Agentic Literacy Debt: A Structural Problem the AI Literacy Field Has Not Yet Named
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Memory-Based vs. Context-Only Conditioning Produces Distinct Behavioral Patterns in State…
Bridging the Stability-Expressivity Gap: Synthetic Data Scaling and Preference Alignment …
Pruning and Distilling Mixture-of-Experts into Dense Language Models
Whose Name Comes Up? III: Persona Prompting Effects in LLM-Based Scholar Recommendation
QuITE: Query-Based Irregular Time Series Embedding
Mind the Gap: Mixtures of Gaussians in Approximate Differential Privacy
Unified Synthesis of Compositional Speech and Sound from Free-Form Text Prompts
MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Mo…
An LLM-Based Assistance System for Intuitive and Flexible Capability-Based Planning
LACUNA: Safe Agents as Recursive Program Holes
Extracting Small Translation Specialists from LLMs by Aggressively Pruning Experts
Learning to Assign Prediction Tasks to Agents with Capacity Constraints
Semantic Flow Regularization: Teaching LLMs to Generate Diverse Yet Coherent Responses
When Think-with-Image Meets Safety: What Determines Multimodal Jailbreak Robustness?
Efficient Pre-Training of LLMs through Truncated SVD Layers
Snippet-Driven Supply Chain Discovery with LLMs: Scaling Visibility in China
Locality-Aware Redundancy Pruning for LLM Depth Compression
UniMaia: Steering Chess Policies with Language for Human-like Play
Can Segmentation Models Understand the World? Towards Proactive Affordance Reasoning via …
HumanoidMimicGen: Data Generation for Loco-Manipulation via Whole-Body Planning
Simulation-Informed Diffusion for Decentralized Multi-robot Motion Planning
PrunePath: Towards Highly Structured Sparse Language Models
Developing an Intelligent Job Recommendation System Using Semantic Retrieval and Explaina…
Supervised Distributional Reduction via Optimal Transport and Dependence Maximization
Clinical Validation of the Melanoscope AI Mobile Dermoscopy Clinical Decision Support Sys…
Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an An…
ASTRA: Communication-Efficient Acceleration for Multi-Device Transformer Inference
EVADE-Bench: Multimodal Benchmark for Evaluating and Enhancing Evasive Content Detection
Manboformer: Learning Gaussian Representations via Spatial-temporal Attention Mechanism