Skip to content
conftrace_

Rafael Rafailov

22 papers · 2021–2026 · 10 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
+8 more ↓ πŸ—ΊοΈ Taxonomy Completionist (40) πŸƒ Academic Marathon Β· Sprint 🌍 Conference Polyglot Β· Gold πŸŒ‰ Interdisciplinary Bridge Β· Silver 🐣 Hot Topic Early Bird
🧭 Keyword Pioneer 🀝 Dynamic Duo (18) πŸ‘‘ Triple Crown ⚑ Prolific Year Β· Prolific πŸ”₯ Unstoppable Β· Bronze πŸ’Ž Century Club Β· Bronze 🌈 Renaissance Researcher (5) πŸ—ƒοΈ Keyword Collector (102)

Venues

NeurIPS (5) ICLR (4) ICML (3) L4DC (3) CoRL (2) ACL (1) COLING (1) CVPR (1) EACL (1) EMNLP (1)

Top co-authors

Chelsea Finn (18) Archit Sharma (5) Eric Mitchell (5) Stefano Ermon (5) Sergey Levine (4) Tianhe Yu (4) Christopher D Manning (3) Aravind Rajeswaran (3) Aviral Kumar (2) Scott Niekum (2)

Research topics

Machine Learning (18) Artificial Intelligence (15) Core AI (12) Learning Types (10) Reinforcement Learning (8) Methods (8) Optimization & Theory (7) Natural Language Processing (4) Application Areas (4) Learning Paradigms (4) Deep Learning (3) Robotics (3) Capabilities (3) Core Methods (3) Generation (2)

Keywords

reinforcement learning (6) offline reinforcement learning (6) reward model (4) direct preference optimization (4) model-based reinforcement learning (4) reinforcement learning from human feedback (4) language model (3) large language model (3) language model alignment (3) preference learning (2) preference modeling (2) human feedback (2) text generation (2) contrastive learning (2) text classification (1) few-shot learning (1) transfer learning (1) maximum entropy (1) on-policy sampling (1) policy optimization (1)

Papers

LitBench: A Benchmark and Dataset for Reliable Evaluation of Creative Writing EACL 2026 Collapse or Thrive: Perils and Promises of Synthetic Data in a Self-Generating World ICML 2025 PERSONA: A Reproducible Testbed for Pluralistic Alignment COLING 2025 An Emulator for Fine-tuning Large Language Models using Small Language Models ICLR 2024 Contrastive Preference Learning: Learning from Human Feedback without Reinforcement Learning ICLR 2024 Diffusion Model Alignment Using Direct Preference Optimization CVPR 2024 Disentangling Length from Quality in Direct Preference Optimization ACL 2024 Efficient imitation learning with conservative world models L4DC 2024 Language Model Detectors Are Easily Optimized Against ICLR 2024 OpenVLA: An Open-Source Vision-Language-Action Model CoRL 2024 Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data ICML 2024 Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms NeurIPS 2024 Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels NeurIPS 2024 Contrastive Example-Based Control L4DC 2023 Direct Preference Optimization: Your Language Model is Secretly a Reward Model NeurIPS 2023 Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback EMNLP 2023 MOTO: Offline Pre-training to Online Fine-tuning for Model-based Robot Learning CoRL 2023 Vision-Based Manipulators Need to Also See from Their Hands ICLR 2022 COMBO: Conservative Offline Model-Based Policy Optimization NeurIPS 2021 Offline Meta-Reinforcement Learning with Advantage Weighting ICML 2021 Offline Reinforcement Learning from Images with Latent Space Models L4DC 2021 Visual Adversarial Imitation Learning using Variational Models NeurIPS 2021