Models
Datasets
Spaces
Docs
Enterprise
Pricing
Log In
Sign Up

Collections

Discover the best community collections!

Collections including paper arxiv:2405.08448

Reinforcement Learning (RL / RLHF)

RLHF Workflow: From Reward Modeling to Online RLHF

Paper • 2405.07863 • Published May 13, 2024 • 71
Understanding and Diagnosing Deep Reinforcement Learning

Paper • 2406.16979 • Published Jun 23, 2024 • 10
Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences

Paper • 2404.03715 • Published Apr 4, 2024 • 62
Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning

Paper • 2407.00617 • Published Jun 30, 2024 • 7

Understanding the performance gap between online and offline alignment algorithms

Paper • 2405.08448 • Published May 14, 2024 • 18
Self-Exploring Language Models: Active Preference Elicitation for Online Alignment

Paper • 2405.19332 • Published May 29, 2024 • 22
Offline Regularised Reinforcement Learning for Large Language Models Alignment

Paper • 2405.19107 • Published May 29, 2024 • 15
Show, Don't Tell: Aligning Language Models with Demonstrated Feedback

Paper • 2406.00888 • Published Jun 2, 2024 • 33

ORPO: Monolithic Preference Optimization without Reference Model

Paper • 2403.07691 • Published Mar 12, 2024 • 72
sDPO: Don't Use Your Data All at Once

Paper • 2403.19270 • Published Mar 28, 2024 • 41
Teaching Large Language Models to Reason with Reinforcement Learning

Paper • 2403.04642 • Published Mar 7, 2024 • 49
Best Practices and Lessons Learned on Synthetic Data for Language Models

Paper • 2404.07503 • Published Apr 11, 2024 • 31

Interesting things.

AtP*: An efficient and scalable method for localizing LLM behaviour to components

Paper • 2403.00745 • Published Mar 1, 2024 • 14
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Paper • 2402.17764 • Published Feb 27, 2024 • 627
MobiLlama: Towards Accurate and Lightweight Fully Transparent GPT

Paper • 2402.16840 • Published Feb 26, 2024 • 25
LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens

Paper • 2402.13753 • Published Feb 21, 2024 • 116

LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models

Paper • 2309.12307 • Published Sep 21, 2023 • 90
NEFTune: Noisy Embeddings Improve Instruction Finetuning

Paper • 2310.05914 • Published Oct 9, 2023 • 14
SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling

Paper • 2312.15166 • Published Dec 23, 2023 • 61
Soaring from 4K to 400K: Extending LLM's Context with Activation Beacon

Paper • 2401.03462 • Published Jan 7, 2024 • 28

reinforcement learning

Understanding the performance gap between online and offline alignment algorithms

Paper • 2405.08448 • Published May 14, 2024 • 18
OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework

Paper • 2405.11143 • Published May 20, 2024 • 41

Foundation AI Papers (II)

Iterative Reasoning Preference Optimization

Paper • 2404.19733 • Published Apr 30, 2024 • 49
Better & Faster Large Language Models via Multi-token Prediction

Paper • 2404.19737 • Published Apr 30, 2024 • 81
ORPO: Monolithic Preference Optimization without Reference Model

Paper • 2403.07691 • Published Mar 12, 2024 • 72
KAN: Kolmogorov-Arnold Networks

Paper • 2404.19756 • Published Apr 30, 2024 • 116

A Critical Evaluation of AI Feedback for Aligning Large Language Models

Paper • 2402.12366 • Published Feb 19, 2024 • 3
Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation

Paper • 2401.08417 • Published Jan 16, 2024 • 37
Insights into Alignment: Evaluating DPO and its Variants Across Multiple Tasks

Paper • 2404.14723 • Published Apr 23, 2024 • 10
Self-Play Preference Optimization for Language Model Alignment

Paper • 2405.00675 • Published May 1, 2024 • 28

EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters

Paper • 2402.04252 • Published Feb 6, 2024 • 29
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models

Paper • 2402.03749 • Published Feb 6, 2024 • 15
ScreenAI: A Vision-Language Model for UI and Infographics Understanding

Paper • 2402.04615 • Published Feb 7, 2024 • 44
EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss

