CrossModalQA: A Cross-modal and Multi-hop Benchmark for Multimodal Retrieval-augmented Ge…
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
Hyperparameter Scaling Laws Across MoE Sparsity
The human-authorship halo: attribution bias in literary style evaluation by humans and AI
A Data-Driven Framework for Identifying and Prioritizing RPA Opportunities in Healthcare …
Procedural Graphs: Self-Evolving Execution Structures for LLM Agents
Data-driven rational function neural networks: a new method for generating analytical mod…
Leveraging Cardiac Imaging to Improve ECG-Based Detection of Chagas Disease in Resource-C…
FACT: A Forensic Agent with Compiled Tool-Use Trajectories for AI-Generated Image Detecti…
Intent Drift at SME Scale: Deployment Practice, Not Model Capability, Determines Agentic …
A Generalization of Amari's Bayesian Duality
Neural Symbollic Regression Using Deep Learning and Sparse Modelling
The Surprising Effectiveness of Approximate Value Iteration in Self-Play
SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?
From Where to How: Continuous 4D Interaction Forecasting from Egocentric Video
Adaptive Cost-Sensitive Machine Learning for Autonomous Robot Navigation Failure Predicti…
Analysis of Respiratory Sinus Arrhythmia with Neural Networks
Recovering Temporal and Geographic Signals from Language Model Embeddings
Exposing Weaknesses in Emotion Recognition in Conversations
Generator-Independent Runtime Assurance under Partial Observation
ProToMEx: Rapid, Interpretable Explanations via Structured Representations
A Measurement Study of LLM Inference Trade-offs Across Edge Continuum Hardware
Instance-wise Linearization of Neural Network for Model Interpretation
Provable Pluralistic Alignment: Multi-Party RLHF under Offline Human Feedback
Exploring Bottom-Up Clustering for Creating Semantic IDs
Same Values, Different Languages? From Multilingual Probing to Steering LLMs Toward Chine…
Deposon: An Auditable, Conservation-Guaranteed, Game-Theoretically Tested Scattering Laye…
MoEMB: Scaling Universal Multimodal Embeddings with Efficient Mixture-of-Experts Models
Closing the Consistency Gap: Self-Evolving Agents That Learn to Stay on Course
SkillAdam: Stable and Efficient Skill Evolution for Agents
Answer-Distribution Trajectories: A Stochastic-Dynamics View of LLM Reasoning