Daily Papers of 2023-05-29
- Break-A-Scene: Extracting Multiple Concepts from a Single Image 8 upvotes, #1 of 2023-05-29
- Role-Play with Large Language Models 5 upvotes, #2 of 2023-05-29
- Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer 5 upvotes, #2 of 2023-05-29
- ControlVideo: Adding Conditional Control for One Shot Text-to-Video Editing 5 upvotes, #2 of 2023-05-29
- Think Before You Act: Decision Transformers with Internal Working Memory 4 upvotes, #5 of 2023-05-29
- PandaGPT: One Model To Instruction-Follow Them All 4 upvotes, #5 of 2023-05-29
- DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models 4 upvotes, #5 of 2023-05-29
- Training Socially Aligned Language Models in Simulated Human Society 4 upvotes, #5 of 2023-05-29
- Mindstorms in Natural Language-Based Societies of Mind 4 upvotes, #5 of 2023-05-29
- Large Language Models as Tool Makers 4 upvotes, #5 of 2023-05-29
- Lexinvariant Language Models 2 upvotes, #11 of 2023-05-29
- Randomized Positional Encodings Boost Length Generalization of Transformers 2 upvotes, #11 of 2023-05-29
- Playing repeated games with Large Language Models 2 upvotes, #11 of 2023-05-29
- MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies 2 upvotes, #11 of 2023-05-29
- Three Towers: Flexible Contrastive Learning with Pretrained Image Models 2 upvotes, #11 of 2023-05-29
- OlaGPT: Empowering LLMs With Human-like Problem-Solving Abilities 1 upvotes, #16 of 2023-05-29
- ZeroAvatar: Zero-shot 3D Avatar Generation from a Single Image 1 upvotes, #16 of 2023-05-29
- Impossible Distillation: from Low-Quality Model to High-Quality Dataset & Model for Summarization and Paraphrasing 1 upvotes, #16 of 2023-05-29
- A Closer Look at In-Context Learning under Distribution Shifts 1 upvotes, #16 of 2023-05-29
- Backpack Language Models 1 upvotes, #16 of 2023-05-29
- Do GPTs Produce Less Literal Translations? 1 upvotes, #16 of 2023-05-29
Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.