Machine Learning

Split-RL: Local Conflict Resolution in Reinforcement Learning

Reinforcement learning (RL) policies are often trained by mixing contradictory feedback that is localized in space and time. For example, a robot may prioritize speed in open areas versus precision in tight gaps. We introduce Split-RL, a Gradient …

Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributions

Data-Driven Loss Functions for Inference-Time Optimization in Text-to-Image

Accelerating Vehicle Routing via AI-Initialized Genetic Algorithms

Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT

Efficient Fairness-Performance Pareto Front Computation

GradMetaNet: An Equivariant Architecture for Learning on Gradients

Non-rectangular Robust MDPs with Normed Uncertainty Sets

On the Convergence of Single-Timescale Actor-Critic

Policy Optimized Text-to-Image Pipeline Design