PhysMAS: Physics-Grounded Multi-Agent Synthesis of Compositional 4D Gaussians
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
An Auditable Symbolic-RAG-Generative AI Architecture for Goal-Oriented Conversation Orche…
Agentic Pressure: The Endogenous Entropy of Reliable Autonomy
Generator-Independent Runtime Assurance under Partial Observation
Quantile-Led Feature Extraction for Multi-Horizon Predictive Maintenance in Industrial Ma…
Exposing Weaknesses in Emotion Recognition in Conversations
DAREBench: Deployment-Aware and Reliable Evaluation of Models as Agents
Modus Tollens and Counterfactuals and Counterfactual Reasoning Based on Three Types of Ne…
Beyond Final Decisions: A Process-Centric Benchmark for Transparent AI-Assisted Peer Revi…
More Than Mimicking Reviewers: Evaluating LLMs for Pre-Submission Peer Review
Learning Counterfactual World Models for Embodied Reasoning under Partial Observability
AgentBrew: Offline Tool-Use Agent Learning from Raw Real-World Trajectories
When and Why LLM Causal Priors Help: Closed-Loop Prior Selection for Amortized Causal Inf…
Generating Instance Generators in PDDL Planning
Beyond Prompts: Measuring and Optimizing LLM Tool-Agent Harnesses
The Normalization of Deviance in AI Development
From Monolithic Blending to Agentic Orchestration: Dynamic Response for Conversational As…
What LLM Trading Agents Actually Do in Production: A Six-Month, Population-Scale Record f…
The convergent laboratory: when AI reasoning, autonomous experiments, high performance an…
CUSP: Decomposable Collective Uncertainty for Multi-Agent Multimodal Reasoning
Recovering Temporal and Geographic Signals from Language Model Embeddings
Distilling Vision-Language Models for On-Device Fire Understanding
SCIRIGOR:Evaluating Open-Ended Scientific Analysis Beyond Final Scores
Steering Geometry: Validating Human Value Geometry in LLM Steering Space
The Failure Happens Before the Drift: The Social Dynamics of Values in LLM Agent Societies
Beyond "AI Helps Humans": Decision-Targeted Evaluation Design for Human-Agent Teams in th…
Reducing Hallucinations in LLM-based Scientific Literature Analysis Using Peer Context Ou…
Deep belief networks are exact
Unraveling the Real Working Mechanism and Inherent Flaws of GAE: A Method for Interpretin…
Linear Algebra Foundations of Efficient Attention: A Phase Reversal in Rank Collapse Unde…