Paper • 2402.05008 • Published Feb 7, 2024 • 23

Reinforcement Learning (RL / RLHF)

RLHF Workflow: From Reward Modeling to Online RLHF

Paper • 2405.07863 • Published May 13, 2024 • 71
Understanding and Diagnosing Deep Reinforcement Learning

Paper • 2406.16979 • Published Jun 23, 2024 • 10
Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences

Paper • 2404.03715 • Published Apr 4, 2024 • 62
Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning

Paper • 2407.00617 • Published Jun 30, 2024 • 7

reinforcement learning

Understanding the performance gap between online and offline alignment algorithms

Paper • 2405.08448 • Published May 14, 2024 • 18
OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework

Paper • 2405.11143 • Published May 20, 2024 • 41

Understanding the performance gap between online and offline alignment algorithms

Paper • 2405.08448 • Published May 14, 2024 • 18
Self-Exploring Language Models: Active Preference Elicitation for Online Alignment

Paper • 2405.19332 • Published May 29, 2024 • 22
Offline Regularised Reinforcement Learning for Large Language Models Alignment

Paper • 2405.19107 • Published May 29, 2024 • 15
Show, Don't Tell: Aligning Language Models with Demonstrated Feedback

Paper • 2406.00888 • Published Jun 2, 2024 • 33

Foundation AI Papers (II)

Iterative Reasoning Preference Optimization

Paper • 2404.19733 • Published Apr 30, 2024 • 49
Better & Faster Large Language Models via Multi-token Prediction

Paper • 2404.19737 • Published Apr 30, 2024 • 81
ORPO: Monolithic Preference Optimization without Reference Model

Paper • 2403.07691 • Published Mar 12, 2024 • 72
KAN: Kolmogorov-Arnold Networks

Paper • 2404.19756 • Published Apr 30, 2024 • 116

ORPO: Monolithic Preference Optimization without Reference Model

Paper • 2403.07691 • Published Mar 12, 2024 • 72
sDPO: Don't Use Your Data All at Once

Paper • 2403.19270 • Published Mar 28, 2024 • 41
Teaching Large Language Models to Reason with Reinforcement Learning

Paper • 2403.04642 • Published Mar 7, 2024 • 49
Best Practices and Lessons Learned on Synthetic Data for Language Models

Paper • 2404.07503 • Published Apr 11, 2024 • 31

A Critical Evaluation of AI Feedback for Aligning Large Language Models

Paper • 2402.12366 • Published Feb 19, 2024 • 3
Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation

Paper • 2401.08417 • Published Jan 16, 2024 • 37
Insights into Alignment: Evaluating DPO and its Variants Across Multiple Tasks

Paper • 2404.14723 • Published Apr 23, 2024 • 10
Self-Play Preference Optimization for Language Model Alignment

Paper • 2405.00675 • Published May 1, 2024 • 28

Interesting things.

AtP*: An efficient and scalable method for localizing LLM behaviour to components

Paper • 2403.00745 • Published Mar 1, 2024 • 14
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Paper • 2402.17764 • Published Feb 27, 2024 • 627
MobiLlama: Towards Accurate and Lightweight Fully Transparent GPT

Paper • 2402.16840 • Published Feb 26, 2024 • 25
LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens

Paper • 2402.13753 • Published Feb 21, 2024 • 116

EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters

Paper • 2402.04252 • Published Feb 6, 2024 • 29
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models

Paper • 2402.03749 • Published Feb 6, 2024 • 15
ScreenAI: A Vision-Language Model for UI and Infographics Understanding

Paper • 2402.04615 • Published Feb 7, 2024 • 44
EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss

Paper • 2402.05008 • Published Feb 7, 2024 • 23

LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models

Paper • 2309.12307 • Published Sep 21, 2023 • 90
NEFTune: Noisy Embeddings Improve Instruction Finetuning

Paper • 2310.05914 • Published Oct 9, 2023 • 14
SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling

Paper • 2312.15166 • Published Dec 23, 2023 • 61
Soaring from 4K to 400K: Extending LLM's Context with Activation Beacon

Paper • 2401.03462 • Published Jan 7, 2024 • 28

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs