Doubling the embedding dimension proves the complete-graph s-stress landscape is benign, confirming the conjecture that k≥2(ℓ+1).

Christopher Criscitiello

Neurosymbolic embodied agent combines visual exploration and symbolic planning, achieving over 90% success in household tasks.

Mohammad Albinhassan, Yuming Feng, Alessandra Russo et al.

PixRestore is a VAE-free pixel-space diffusion transformer with 50M parameters, enabling single-step high-fidelity image restoration.

Lingchen Sun, Rongyuan Wu, Xiangtao Kong et al.

GenRouter optimizes image generation workflows, reducing computational costs by 95%.

Harold Haodong Chen, Zhiyu Hou, Wen-Jie Shu et al.

Proposes a control function-based unbiased ranking framework, correcting position bias and improving ranking accuracy.

Md Aminul Islam

Prototypical Network-based ID PAD achieves ~9% EER with only 4 samples, enabling cross-country domain generalization.

Mario Nieto-Hidalgo, Juan M. Espin, Juan E. Tapia

Ultra framework achieves 73.0% mIoU on ACDC using CTDN and CMIL for unsupervised cross-task optimization under adverse weather.

Shiqin Wang, Zhiqian Li, Haoyuan Du et al.

Proposes density-reweighted entropic OT to decouple geometry from sampling density, improving alignment fidelity on low-dimensional manifolds with density disparities.

Keyi Li, Yuval Kluger, Boris Landa

Proposes PP-RFANNS combining N-ary trees and HNSW for privacy-preserving range filtered ANN over encrypted vectors, achieving high efficiency on large datasets.

Haoyu Wang, Yandi Zhang, Jiadong Xie et al.

This paper introduces TTP-D, combining MILP, metaheuristics, and DRL to optimize truck-drone collection, boosting profit and efficiency.

Kabir Murjani, Abhay Sobhanan

D2-ScaleAgent employs dual-dimensional scaling with Verifier-driven routing, achieving logical closure over evidence chains, outperforming traditional methods.

Hao Zhang, Longrong Yang, Lunhao Duan et al.

LLM-MGCL enhances POI recommendation with multi-graph contrastive learning, achieving a 52% Recall@20 improvement.

Burak Tamer, Wolfram Höpken, Zehui Wang

Using class-conditional GAN and DDPM to augment satellite images, boosting classification accuracy to 88%.

Marta Sumyk, Oleksandr Kosovan, Iryna Voitsitska

LACE leverages cheap auxiliary signals within a local control variate framework to efficiently estimate conditional language model performance with limited gold labels.

Zhi Zhang, Lingfeng Lyu, Yue Kang et al.

This study evaluates how identity-conditioned prompts affect LLM-generated surveillance robot descriptions using six readability metrics, revealing systematic variations.

Nneka Hyman, Jasmine Khan, Raj Korpan

KV-Cache mismatch during model rollback causes state residuals, enabling information leakage via a causal cache effect.

Guijia Zhang, Harry Yang

Proposes the Global Mediation Workspace (GMW) control model using boundary reachability and observability, validated on macaque ECoG data to quantify neural mediation capacity.

Ryota Kanai

RAPAC-DP introduces response-aligned pending-action compensation, retaining 81.4% performance at maximum delay, improving robustness of diffusion policies under communication latency.

Tao Wang, Wei Wang, Jianhui Wang et al.

Layer-adaptive regularization based on Hessian top eigenvalues improves continual learning by reducing forgetting.

Brian B. Moser, Ahmed Anwar, Tobias Christian Nauen et al.

MicroVerse employs long-horizon multi-agent simulations with a 'soul file' and multi-layer memory to quantify identity drift, validated through threshold robustness tests.

Sky Ng, Brihi Joshi, Ishan Gupta et al.