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
…
@dair_ai
-
Top Machine Learning Papers of the Week: LongLoRA, AlphaMissense
By
–
-
AlphaMissense: AI Model Classifies Genetic Disease Variants
By
–
1/ AlphaMissense – an AI model classifying missense variants to help pinpoint the cause of diseases; used to develop a catalogue of genetic mutations; it can categorize 89% of all 71 mil missense variants as either likely pathogenic or likely benign.https://t.co/TIYUbN4hYu
— DAIR.AI (@dair_ai) 24 septembre 20231/ AlphaMissense – an AI model classifying missense variants to help pinpoint the cause of diseases; used to develop a catalogue of genetic mutations; it can categorize 89% of all 71 mil missense variants as either likely pathogenic or likely benign.
-
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.
-
MAmmoTH: Open-Source LLMs for Mathematical Problem-Solving
By
–
10/ MAmmoTH – a series of open-source LLMs tailored for general math problem-solving; the models are trained on a curated instruction tuning dataset and outperform existing open-source models on several mathematical reasoning datasets.
-
Radiology-Llama2: Specialized LLM for Medical Imaging
By
–
8/ Radiology-Llama2: Best-in-Class LLM for Radiology – presents an LLM based on Llama 2 tailored for radiology; it's tuned on a large dataset of radiology reports to generate coherent and clinically useful impressions from radiology findings.
-
ChatDev: AI-Powered Software Development in Under Seven Minutes
By
–
9/ ChatDev – a virtual chat-powered software development company mirroring the waterfall model; shows efficacy in software generation, even completing the entire software development process in less than seven minutes for less than one dollar.
-
Open-source library for building autonomous language agents
By
–
7/ Agents – an open-source library for building autonomous language agents including support for features like planning, memory, tool usage, multi-agent communication, and more.
-
Quadrupedal Robot Learns Parkour via Vision-Based Policy Transfer
By
–
5/ Robot Parkour Learning – presents a system for learning end-to-end vision-based parkour policy which is transferred to a quadrupedal robot using its ecocentric depth camera.https://t.co/6720eLUt7w
— DAIR.AI (@dair_ai) 17 septembre 20235/ Robot Parkour Learning – presents a system for learning end-to-end vision-based parkour policy which is transferred to a quadrupedal robot using its ecocentric depth camera.
-
LLMs Self-Align Without Finetuning via Self-Boosting
By
–
4/ LLMs Can Align Themselves without Finetuning? – discovers that by integrating self-evaluation and rewind mechanisms, unaligned LLMs can directly produce responses consistent with human preferences via self-boosting.
-
Survey of Hallucination Phenomena in Large Language Models
By
–
6/ A Survey of Hallucination in LLMs – classifies different types of hallucination phenomena and provides evaluation criteria for assessing hallucination along with mitigation strategies.