语言大模型 / LLM - arXivDaily 专题

2404.12926 2025-01-14 cs.AI 57%

MM-PhyRLHF: Reinforcement Learning Framework for Multimodal Physics Question-Answering

Janak Kapuriya, Chhavi Kirtani, Apoorv Singh, Jay Saraf, Naman Lal, Jatin Kumar, Adarsh Raj Shivam, Astha Verma, Avinash Anand, Rajiv Ratn Shah

专题命中后训练与偏好优化：RLHF(abstract)；分类 cs.AI

2411.04127 2024-11-08 cs.AI 57%

Combining Theory of Mind and Kindness for Self-Supervised Human-AI Alignment

Joshua T. S. Hewson

专题命中后训练与偏好优化：RLHF(abstract)；分类 cs.AI

2405.19279 2024-11-08 cs.LG 57%

Understanding and Minimising Outlier Features in Neural Network Training

Bobby He, Lorenzo Noci, Daniele Paliotta, Imanol Schlag, Thomas Hofmann

专题命中后训练与偏好优化：post-training(abstract)；分类 cs.LG

Comments NeurIPS 2024 camera ready

2407.01648 2024-10-29 q-bio.BM cs.LG q-bio.QM 57%

Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization

Siyi Gu, Minkai Xu, Alexander Powers, Weili Nie, Tomas Geffner, Karsten Kreis, Jure Leskovec, Arash Vahdat, Stefano Ermon

专题命中后训练与偏好优化：preference optimization(abstract)；分类 cs.LG

2409.19472 2024-10-24 cs.CV cs.LG 57%

Towards Croppable Implicit Neural Representations

Maor Ashkenazi, Eran Treister

专题命中后训练与偏好优化：post-training(abstract)；分类 cs.LG

Comments Accepted to NeurIPS 2024

2404.12318 2024-10-15 cs.CL 57%

Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment

Zhaofeng Wu, Ananth Balashankar, Yoon Kim, Jacob Eisenstein, Ahmad Beirami

专题命中后训练与偏好优化：language model(abstract)；分类 cs.CL

Comments EMNLP 2024

2406.09279 2024-10-10 cs.CL 57%

Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback

Hamish Ivison, Yizhong Wang, Jiacheng Liu, Zeqiu Wu, Valentina Pyatkin, Nathan Lambert, Noah A. Smith, Yejin Choi, Hannaneh Hajishirzi

专题命中后训练与偏好优化：language model(abstract)；分类 cs.CL

Comments Neurips 2024 camera-ready

2310.15128 2024-09-05 cs.CV cs.LG quant-ph 57%

Projected Stochastic Gradient Descent with Quantum Annealed Binary Gradients

Maximilian Krahn, Michele Sasdelli, Fengyi Yang, Vladislav Golyanik, Juho Kannala, Tat-Jun Chin, Tolga Birdal

专题命中后训练与偏好优化：post-training(abstract)；分类 cs.LG

Journal ref BMVC 2024

2206.00794 2024-08-21 stat.ML cs.LG math.ST stat.TH 57%

Sequential Bayesian Neural Subnetwork Ensembles

Sanket Jantre, Shrijita Bhattacharya, Nathan M. Urban, Byung-Jun Yoon, Tapabrata Maiti, Prasanna Balaprakash, Sandeep Madireddy

专题命中后训练与偏好优化：post-training(abstract)；分类 cs.LG

2408.04532 2024-08-09 cs.LG 57%

How Transformers Utilize Multi-Head Attention in In-Context Learning? A Case Study on Sparse Linear Regression

Xingwu Chen, Lei Zhao, Difan Zou

专题命中后训练与偏好优化：post-training(abstract)；分类 cs.LG

2311.13355 2024-08-06 cs.CV cs.LG 57%

Unified Classification and Rejection: A One-versus-All Framework

Zhen Cheng, Xu-Yao Zhang, Cheng-Lin Liu

专题命中后训练与偏好优化：post-training(abstract)；分类 cs.LG

Comments Published in Machine Intelligence Research (https://link.springer.com/article/10.1007/s11633-024-1514-4)

