ChinaHeritaQA: A Culturally-Grounded Visual Question Answering Dataset for World Heritage…
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
From Hazard Functions to Language Space: Cox-Supervised Distillation of Survival Risk int…
Order Matters: Unveiling the Hidden Impact of Macro Placement Sequences via Proxy-Guided …
Synthetic but Not Realistic: The Evaluation Challenge in Generative Modelling for Structu…
FAME: Forecastability-Aware Mixture of Experts for Heterogeneous Time Series Forecasting
Cheap Reward Hacking Detection
Introducing the OpenAI Economic Research Exchange
The Open Source Community is backing OpenEnv for Agentic RL
Five labs, five minds: building a multi-model finance drama on small models
LLM Research Papers: The 2026 List (January to May)
Thousand Token Wood: shipping a multi-agent economy on a 3B model
How to Stop Shipping Low-Quality RL Environments (with Examples)
The University of Cambridge says it successfully tested a vaccine with an AI-designed ant…
Fine-tuning an LLM to write docs like it's 1995
Benchmarking Emergent Coordination in Large-Scale LLM Populations: An Evaluation Framewor…
Is Diversity All You Need for Scalable Robotic Manipulation?
A Systematic Analysis of Biases in Large Language Models
Semi-Offline Reinforcement Learning for Optimized Text Generation
Evidence Over Plans: Online Trajectory Verification for Skill Distillation
Learning What Matters: Probabilistic Task Selection via Mutual Information for Model Fine…
Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Ma…
Beyond Means: Topological Causal Effects under Persistent-Homology Ignorability
Severity-Aware Curriculum Learning with Multi-Model Response Selection for Medical Text G…
Where does Absolute Position come from in decoder-only Transformers?
TRACE: A Temporal Conditional Estimation for Multimodal Time Series Foundation Models
What Objects Enable, Not What They Are: Functional Latent Spaces for Affordance Reasoning
ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows
Enhancing Software Engineering Through Closed-Loop Memory Optimization
Retry Policy Gradients in Continuous Action Spaces
Quantifying Sensitivity for Tree Ensembles: A symbolic and compositional approach