Attention Is All You Need (lemmy.intai.tech)
arxiv.org/pdf/1706.03762.pdf...
Attention Is Off By One (www.evanmiller.org)
Large Language Models as General Pattern Machines (lemmy.intai.tech)
Large Language Models as General Pattern Machines...
ChatGPT an ENFJ, Bard an ISTJ: Empirical Study on Personalities of Large Language Models (lemmy.intai.tech)
Title: ChatGPT an ENFJ, Bard an ISTJ: Empirical Study on Personalities of Large Language Models...
Language models can explain neurons in language models (openai.com)
LMFlow - An Extensible Toolkit for Finetuning and Inference of Large Foundation Models (lemmy.intai.tech)
[Tweet](https://twitter.com/SourabhAgr03/status/1671884579203063812}...
AI that uses sketches to detect objects within an image could boost tumor detection, and search for rare bird species (www.sciencedaily.com)
Textbooks Are All You Need (lemmy.intai.tech)
Found here...
Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4 (lemmy.intai.tech)
https://arxiv.org/pdf/2305.00118.pdf
You all heard about the new paper claiming that you can train on 1000 samples & nearly match GPT-4. The public FOMO nowadays often take such claims out of context for papers like this one and cast a
Original LIMA Paper...
Deep learning: the unintuitive relationship between overparameterization, overfitting and generalization (brain.harvard.edu)
cross-posted from: https://sh.itjust.works/post/225391...
What's the kernel trick? (explanation) (eranraviv.com)
cross-posted from: https://sh.itjust.works/post/223997...
Inverse Scaling - When Bigger Isn’t Better (lemmy.intai.tech)
https://arxiv.org/pdf/2306.09479.pdf
CAJun - Continuous Adaptive Jumping using a Learned Centroidal Controller (lemmy.intai.tech)
https://twitter.com/_akhaliq/status/1670650476004556800 https://arxiv.org/pdf/2306.09557.pdf
OCTScenes - A Versatile Real-World Dataset of Tabletop Scenes for Object-Centric Learning (lemmy.intai.tech)
https://arxiv.org/pdf/2306.09682.pdf
Demystifying GPT Self-Repair for Code Generation (lemmy.intai.tech)
https://arxiv.org/pdf/2306.09896.pdf
Chatbots to ChatGPT in a Cybersecurity Space - Evolution, Vulnerabilities, Attacks, Challenges, and Future Recommendations (lemmy.intai.tech)
https://arxiv.org/pdf/2306.09255.pdf
Large language models predict human sensory judgments across six modalities (lemmy.intai.tech)
https://arxiv.org/pdf/2302.01308.pdf...
LIMA - Less Is More for Alignment (lemmy.intai.tech)
https://arxiv.org/pdf/2305.11206.pdf
Unifying Large Language Models and Knowledge Graphs: A Roadmap (lemmy.intai.tech)
https://arxiv.org/pdf/2306.08302.pdf
Orca - Progressive Learning from Complex Explanation Traces of GPT-4 (lemmy.intai.tech)
Paper Title: Orca: Progressive Learning from Complex Explanation Traces of GPT-4...
From Pixels to UI Actions - Learning to Follow Instructions via Graphical User Interfaces (lemmy.intai.tech)
Title: From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces...
Fine-Grained Human Feedback Gives Better Rewards for Language Model Training (lemmy.intai.tech)
The content discusses a proposed method called Fine-Grained Reinforcement Learning from Human Feedback (Fine-Grained RLHF) for improving language model training using fine-grained human feedback. It shows how providing dense rewards after small text segments for specific types of undesired behaviors can enable more effective...
Controlled and compliant AI applications (open.spotify.com)
Daily Papers - Hugging Face (huggingface.co)
https://lemmy.intai.tech/pictrs/image/2467a558-b2c9-48cb-b425-8c157cd6eef5.png
