Leakage-Safe and Scheduler-Aware Machine Learning for Grid Job Runtime Prediction
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
How Semantically Stable Are LLM Refusals? Measuring Confusion in Local Safety Boundaries
Oops, Not Now: PEARL, a RAG-Based Support Agent for Gameplay and What Players Want from A…
Large Language Models As Shannon Lossy Compressors Not Solomonoff Induction Estimators: T…
Learning Human-Like Badminton Skills for Humanoid Robots
Hindsight-Anchored Policy Optimization: Learning Through Hindsight with Thompson Sampling…
Testing the Limits of Truth Directions in LLMs
Can We Still Trace L1 Signals? Investigating the Resilience of Native Language Signals in…
MulRobBench: A Decision-Level Benchmark for Safe and Security-Policy-Compliant Multimodal…
Looping Is Not Reliability: State-Bound Evidence and Typed Revision Contracts for Agentic…
TyPatch: Transforming Patches into Typestate Rules for Kernel Bug Detection
Failure-Guided Co-Evolution of Prompts and Training Data
Tool Use Reduces Depth-Induced Collapse in OOD Reasoning
LPA-CWM: A Learned Physical Adjudicator for Motion Reasoning with Counterfactual World Mo…
LIMBO: Lifelong Inference-Time Memory and Budget Optimization for LLM Agents
Towards Evolving Context Parameterization for Large Language Models
Mizan: A National Benchmark for Evaluating Large Language Models on Iraqi Arabic and the …
Predictive audio representations for early detection and tracking of hidden dynamic objec…
Hardware-Aware Learned Representation Compression for Distributed In-Sensor Vision
Thought without systematicity? Evaluating reasoning models on rule induction tasks
Confuse the Model, Control the Flow: Understanding and Mitigating Privacy Leakage from LL…
Rethinking the Implications of Human Feedback for Preference Learning in Human-Robot Coll…
Event-Native Symbolic-Temporal Spike Encoding Framework for Heterogeneous Cyber Streams
Privacy-enhanced federated learning via asynchronous aggregation and local differential p…
Adaptive Phase-Switching for Communication-Efficient Federated LoRA Fine-Tuning
RA-CoA: Training-free Fashion Image Captioning via Retrieval-Augmented Chain-of-Attributes
HarnessBandit: Joint Learnability-Transferability Scheduling for Multi-Harness Agentic Re…
Building a Production Greek-English Speech Recognizer
One Spectrum, Two Resources: Data-Memory Scaling in Autoregressive Prediction
Atria Dawn: The Dawn of Agentic Superintelligence