Safe Reinforcement Learning with Preference-based Constraint Inference
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
How Mobile World Model Guides GUI Agents?
A Proactive Multi-Agent Dialogue Framework for Assessing Social Language Disorder Traits …
WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native …
Does Your Wildfire Prediction Model Actually Work, or Just Score Well?
Visually-Guided Policy Optimization for Multimodal Reasoning
Representation over Routing: Overcoming Surrogate Hacking in Multi-Timescale PPO
Uncovering the Latent Potential of Deep Intermediate Representations
Do Language Models Know What Not to Say? Causal Evidence for Statistical Preemption in LL…
AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery
PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning
Sparse Compositional Flow Matching by geometric assembly from motion primitives
The Deterministic Horizon: Impossibility Results as Design Specifications for Trustworthy…
Learning Through Noise: Why Subliminal Learning Works and When It Fails
DreamerNLplus: Interpretable Modeling of Mental Health Dynamics from Social Media Timelin…
Decomposing and Measuring Evaluation Awareness
VACE: Learning Geometrically Structured Representations for Time Series Anomaly Detection
SUDP: Secret-Use Delegation Protocol for Agentic Systems
Any2Any: Efficient Cross-Embodiment Transfer for Humanoid Whole-Body Tracking
It's the humans, not the data: Geopolitical bias in LLMs originates in post-training, amp…
PGT: Procedurally Generated Tasks for improving visual grounding in MLLMs
XWind: A Cross-site Router for Large Language Model Inference Serving at Renewable Energy…
A measurement substrate for agentic Kubernetes operations: Methodology and a case study i…
SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research
Robust Counterfactual Inference in Markov Decision Processes
FATHOMS-RAG: A Framework for the Assessment of Thinking and Observation in Multimodal Sys…
Do Synthetic Brain MRIs Reliably Improve Tumour Classification? A StyleGAN2-ADA Class-Pla…
SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
MedSAE: Dissecting MedCLIP Representations with Sparse Autoencoders
Bridging AI and Clinical Reasoning: Abductive Explanations for Alignment on Critical Symp…