Similar Items: Why Global LLM Leaderboards Are Misleading: Small Portfolios for Heterogeneous Supervised ML
- Strait: Perceiving Priority and Interference in ML Inference Serving
- Dimensionality-Aware Anomaly Detection in Learned Representations of Self-Supervised Speech Models
- Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why
- Label-Efficient School Detection from Aerial Imagery via Weakly Supervised Pretraining and Fine-Tuning
- Generating Statistical Charts with Validation-Driven LLM Workflows
- Steer Like the LLM: Activation Steering that Mimics Prompting