MedPsy: State-of-the-Art Small Medical Language Models for Efficient Edge Deployment
cs.CL
Submitted: 2026-11-01
Updated: 2026-11-19
Code: https://github.com/tether-ai-research/qvac-medpsy
Terminology
Sources
- MedGemma Technical Report
- MedGemma 1.5 Technical Report
- Fleming-R1: Toward Expert-Level Medical Reasoning via Reinforcement Learning
- Measuring Massive Multitask Language Understanding
- MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
- HealthBench: Evaluating Large Language Models Towards Improved Human Health
- Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RL
- ThinkLess: A Training-Free Inference-Efficient Method for Reducing Reasoning Redundancy
- The Energy Cost of Reasoning: Analyzing Energy Usage in LLMs with Test-time Compute
- Baichuan-M3: Modeling Clinical Inquiry for Reliable Medical Decision-Making
- Med-U1: Incentivizing Unified Medical Reasoning in LLMs via Large-scale Reinforcement Learning
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- OpenCompass: A Universal Evaluation Platform for Large Language Models
- CompassJudger-2: Towards Generalist Judge Model via Verifiable Rewards
- Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks
- LongHealth: A Question Answering Benchmark with Long Clinical Documents
- Ultra-FineWeb: Efficient Data Filtering and Verification for High-Quality LLM Training Data
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data