EGF generates categorical graphs via continuous embeddings, achieving 0.150 FCD on QM9.

Ethan Ma, Zihan Wang, Chris Siu Yeung Chow et al.

FIRE-LIVWO achieves robust LiDAR-Inertial-Visual-Wheel Odometry with mmWave radar enhancement, average localization error of 5.677m.

Kun Hu, Menggang Li, Kaidi Wu et al.

RoboSPA evaluates VLA models with 527K trajectories in complex scenes and long-horizon tasks.

Zhenxuan Fan, Bo Zhang, Yutong Lin et al.

AdaGate-DF achieves efficient deepfake detection in low-resolution settings with AUC of 0.9370 on Celeb-DF.

Vaishnavi Sen, Cody Laurie, Rashida Hasan

Study optimizes information aggregation rates, proposing M²/D error rate, applicable to linear regression and logistic classification.

MohammadHossein Bateni, Zahra Hadizadeh, MohammadTaghi Hajiaghayi et al.

Large language models for HVAC operations in building energy systems; none ready for industry deployment.

Alexander Neubauer, Tianzhen Hong, Han Li et al.

mHC optimizes residual streams via selective routing and near-identity mixing, improving C4 perplexity by 1.9%.

Pengxiang Zhao, Xing Li, Xianzhi Yu et al.

Study finds lineage isolation, not masking, is key for memory retention, improving AUC by 0.010.

Jia Huang, Yangjun Ou

H2INT uses a two-stage Transformer to enhance robot navigation safety and robustness in dense crowds.

Ao Shen, Kaixi Chen, Shiwei Liu et al.

Introduces PPR algorithm for detecting change-points in multi-agent learning using reward signals, balancing detection speed and stability.

Fatemeh Saberi Khomami, Julita Vassileva

LexFlip uses lexical perturbations to detect legal meaning changes; NLI performs best.

Gaurab Baral

Using β-VAE to extract features from ECG for myocardial scar differentiation, achieving ROC of 0.643.

Shayan Sharifi, Riccardo Treu, Ilaria Gandin et al.

Combining VLA model and compliance controller enhances robot-to-human bimanual handover efficiency.

Pasquale Marra, Stefano Berti, Gabriele Mario Caddeo et al.

Introduces DualCWE, a self-supervised framework learning lexical representations from IPA lists, enabling rapid phylogenetic inference for 3,399 languages.

Tim Wientzek

Improves reasoning depth to 72.20% using Gold-Anchored QLoRA and RLVR.

Thi Kim Trang Vo, Nam Tien Le, Thi Kim Nguyet Vo et al.

The paper proposes PAC-Bayesian reconstruction guarantees for time series VAEs, capturing temporal dependencies.

Chloé Hashimoto-Cullen, Ghislain Agoua, Benjamin Guedj et al.

FluxDisco uses Monte Carlo Graph Search for symbolic regression in stoichiometric dynamical systems, ensuring physical adherence.

Cassandra Durr, Alvaro Köhn-Luque, Chris Jewell et al.

FlexPension-LLM predicts pension enrollment among China's flexible workers, achieving 0.9316 F1.

Yumiao Li, Peixin Liu, Donglin Di et al.

Proposed a TTFS-based SNN architecture, scaling to 1.5 billion parameters in LLMs, significantly enhancing energy efficiency.

Zhuoya Zhao, Parsa Omidi, Aref Jafari et al.

Embedding Surgery: Adaptive ranking correction in dense retrieval, achieving 60.64% nDCG@10 improvement.

Maddalena Amendola, Antonio Mallia, Raffaele Perego