{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963},{"id":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"id":"2304.11277","title":"PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel","created":"2023-04-21","cited_by_count":660},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656},{"id":"2406.12845","title":"Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts","created":"2024-06-18","cited_by_count":376},{"id":"2103.09568","title":"A Practical Guide to Multi-Objective Reinforcement Learning and Planning","created":"2021-03-17","cited_by_count":256},{"id":"2404.19733","title":"Iterative Reasoning Preference Optimization","created":"2024-04-30","cited_by_count":246},{"id":"1402.0590","title":"A Survey of Multi-Objective Sequential Decision-Making","created":"2014-02-04","cited_by_count":242},{"id":"2406.08673","title":"HelpSteer2: Open-source dataset for training top-performing reward models","created":"2024-06-12","cited_by_count":236},{"id":"1908.08342","title":"A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation","created":"2019-08-21","cited_by_count":177},{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176},{"id":"2402.10207","title":"Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment","created":"2024-02-15","cited_by_count":175},{"id":"2206.13517","title":"ProGen2: Exploring the Boundaries of Protein Language Models","created":"2022-06-27","cited_by_count":159},{"id":"2402.18571","title":"Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards","created":"2024-02-28","cited_by_count":148},{"id":"2406.02900","title":"Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms","created":"2024-06-05","cited_by_count":143},{"id":"2312.10240","title":"Rich Human Feedback for Text-to-Image Generation","created":"2023-12-15","cited_by_count":141},{"id":"2310.03708","title":"Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization","created":"2023-10-05","cited_by_count":124},{"id":"2401.01879","title":"Theoretical guarantees on the best-of-n alignment policy","created":"2024-01-03","cited_by_count":124},{"id":"2402.10571","title":"Direct Preference Optimization with an Offset","created":"2024-02-16","cited_by_count":122},{"id":"2405.16436","title":"Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer","created":"2024-05-26","cited_by_count":109},{"id":"2102.04509","title":"Oops I Took A Gradient: Scalable Sampling for Discrete Distributions","created":"2021-02-08","cited_by_count":92},{"id":"2402.02229","title":"Vanilla Bayesian Optimization Performs Great in High Dimensions","created":"2024-02-03","cited_by_count":92},{"id":"1906.02386","title":"Deep Reinforcement Learning for Multi-objective Optimization","created":"2019-06-06","cited_by_count":90},{"id":"2506.19767","title":"SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning","created":"2025-06-24","cited_by_count":84},{"id":"2404.16767","title":"REBEL: Reinforcement Learning via Regressing Relative Rewards","created":"2024-04-25","cited_by_count":69},{"id":"2405.19316","title":"Robust Preference Optimization through Reward Model Distillation","created":"2024-05-29","cited_by_count":67},{"id":"2402.19078","title":"Smooth Tchebycheff Scalarization for Multi-Objective Optimization","created":"2024-02-29","cited_by_count":54},{"id":"2401.05675","title":"Parrot: Pareto-optimal Multi-Reward Reinforcement Learning Framework for Text-to-Image Generation","created":"2024-01-11","cited_by_count":36},{"id":"2306.06156","title":"PoET: A generative model of protein families as sequences-of-sequences","created":"2023-06-09","cited_by_count":29},{"id":"2410.10148","title":"AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization","created":"2024-10-14","cited_by_count":29},{"id":"1906.06211","title":"Distributionally Robust Counterfactual Risk Minimization","created":"2019-06-14","cited_by_count":26},{"id":"2407.17466","title":"Traversing Pareto Optimal Policies: Provably Efficient Multi-Objective Reinforcement Learning","created":"2024-07-24","cited_by_count":15},{"id":"2402.16030","title":"Don't Forget Your Reward Values: Language Model Alignment via Value-based Calibration","created":"2024-02-25","cited_by_count":13},{"id":"2407.00002","title":"Kermut: Composite kernel regression for protein variant effects","created":"2024-04-09","cited_by_count":12},{"id":"2406.07295","title":"Multi-objective Reinforcement learning from AI Feedback","created":"2024-06-11","cited_by_count":10},{"id":"2405.12961","title":"Aligning Transformers with Continuous Feedback via Energy Rank Alignment","created":"2024-05-21","cited_by_count":7},{"id":"2412.20984","title":"Pareto-Optimal Energy Alignment for Designing Nature-Like Antibodies","created":"2024-12-30","cited_by_count":7},{"id":"2508.04724","title":"Understanding protein function with a multimodal retrieval-augmented foundation model","created":"2025-08-05","cited_by_count":6},{"id":"2603.10302","title":"How to make the most of your masked language model for protein engineering","created":"2026-03-11","cited_by_count":2}],"next_cursor":null}