Similar Items: Automated Clinical Report Generation for Remote Cognitive Remediation: Comparing Knowledge-Engineered Templates and LLMs in Low-Resource Settings
- LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling
- Dependency Parsing Across the Resource Spectrum: Evaluating Architectures on High and Low-Resource Languages
- Misaligned by Reward: Socially Undesirable Preferences in LLMs
- Uncertainty-Aware Structured Data Extraction from Full CMR Reports via Distilled LLMs
- Tibetan-TTS:Low-Resource Tibetan Speech Synthesis with Large Model Adaptation
- Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs