AION: Next-Generation Tasks and Practical Harness for Time Series
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Towards Multi-Turn Dialog Systems for Industrial Asset Operations and Maintenance
Trust-Aware Joint Feature-Prediction Discrepancy for Robust Domain Adaptation
Courant: a State-Adaptive Perceiver-Based Neural Surrogate with Local Support and Interpr…
Leveraging Gauge Freedom for Learning Non-Gradient Population Dynamics of Stochastic Syst…
Intent Signal Theory: A Computational Framework for Intent-State Control in Human-AI Inte…
Extracting Training Data from Diffusion Language Models via Infilling
TaBIIC2: Interactive Building of Ontological Taxonomies using Weighted Self-Organizing Ma…
Agent Manufacturing: Foundation-Model Agents as First-Class Industrial Entities
GRAIL: AI translation for scientists application workflow on satellite data
Fundamental Limitation in Explaining AI
When Mean CE Fails: Median CE Can Better Track Language Model Quality
LAPLEX: The FFT of Learnable Laplace Kernels
Agent-Facing Information Design in LLM Tool Registries
Document Classification Pattern Recognition via Information Fusion: A Systematic Review o…
LETS Forecast: Learning Embedology for Time Series Forecasting
From Model Scaling to System Scaling: Scaling the Harness in Agentic AI
Retrying vs Resampling in AI Control
Agent-as-Peer-Debriefer: A Multi-Agent Framework with Perspective-Based Refinement for Qu…
Summoning the Oracle to Slay It: Mitigating Look-Ahead Bias in Financial Backtesting with…
DemoEvolve: Overcoming Sparse Feedback in Agentic Harness Evolution with Demonstrations
TIGER: Text-Informed Generalized Enzyme-Reaction Retrieval
Benchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc Teamwork
Efficient Benchmarking Is Just Feature Selection and Multiple Regression
Mosaic: Compositional Multi-Concept Erasure via Vector Field Blending
LGMT: Logic-Grounded Metamorphic Testing for Evaluating the Reasoning Reliability of LLMs
E3AD: An Emotion-Aware Vision-Language-Action Model for Human-Centric End-to-End Autonomo…
Why We Need World Models for AGI: Where LLMs Fail and How World Models May Outperform
BackWeak: Backdooring Knowledge Distillation Simply with Weak Triggers and Fine-tuning
LC-ERD: Mining Latent Logic for Self-Evolving Reasoning via Consistency-Regulated Reward …