AI Research
/AgentsGo to topic
MindAgent: Emergent Gaming Interaction
MindAgent: Emergent Gaming Interaction
Prof. Otto NomosMay 27, 2024 ∙ 2 min readAbstract Commentary & RatingA Data Source for Reasoning Embodied Agents
A Data Source for Reasoning Embodied Agents
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & Rating
LASER: LLM Agent with State-Space Exploration for Web Navigation
LASER: LLM Agent with State-Space Exploration for Web Navigation
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingAgents: An Open-source Framework for Autonomous Language Agents
Agents: An Open-source Framework for Autonomous Language Agents
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingModelScope-Agent: Building Your Customizable Agent System with Open-source Large Language Models
ModelScope-Agent: Building Your Customizable Agent System with Open-source Large Language Models
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingBOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents
BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & Rating
/AlignmentGo to topic
From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models
From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingTrustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingSimple synthetic data reduces sycophancy in large language models
Simple synthetic data reduces sycophancy in large language models
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & Rating
/AudioGo to topic
Augmenting text for spoken language understanding with Large Language Models
Augmenting text for spoken language understanding with Large Language Models
Prof. Otto NomosMay 25, 2024 ∙ 2 min readAbstract Commentary & RatingNatural Language Supervision for General-Purpose Audio Representations
Natural Language Supervision for General-Purpose Audio Representations
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingImproving Joint Speech-Text Representations Without Alignment
Improving Joint Speech-Text Representations Without Alignment
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & Rating
/ChatGo to topic
S3-DST: Structured Open-Domain Dialogue Segmentation and State Tracking in the Era of LLMs
S3-DST: Structured Open-Domain Dialogue Segmentation and State Tracking in the Era of LLMs
Prof. Otto NomosMay 25, 2024 ∙ 2 min readAbstract Commentary & RatingInvestigating Answerability of LLMs for Long-Form Question Answering
Investigating Answerability of LLMs for Long-Form Question Answering
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & Rating
SoTaNa: The Open-Source Software Development Assistant
SoTaNa: The Open-Source Software Development Assistant
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingPIPPA: A Partially Synthetic Conversational Dataset
PIPPA: A Partially Synthetic Conversational Dataset
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & Rating
/ClimateGo to topic
/CodeGo to topic
Large Language Models for Compiler Optimization
Large Language Models for Compiler Optimization
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingLLM As DBA
LLM As DBA
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingBioCoder: A Benchmark for Bioinformatics Code Generation with Contextual Pragmatic Knowledge
BioCoder: A Benchmark for Bioinformatics Code Generation with Contextual Pragmatic Knowledge
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingCan Programming Languages Boost Each Other via Instruction Tuning?
Can Programming Languages Boost Each Other via Instruction Tuning?
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingSoTaNa: The Open-Source Software Development Assistant
SoTaNa: The Open-Source Software Development Assistant
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingSolving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification
Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingOctoPack: Instruction Tuning Code Large Language Models
OctoPack: Instruction Tuning Code Large Language Models
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingEnhancing Network Management Using Code Generated by Large Language Models
Enhancing Network Management Using Code Generated by Large Language Models
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & Rating
/CommentaryGo to topic
![LoraHub: Efficient Cross-Task Generalization Via Dynamic LoRA Composition [Commentary]](/_next/image?url=https%3A%2F%2Fwww.datocms-assets.com%2F101962%2F1690946901-abr8-img1.png&w=3840&q=75)
LoraHub: Efficient Cross-Task Generalization Via Dynamic LoRA Composition [Commentary]
LoraHub: Efficient Cross-Task Generalization Via Dynamic LoRA Composition [Commentary]
Prof. Otto NomosOct 02, 2023 ∙ 8 min readExplore the dynamic composition of LoRA modules with LoraHub for adaptable LLM performance. Dive into problem statements, methodology, evaluation, and more.![ToolLLM: Facilitating Large Language Models To Master 16000+ Real-World APIs [Commentary]](/_next/image?url=https%3A%2F%2Fwww.datocms-assets.com%2F101962%2F1690949823-screenshot-2023-08-02-at-12-14-28-am.png&w=3840&q=75)
ToolLLM: Facilitating Large Language Models To Master 16000+ Real-World APIs [Commentary]
ToolLLM: Facilitating Large Language Models To Master 16000+ Real-World APIs [Commentary]