2406.05391 2024-07-22 cs.LG 57%

DUPLEX: Dual GAT for Complex Embedding of Directed Graphs

Zhaoru Ke, Hang Yu, Jianguo Li, Haipeng Zhang

专题命中后训练与偏好优化：post-training(abstract)；分类 cs.LG

2401.04056 2024-06-14 cs.LG 57%

A Minimaximalist Approach to Reinforcement Learning from Human Feedback

Gokul Swamy, Christoph Dann, Rahul Kidambi, Zhiwei Steven Wu, Alekh Agarwal

专题命中后训练与偏好优化：preference optimization(abstract)；分类 cs.LG

2406.07295 2024-06-13 cs.LG 57%

Multi-objective Reinforcement learning from AI Feedback

Marcus Williams

专题命中后训练与偏好优化：language model(abstract)；分类 cs.LG

2406.05882 2024-06-11 cs.LG stat.ML 57%

Distributional Preference Alignment of LLMs via Optimal Transport

Igor Melnyk, Youssef Mroueh, Brian Belgodere, Mattia Rigotti, Apoorva Nitsure, Mikhail Yurochkin, Kristjan Greenewald, Jiri Navratil, Jerret Ross

专题命中后训练与偏好优化：LLM(abstract)；分类 cs.LG

2312.09748 2024-06-11 cs.LG cs.SE 57%

VNN: Verification-Friendly Neural Networks with Hard Robustness Guarantees

Anahita Baninajjar, Ahmed Rezine, Amir Aminifar

专题命中后训练与偏好优化：post-training(abstract)；分类 cs.LG

2310.12103 2024-06-05 cs.AI cs.NE 57%

Quality Diversity through Human Feedback: Towards Open-Ended Diversity-Driven Optimization

Li Ding, Jenny Zhang, Jeff Clune, Lee Spector, Joel Lehman

专题命中后训练与偏好优化：RLHF(abstract)；分类 cs.AI

Comments ICML 2024

2310.06600 2024-05-29 cs.LG cs.CV 57%

Pi-DUAL: Using Privileged Information to Distinguish Clean from Noisy Labels

Ke Wang, Guillermo Ortiz-Jimenez, Rodolphe Jenatton, Mark Collier, Efi Kokiopoulou, Pascal Frossard

专题命中后训练与偏好优化：post-training(abstract)；分类 cs.LG

Comments Accepted ICML 2024

2308.02585 2024-05-02 cs.LG 57%

PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback

Souradip Chakraborty, Amrit Singh Bedi, Alec Koppel, Dinesh Manocha, Huazheng Wang, Mengdi Wang, Furong Huang

专题命中后训练与偏好优化：RLHF(abstract)；分类 cs.LG

2403.06735 2024-03-12 cs.CV cs.AI 57%

Enhancing Image Caption Generation Using Reinforcement Learning with Human Feedback

Adarsh N L, Arun P, Aravindh N L

专题命中后训练与偏好优化：RLHF(abstract)；分类 cs.AI

Comments 6 Pages, 8 figures

2306.00740 2024-02-15 cs.LG stat.ML 57%

On the Limitations of Temperature Scaling for Distributions with Overlaps

Muthu Chidambaram, Rong Ge

专题命中后训练与偏好优化：post-training(abstract)；分类 cs.LG

Comments 27 pages, 9 Figures, published in ICLR 2024

2402.04229 2024-02-07 cs.LG cs.SD eess.AS 57%

MusicRL: Aligning Music Generation to Human Preferences

Geoffrey Cideron, Sertan Girgin, Mauro Verzetti, Damien Vincent, Matej Kastelic, Zalán Borsos, Brian McWilliams, Victor Ungureanu, Olivier Bachem, Olivier Pietquin, Matthieu Geist, Léonard Hussenot, Neil Zeghidour, Andrea Agostinelli

专题命中后训练与偏好优化：RLHF(abstract)；分类 cs.LG

2310.02054 2024-02-06 cs.AI 57%

AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model

Zibin Dong, Yifu Yuan, Jianye Hao, Fei Ni, Yao Mu, Yan Zheng, Yujing Hu, Tangjie Lv, Changjie Fan, Zhipeng Hu

