OmniScientist: An Omni-Modal Omni-Discipline AI Scientist
National University of Singapore; University of Oxford
QuoteBench: How Matched Scores Can Hide Command-Path Failures
Stony Brook University; LMU Munich; Munich Center for Machine Learning
AlayaWorld: Interactive Long-Horizon World Modeling - Full Technical Report (v1.1)
Alaya Lab
MARC v1: An Open-Source Multi-Agent Framework for Clinical AI Reasoning and Coordination
College of Engineering, University of California, Davis; University of Pennsylvania; Drexel University; UC Davis Graduate School of Management
A Unifying Perspective on Causal World Models: From Observations to Representations to Structure
Imperial College London
Academic League of Artificial Intelligence - An Integrative Perspective of Teaching, Research, and Extension
Federal University of Santa Catarina (UFSC)
RAIL: An Automatic Classifier of the Artificial Intelligence Readiness Level
CIETEC-IPN; Instituto Politécnico Nacional; CICATA-QRO; UPIITA
Enhancing Virtual Agents through SLMs and Edge-Computing: An Exploratory Evaluation of Think and Memory Processes
University of Central Lancashire
Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development
Meituan; University of Chinese Academy of Sciences
Who Speaks Matters: Authority-Aware Multi-View RAG over Italian Parliamentary Proceedings
University of Milano-Bicocca
Jointly Predicting Courses and Grades Using a Transformer-Based Model
St. Edward’s University
TopoIntent: Compiling Security Intent into Executable, Compliance-Checked Network Topologies
University of Science and Technology of China; Topsec Technologies Group Inc.
Rules or Character? Scaling Laws for AI Safety Design
AI Medical Engineering Team, RIKEN Center for Advanced Intelligence Project; National Cancer Center Research Institute
LongEarth-R1: Benchmarking and Aligning Vision-Language Models for Long-Horizon Earth Observation Reasoning
Wuhan University; Xi’an University of Electronic Science and Technology
LLM-Guided Graph Generation for Structure-Based Local Improvement Methods
TU Wien
StateBridge: Training-free Hidden-state Alignment for Latent Communication in LLM Multi-Agent Systems
University of Sheffield
NAS-Driven Hardware Accelerator Exploration for Edge AI and Quantization Effects on the Pareto Space
University of Patras
Towards Context-Aware Clinical Motion Understanding in Daily Living at Home: Freezing of Gait Detection with Egocentric Vision
KU Leuven; Medical School Hamburg; Delft University of Technology
Sovereign by necessity? Frontier AI export controls, cyber security, and the limits of national AI capability
University of Surrey
vToken: Token-Level Virtualization for Reclaimable KV Caches
National University of Defense Technology; Peking University
