Showing 21–40 of 2,250 results
/ Date/ Name
Apr 24, 2026Superminds Test: Actively Evaluating Collective Intelligence of Agent Society via Probing AgentsApr 24, 2026From Skills to Talent: Organising Heterogeneous Agents as a Real-World CompanyApr 24, 2026SSG: Logit-Balanced Vocabulary Partitioning for LLM WatermarkingApr 24, 2026AgentSearchBench: A Benchmark for AI Agent Search in the WildApr 24, 2026CognitiveTwin: Robust Multi-Modal Digital Twins for Predicting Cognitive Decline in Alzheimer's DiseaseApr 24, 2026How Hard is it to Decide if a Fact is Relevant to a Query?Apr 24, 2026From Local to Cluster: A Unified Framework for Causal Discovery with Latent VariablesApr 24, 2026Distance-Misaligned Training in Graph Transformers and Adaptive Graph-Aware ControlApr 24, 2026Introducing Background Temperature to Characterise Hidden Randomness in Large Language ModelsApr 24, 2026Hidden Failure Modes of Gradient Modification under Adam in Continual Learning, and Adaptive Decoupled Moment Routing as a RepairApr 24, 2026CNSL-bench: Benchmarking the Sign Language Understanding Capabilities of MLLMs on Chinese National Sign LanguageApr 24, 2026LeHome: A Simulation Environment for Deformable Object Manipulation in Household ScenariosApr 24, 2026ChangeQuery: Advancing Remote Sensing Change Analysis for Natural and Human-Induced Disasters from Visual Detection to Semantic UnderstandingApr 24, 2026FETS Benchmark: Foundation Models Outperform Dataset-specific Machine Learning in Energy Time Series ForecastingApr 24, 2026BLAST: Benchmarking LLMs with ASP-based Structured TestingApr 24, 2026Contexts are Never Long Enough: Structured Reasoning for Scalable Question Answering over Long Document SetsApr 24, 2026ReLeVAnT: Relevance Lexical Vectors for Accurate Legal Text ClassificationApr 24, 2026When Does LLM Self-Correction Help? A Control-Theoretic Markov Diagnostic and Verify-First InterventionApr 24, 2026Semantic Error Correction and Decoding for Short Block Channel CodesApr 24, 2026Towards Safe Mobility: A Unified Transportation Foundation Model enabled by Open-Ended Vision-Language Dataset