Prof. Otto NomosOct 02, 2023 ∙ 4 min readExplore the power of Large Language Models (LLMs) in API interaction with our summary of 'Tool LLM'
/CompressionGo to topic
Language Modeling Is Compression
Language Modeling Is Compression
Prof. Otto NomosMay 25, 2024 ∙ 2 min readAbstract Commentary & RatingA Survey on Model Compression for Large Language Models
A Survey on Model Compression for Large Language Models
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & Rating
/DataGo to topic
SlimPajama-DC: Understanding Data Combinations for LLM Training
SlimPajama-DC: Understanding Data Combinations for LLM Training
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingCulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages
CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingA Data Source for Reasoning Embodied Agents
A Data Source for Reasoning Embodied Agents
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingWhen Less is More: Investigating Data Pruning for Pretraining LLMs at Scale
When Less is More: Investigating Data Pruning for Pretraining LLMs at Scale
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingPlatypus: Quick, Cheap, and Powerful Refinement of LLMs
Platypus: Quick, Cheap, and Powerful Refinement of LLMs
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingPIPPA: A Partially Synthetic Conversational Dataset
PIPPA: A Partially Synthetic Conversational Dataset
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingShepherd: A Critic for Language Model Generation
Shepherd: A Critic for Language Model Generation
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & Rating
/DiffusionGo to topic
PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solvers
PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solvers
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingFLIRT: Feedback Loop In-context Red Teaming
FLIRT: Feedback Loop In-context Red Teaming
Prof. Otto NomosOct 02, 2023 ∙ 1 min readAbstract Commentary & Rating
/EdgeGo to topic
/EntityGo to topic
LMDX: Language Model-based Document Information Extraction and Localization
LMDX: Language Model-based Document Information Extraction and Localization
Prof. Otto NomosMay 24, 2024 ∙ 2 min readAbstract Commentary & RatingLeveraging Contextual Information for Effective Entity Salience Detection
Leveraging Contextual Information for Effective Entity Salience Detection
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & Rating
/EvaluationGo to topic
Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation?
Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation?
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingThe Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants
The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingWeatherBench 2: A benchmark for the next generation of data-driven global weather models
WeatherBench 2: A benchmark for the next generation of data-driven global weather models
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingTrustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & Rating
/FinanceGo to topic
/Fine-tuningGo to topic
Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference Using Sorted Fine-Tuning (SoFT)
Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference Using Sorted Fine-Tuning (SoFT)
Prof. Otto NomosMay 27, 2024 ∙ 2 min readAbstract Commentary & RatingLeveraging Contextual Information for Effective Entity Salience Detection
Leveraging Contextual Information for Effective Entity Salience Detection
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingFIAT: Fusing learning paradigms with Instruction-Accelerated Tuning
FIAT: Fusing learning paradigms with Instruction-Accelerated Tuning
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingPlatypus: Quick, Cheap, and Powerful Refinement of LLMs
Platypus: Quick, Cheap, and Powerful Refinement of LLMs
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & Rating
/GamingGo to topic
/HallucinationGo to topic
Chain-of-Verification Reduces Hallucination in Large Language Models
Chain-of-Verification Reduces Hallucination in Large Language Models
Prof. Otto NomosMay 24, 2024 ∙ 1 min readAbstract Commentary & RatingLMDX: Language Model-based Document Information Extraction and Localization
LMDX: Language Model-based Document Information Extraction and Localization
Prof. Otto NomosMay 24, 2024 ∙ 2 min readAbstract Commentary & Rating
/HealthcareGo to topic
Adapting Large Language Models via Reading Comprehension
Adapting Large Language Models via Reading Comprehension
Prof. Otto NomosMay 27, 2024 ∙ 2 min readAbstract Commentary & RatingClinical Text Summarization: Adapting Large Language Models Can Outperform Human Experts
Clinical Text Summarization: Adapting Large Language Models Can Outperform Human Experts
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingPredicting transcriptional outcomes of novel multigene perturbations with GEARS
Predicting transcriptional outcomes of novel multigene perturbations with GEARS
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingBioCoder: A Benchmark for Bioinformatics Code Generation with Contextual Pragmatic Knowledge
