Towards Shutdownable Agents: Generalizing Stochastic Choice in RL Agents and LLMs
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Rectification Difficulty and Optimal Sample Allocation in LLM-Augmented Surveys
Decoupling Language Guidance from Backbones for Text-Guided Medical Segmentation
Embodied Multi-Agent Coordination by Aligning World Models Through Dialogue
Tuning Derivatives for Causal Fairness in Machine Learning
The LLMbda Calculus: AI Agents, Conversations, and Information Flow
Preference Conditioned Multi-Objective Reinforcement Learning: Decomposed, Diversity-Driv…
Principles of Lipschitz continuity in neural networks
How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential …
Data-Driven Learnability Transition of Measurement-Induced Entanglement
H3Former: Hypergraph-based Semantic-Aware Aggregation via Hyperbolic Hierarchical Contras…
Explaining Human Choice Probabilities with Simple Vector Representations
Evaluating Retrieval-Augmented Generation vs. Long-Context Input for Clinical Reasoning o…
GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs
Single-Frame Point-Pixel Registration via Supervised Cross-Modal Feature Matching
BackendForge: Benchmarking Agentic End-to-End Code Generation with Backend Services
Reference-Based Face Super-Resolution Using the Spatial Transformer
EasyOPD: An Easy-to-use On-Policy Distillation Framework for Large Language Models
Temporal Feature Distillation for Label-Efficient Precise Event Spotting in Sports Videos
MED-DSLC: Multi-Expert-Domain Classification via Domain Supervision and Logit Calibration
From Checker to Forecaster: Code-Owned Evaluation of Model-Generated Strategic Routes Und…
Enhanced Byzantine-Robust Federated Learning Via Truncated-Quadratic Loss for Heterogeneo…
CGS: Configurable Graph Summarization with Bounded Neighborhood Loss and Query Support
Sticky Jump Diffusions: A Unifying View of Masked, Continuous, and Hybrid Diffusion
Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows
Transferable Implicit Solvent Machine Learning Potential for Drugs and Proteins Approachi…
Learning To Focus: Anatomy-Guided Attention Regularization for Medical Image Classificati…
Predictive Divergence Masks for LLM RL
3D-DefectBench: A Controlled Factorial Study of Vision-Language Model Evaluation Pipeline…
LIDAR-AD: A Decoder-Free Latent-Interaction Dreamer with Action-Residual Chains for Auton…