专题命中后训练与偏好优化：RLHF(abstract)；分类 cs.AI

2303.10420 2023-12-27 cs.CL 57%

A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models

Junjie Ye, Xuanting Chen, Nuo Xu, Can Zu, Zekai Shao, Shichun Liu, Yuhan Cui, Zeyang Zhou, Chao Gong, Yang Shen, Jie Zhou, Siming Chen, Tao Gui, Qi Zhang, Xuanjing Huang

专题命中后训练与偏好优化：RLHF(abstract)；分类 cs.CL

2311.18376 2023-12-01 q-bio.NC cs.LG 57%

Age Effects on Decision-Making, Drift Diffusion Model

Zahra Kavian, Kimia Hajisadeghi, Yashar Rezazadeh, Mehrbod Faraji, Reza Ebrahimpour

专题命中后训练与偏好优化：post-training(abstract)；分类 cs.LG

2311.14766 2023-11-28 cs.LG math.ST stat.ME stat.TH 57%

Reinforcement Learning from Statistical Feedback: the Journey from AB Testing to ANT Testing

Feiyang Han, Yimin Wei, Zhaofeng Liu, Yanxing Qi

专题命中后训练与偏好优化：RLHF(abstract)；分类 cs.LG

2311.10203 2023-11-20 cs.LG math.OC 57%

Adaptive Optimization Algorithms for Machine Learning

Slavomír Hanzely

专题命中后训练与偏好优化：post-training(abstract)；分类 cs.LG

Comments Dissertation thesis

2304.12579 2023-11-01 cs.LG 57%

Learning Trajectories are Generalization Indicators

Jingwen Fu, Zhizheng Zhang, Dacheng Yin, Yan Lu, Nanning Zheng

专题命中后训练与偏好优化：post-training(abstract)；分类 cs.LG

2310.19733 2023-10-31 cs.LG cs.CR 57%

Differentially Private Reward Estimation with Preference Feedback

Sayak Ray Chowdhury, Xingyu Zhou, Nagarajan Natarajan

专题命中后训练与偏好优化：RLHF(abstract)；分类 cs.LG

2106.11753 2023-10-24 cs.LG cs.NA math.NA 57%

Symplectic Learning for Hamiltonian Neural Networks

Marco David, Florian Méhats

专题命中后训练与偏好优化：post-training(abstract)；分类 cs.LG

Comments 10 pages, 4 figures; Source code, datasets and pre-trained models available at https://github.com/SpaceAbleOrg/symplectic-hnn

Journal ref Journal of Computational Physics (2023), vol. 494, 112495

1. 后训练与偏好优化 4541 篇

MM-PhyRLHF: Reinforcement Learning Framework for Multimodal Physics Question-Answering

Combining Theory of Mind and Kindness for Self-Supervised Human-AI Alignment

Understanding and Minimising Outlier Features in Neural Network Training

Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization

Towards Croppable Implicit Neural Representations

Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment

Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback

Projected Stochastic Gradient Descent with Quantum Annealed Binary Gradients

Sequential Bayesian Neural Subnetwork Ensembles

How Transformers Utilize Multi-Head Attention in In-Context Learning? A Case Study on Sparse Linear Regression

Unified Classification and Rejection: A One-versus-All Framework

DUPLEX: Dual GAT for Complex Embedding of Directed Graphs

A Minimaximalist Approach to Reinforcement Learning from Human Feedback

Multi-objective Reinforcement learning from AI Feedback

Distributional Preference Alignment of LLMs via Optimal Transport

VNN: Verification-Friendly Neural Networks with Hard Robustness Guarantees

Quality Diversity through Human Feedback: Towards Open-Ended Diversity-Driven Optimization

Pi-DUAL: Using Privileged Information to Distinguish Clean from Noisy Labels

PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback

Enhancing Image Caption Generation Using Reinforcement Learning with Human Feedback

On the Limitations of Temperature Scaling for Distributions with Overlaps

MusicRL: Aligning Music Generation to Human Preferences

AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model

A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models

Age Effects on Decision-Making, Drift Diffusion Model

Reinforcement Learning from Statistical Feedback: the Journey from AB Testing to ANT Testing

Adaptive Optimization Algorithms for Machine Learning

Learning Trajectories are Generalization Indicators

Differentially Private Reward Estimation with Preference Feedback

Symplectic Learning for Hamiltonian Neural Networks