et al.

GC-OPD introduces group-normalized verifier rewards and relative advantage credit assignment, boosting long-context reasoning scores from 29.08 to 40.47 on five benchmarks.

Zhu Zhang, Jixun Wang, Xiaoang Xu et al.

Outcome Monitors increase ToolMaze completion rate to 28.1%, significantly improving tool failure recovery.

Sugam Panthi, Rabab Abdelfattah

MDTIM model discretizes time series for imputation, achieving 30% accuracy improvement.

Dongbin Kim, Seungyun Lee, Geonwoo Shin et al.

JANUS is a multi-modal neural sampler that efficiently reproduces equilibrium states in disordered materials with minimal energy evaluations.

Denis Blessing, Mouyang Cheng, Maximilian Schebek et al.

Proposes DistScan, detecting backdoors via pre-NMS class distribution shift, achieving 97.22% accuracy.

Longtian Wang, Zhengyu Zhao, Chenhao Lin et al.

DA-WAM introduces decision-aligned future latent representations for autonomous driving, achieving state-of-the-art performance with 93.7 PDMS on NAVSIM-v1, by coupling action-conditioned future prediction with trajectory scoring.

Ruiguo Zhong, Benshan Ma, Xiaolong Chen et al.

Empirical analysis of 1,338 LLM post-training trajectories reveals strategies are locked in early, lacking in-execution self-reassessment mechanisms, limiting AI self-improvement.

Joy Jia Yin Lim, Xin Huang, Hao Peng et al.

SiConMo reaches 34.8 mIoU on ADE20K at 0.6 GFLOPs by concentrating local–global context modeling in the bottleneck.

Mian Muhammad Naeem Abid, Nancy Mehta, Zongwei Wu et al.

Introduces Penrose tensor notation mapped to PyTorch einsum, enhancing interpretability and reproducibility of neural architectures.

Pietro Barbiero

Verifiable abstention makes AI leak diagnosis accountable, with 214 correct actions out of 550 events.

Tianwei Mu, Yue Wang, Mingzhe Yuan et al.

Introducing data co-observation as a third key factor in continual learning, quantifying its impact on model generalization beyond forgetting.

Timm Hess, Abhishek Jha, Gido M. van de Ven et al.