Very well said Super important to engineer features to build best quality models
MACHINE LEARNING
-
Distill Whisper Reduces Hallucination Errors in Long Audio Transcription
By
–
Distill Whisper exhibits fewer 'hallucination errors' in transcribing long audio, crucial for customer service and accessibility. Its detailed training underscores the efforts to enhance AI efficiency.
-
Distill Whisper: 99% Accuracy with 2% Data for Real-Time Voice AI
By
–
Distill Whisper uses knowledge distillation to train a smaller model to achieve 99% accuracy of a larger one with 2% data, aiming for real-time AI voice applications without delays.
-
Pearl: Production-Ready RL Agent Software Package Released
By
–
9/ Pearl – introduces a new production-ready RL agent software package that enables researchers and practitioners to develop RL AI agents that adapt to environments with limited observability, sparse feedback, and high stochasticity.
-
Quip: 2-Bit Quantization for Large Language Models
By
–
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.
-
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.
-
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.
-
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.
-
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.
-
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.