Proposes Petri net-based neural circuit model with formal timing guarantees, validated on feedback, lateral inhibition, and hierarchical feature detection microcircuits.

Carlo daCunha, Rodrigo Pena, Marcos Turqueti

Nested SMC enhances discrete diffusion inference control, outperforming traditional methods with significant improvements.

Lohithsai Yadala Chanchu, Hany Abdulsamad, Christian A. Naesseth

SAE-Xplainers combines geographic modulation and rule-based models to enhance interpretability of extreme weather event predictions, improving reconstruction and understanding.

Hugo Porta, Emanuele Dalsasso, Chang Xu et al.

Proposes a cross-lingual fairness evaluation framework for watermarking schemes, revealing structural disparities across 11 languages with specific metrics and experiments.

Alexander Nemecek, Osama Zafar, Debargha Ganguly et al.

Proposes wave-based bilateral teleoperation with direct contact force feedback, using LMI analysis to ensure stability under constant delays in nonlinear multi-DOF robots.

G. Q. Bao Tran, Takanori Miyoshi, Ho Duc Tho

SCoRD employs semantic reasoning-assisted continual distillation to enhance LLM-based retrieval and reranking in dynamic recommendation environments.

Seunghyun Baek, Gyuseok Lee, Seunghan Lee et al.

Proposes a taxonomy of neural models based on state dynamics, credit assignment, and biological grounding, highlighting the disconnection between forward computation and learning mechanisms.

Hadi Al Mubasher, Mariette Awad

PVRA: A pointwise voting framework using 3D keypoints, achieving 89.29% Step [email protected] on assembly pose estimation.

Kulunu Samarawickrama, Roel Pieters

Analyzes the equivalence of union bound in fixed-confidence best-arm identification under two hypothesis orientations, revealing structural insights for error control.

Rianne de Heide

Repo0 uses continuous structural evolution with Dual-DAG to improve code coverage by 20%.

Silin Chen, Haoyi Teng, Xiaodong Gu et al.

Proposes DExtrI for distributional extrapolation of interactions, with theoretical guarantees and superior performance on synthetic and real datasets.

Marin Šola, Xinwei Shen, Peter Bühlmann

Proposes ADAPT, a physics-informed diffusion-based indoor model, achieving 7.3% energy savings and 30.2% occupant comfort improvement.

Xu Yang, Kailai Sun, Dianyu Zhong et al.

Proposes a finite-horizon input–state–output model for AdamW, revealing delayed gradient effects with high accuracy.

Kang Liu, Suyan Li

Training only the projector achieves strong multimodal performance in 3D MLLMs, avoiding language model drift.

Nyx Iskandar, Saathvik Selvan, Slater Victoroff

Proposes CoRRe, a training-free recommendation framework that refines item embeddings post-LLM inference using collaborative signals, achieving state-of-the-art results.

Kyungho Kim, Sunwoo Kim, Geon Lee et al.

This paper reveals fundamental limits of time-uniform self-normalized bounds in discounted least squares, providing counterexamples and correction strategies.

Yi-Shan Wu

TextRefine combines supervised fine-tuning and reward optimization to enhance textual fidelity and placement accuracy in product poster editing.

Honglie Wang, Jia Sun, Zijun Li et al.

ResiGLC achieves semantic communication over packet-loss networks at extreme-low bandwidth, enhancing perceptual fidelity and realism.

Shengshi Yao, Jincheng Dai, Sixian Wang et al.

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.