10/ KOSMOS-2.5 – a multimodal model for machine reading of text-intensive images capable of document-level text generation and image-to-markdown text generation.
LLMS
-
Compositional Foundation Models for Long-Horizon Goals
By
–
8/ Compositional Foundation Models – proposes foundation models that leverage multiple expert foundation models trained on language, vision, and action data to solve long-horizon goals.
-
LMSYS-Chat-1M: 1M Conversations Dataset with 25 LLMs
By
–
6/ LMSYS-Chat-1M – a large-scale dataset containing 1 million real-world conversations with 25 state-of-the-art LLM; it is collected from 210K unique IP addresses on the Vincuna demo and Chatbot Arena website.
-
Language Modeling as Compression: LLM Prediction Capabilities
By
–
7/ Language Modeling is Compression – evaluates the compression capabilities of LLMs; investigates how and why compression and prediction are equivalent; shows that LLMs are powerful general-purpose compressors due to their in-context learning abilities.
-
LLMs for Structured Data Generation: Fine-tuning Approach
By
–
5/ LLMs for Generating Structured Data – studies the use of LLMs for generating complex structured data; proposes a structure-aware fine-tuning method, applied to Llama-7B, which significantly outperform other model like GPT-3.5/4 and Vicuna-13B.
-
Contrastive Decoding Improves LLM Reasoning Performance
By
–
3/ Contrastive Decoding Improves Reasoning in Large Language Models – shows that contrastive decoding leads Llama-65B to outperform Llama 2 and other models on commonsense reasoning and reasoning benchmarks.
-
Top Machine Learning Papers of the Week: LongLoRA, AlphaMissense
By
–
Top ML Papers of the Week (Sep 18 – Sep 24): – LongLoRA
– AlphaMissense
– Chain-of-Verification
– LLMs for IT Operations
– Language Modeling is Compression
– LLMs for Generating Structured Data
… -
Chain-of-Verification Reduces LLM Hallucinations Through Deliberation
By
–
2/ Chain-of-Verification reduces Hallucination in LLMs – a method to enable LLMs to "deliberate" on responses to correct mistakes.
-
BERT Enhanced Versions: Techno-Babble Without Real Solutions
By
–
Again: obvious need does not mean that synthetic text extruding machines provide a solution. "Enhanced versions of BERT" is so much techno-babble.
-
Python ML LLMs tutorials shared daily by Akshay Pachaar
By
–
I hope you learned something new today! If you Enjoyed reading this & are interested in – Python – ML/MLOps – CV/NLP – LLMs – AI Engineering Find me → @akshay_pachaar Everyday, I share tutorials on the above topics! Thanks for reading!