10/ Quip – compresses trained model weights into a lower precision format; combines lattice codebooks with incoherence processing to create 2 bit quantized models; significantly closes the gap between 2 bit quantized LLMs and unquantized 16 bit models.
@dair_ai
-
Self-Training LLMs: Reducing Dependence on Human-Generated Data
By
–
7/ Beyond Human Data for LLMs – an approach for self-training with feedback that substantially reduces dependence on human-generated data; the model-generated data combined with a reward function improves the performance of LLMs on problem-solving tasks.
-
Gaussian-SLAM: Neural RGBD Method for Photorealistic Scene Reconstruction
By
–
8/ Gaussian-SLAM – a neural RGBD SLAM method capable of photorealistically reconstructing real-world scenes without compromising speed and efficiency.https://t.co/HqggU9MvOV
— DAIR.AI (@dair_ai) 17 décembre 20238/ Gaussian-SLAM – a neural RGBD SLAM method capable of photorealistically reconstructing real-world scenes without compromising speed and efficiency.
-
LLMs in Medicine: Comprehensive Survey of Applications and Challenges
By
–
6/ LLMs in Medicine – a comprehensive survey (analyzing 300+ papers) on LLMs in medicine; includes an overview of the principles, applications, and challenges faced by LLMs in medicine.
-
Mathematical LLMs: Progress in Problem-Solving and Theorem Proving
By
–
4/ Mathematical LLMs – a survey on the progress of LLMs on mathematical tasks; covers papers and resources on LLM research around prompting techniques and tasks such as math word problem-solving and theorem proving.
-
LLM360: Transparent Open-Source Large Language Model Training
By
–
5/ Towards Fully Transparent Open-Source LLMs – proposes LLM360 to support open and collaborative AI research by making the end-to-end LLM training process transparent and reproducible.
-
Weak-to-Strong Generalization: Eliciting Full Capabilities of Strong Models
By
–
2/ Weak-to-strong Generalization – studies if weak model supervision can elicit the full capabilities of stronger models; when naively fine-tuning strong pretrained models on weak model generated labels they can perform better than their weak supervisors.
-
Audiobox: Unified Flow-Matching Model for Audio Generation
By
–
3/ Audiobox – a unified model based on flow-matching capable of generating various audio modalities; designs description-based and example-based prompting to enhance controllability and unify speech and sound generation paradigms.https://t.co/OcXaDuRU6j
— DAIR.AI (@dair_ai) 17 décembre 20233/ Audiobox – a unified model based on flow-matching capable of generating various audio modalities; designs description-based and example-based prompting to enhance controllability and unify speech and sound generation paradigms.
-
LLMs Discover New Solutions in Mathematical Sciences
By
–
1/ LLMs for Discoveries in Mathematical Sciences – uses LLMs to search for new solutions in mathematics & computer science.https://t.co/2gCvLQtA2l
— DAIR.AI (@dair_ai) 17 décembre 20231/ LLMs for Discoveries in Mathematical Sciences – uses LLMs to search for new solutions in mathematics & computer science.
-
Top ML Papers of the Week: SLAM, LLMs, Medical AI
By
–
The Top ML Papers of the Week (Dec 11 – Dec 17): – Gaussian-SLAM
– LLMs in Medicine
– Mathematical LLMs
– Beyond Human Data for LLMs
– Weak-to-strong Generalization
– Towards Fully Transparent Open-Source LLM
…