TRACE: Trajectory Correction from Cross-layer Evidence for Hallucination Reduction
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Generating Instance Generators in PDDL Planning
ViT3Flow: A Test-Time Training Transformer MeanFlow for Postoperative Radiograph Synthesi…
SCIRIGOR:Evaluating Open-Ended Scientific Analysis Beyond Final Scores
SAFEGuard: Detect Optimization-Based Jailbreak Attacks Through Harmful Semantic Analysis …
Building Trustworthy Graph-Agentic RAG for Social Good: Architectures, Failure Propagatio…
Scientific Data Skills: Enabling Agent-Ready Scientific Data Services at Scale
From Concentration to Differentiation and Back: Routing Effective Rank in MoE Reasoning C…
Adaptive Cost-Sensitive Machine Learning for Autonomous Robot Navigation Failure Predicti…
Learning transferable human physiology from two million hours of sleep with SleepFM-2
Instance-wise Linearization of Neural Network for Model Interpretation
NormViz: A Benchmark and Framework for Grounding Multimodal Reasoning in Global Cultures
DUA-D2C: Dynamic Uncertainty Aware Method for Overfitting Remediation in Deep Learning
PAN: A World Model for General, Actionable, and Long-Horizon World Simulation
CrossModalQA: A Cross-modal and Multi-hop Benchmark for Multimodal Retrieval-augmented Ge…
SSP-DMGTimeNet: Physics-Constrained Learning for Spatiotemporal Trajectory Prediction of …
ProToMEx: Rapid, Interpretable Explanations via Structured Representations
Diffusion models for eye-gaze trajectory generation using position and velocity represent…
Intent Drift at SME Scale: Deployment Practice, Not Model Capability, Determines Agentic …
CIVI: A Framework for Diagnosing Search Agent Failures in Civic Information
Data-driven rational function neural networks: a new method for generating analytical mod…
EEG-Driven Decoding Framework for Passenger Hazard Perception in Highly Automated Vehicles
Neural Symbollic Regression Using Deep Learning and Sparse Modelling
GIFT: Reconciling Post-Training Objectives via Variational Finite-Temperature Gibbs Initi…
Procedural Graphs: Self-Evolving Execution Structures for LLM Agents
DART: A DAG-Based Reputation and Incentive Framework via Blockchain-Enabled Governance fo…
Empowering VLMs for Few-Shot Multimodal Time Series Classification via Tailored Agentic R…
SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?
An Auditable Symbolic-RAG-Generative AI Architecture for Goal-Oriented Conversation Orche…
A Generalization of Amari's Bayesian Duality