BioCoder: A Benchmark for Bioinformatics Code Generation with Contextual Pragmatic Knowledge
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingMedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records
MedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingOpenProteinSet: Training data for structural biology at scale
OpenProteinSet: Training data for structural biology at scale
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & Rating
/ImageGo to topic
StyleAdapter: A Single-Pass LoRA-Free Model for Stylized Image Generation
StyleAdapter: A Single-Pass LoRA-Free Model for Stylized Image Generation
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingFLIRT: Feedback Loop In-context Red Teaming
FLIRT: Feedback Loop In-context Red Teaming
Prof. Otto NomosOct 02, 2023 ∙ 1 min readAbstract Commentary & Rating
/In-Context LearningGo to topic
Ambiguity-Aware In-Context Learning with Large Language Models
Ambiguity-Aware In-Context Learning with Large Language Models
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingFIAT: Fusing learning paradigms with Instruction-Accelerated Tuning
FIAT: Fusing learning paradigms with Instruction-Accelerated Tuning
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingRAVEN: In-Context Learning with Retrieval Augmented Encoder-Decoder Language Models
RAVEN: In-Context Learning with Retrieval Augmented Encoder-Decoder Language Models
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingCausalLM is not optimal for in-context learning
CausalLM is not optimal for in-context learning
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & Rating
/InferenceGo to topic
/Instruction TuningGo to topic
An Empirical Study of Scaling Instruct-Tuned Large Multimodal Models
An Empirical Study of Scaling Instruct-Tuned Large Multimodal Models
Prof. Otto NomosMay 27, 2024 ∙ 2 min readAbstract Commentary & RatingXGen-7B Technical Report
XGen-7B Technical Report
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingSelf-Alignment with Instruction Backtranslation
Self-Alignment with Instruction Backtranslation
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingCan Programming Languages Boost Each Other via Instruction Tuning?
Can Programming Languages Boost Each Other via Instruction Tuning?
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingMedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records
MedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingOctoPack: Instruction Tuning Code Large Language Models
OctoPack: Instruction Tuning Code Large Language Models
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingSelf-Alignment with Instruction Backtranslation
Self-Alignment with Instruction Backtranslation
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & Rating
/InterpretabilityGo to topic
/LegalGo to topic
Adapting Large Language Models via Reading Comprehension
Adapting Large Language Models via Reading Comprehension
Prof. Otto NomosMay 27, 2024 ∙ 2 min readAbstract Commentary & RatingSILO Language Models: Isolating Legal Risk In a Nonparametric Datastore
SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & Rating
/LLMGo to topic
Adapting Large Language Models via Reading Comprehension
Adapting Large Language Models via Reading Comprehension
Prof. Otto NomosMay 27, 2024 ∙ 2 min readAbstract Commentary & RatingOpenBA: An Open-sourced 15B Bilingual Asymmetric seq2seq Model Pre-trained from Scratch
OpenBA: An Open-sourced 15B Bilingual Asymmetric seq2seq Model Pre-trained from Scratch
Prof. Otto NomosMay 27, 2024 ∙ 2 min readAbstract Commentary & RatingPDFTriage: Question Answering over Long, Structured Documents
PDFTriage: Question Answering over Long, Structured Documents
Prof. Otto NomosMay 27, 2024 ∙ 2 min readAbstract Commentary & RatingSorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference Using Sorted Fine-Tuning (SoFT)
Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference Using Sorted Fine-Tuning (SoFT)
Prof. Otto NomosMay 27, 2024 ∙ 2 min readAbstract Commentary & RatingAn Empirical Study of Scaling Instruct-Tuned Large Multimodal Models
An Empirical Study of Scaling Instruct-Tuned Large Multimodal Models
Prof. Otto NomosMay 27, 2024 ∙ 2 min readAbstract Commentary & RatingMindAgent: Emergent Gaming Interaction
MindAgent: Emergent Gaming Interaction
Prof. Otto NomosMay 27, 2024 ∙ 2 min readAbstract Commentary & RatingStruc-Bench: Are Large Language Models Really Good at Generating Complex Structured Data?
Struc-Bench: Are Large Language Models Really Good at Generating Complex Structured Data?
Prof. Otto NomosMay 25, 2024 ∙ 2 min readAbstract Commentary & RatingRecovering from Privacy-Preserving Masking with Large Language Models
Recovering from Privacy-Preserving Masking with Large Language Models
Prof. Otto NomosMay 25, 2024 ∙ 2 min readAbstract Commentary & RatingS3-DST: Structured Open-Domain Dialogue Segmentation and State Tracking in the Era of LLMs
S3-DST: Structured Open-Domain Dialogue Segmentation and State Tracking in the Era of LLMs
Prof. Otto NomosMay 25, 2024 ∙ 2 min readAbstract Commentary & RatingAugmenting text for spoken language understanding with Large Language Models
Augmenting text for spoken language understanding with Large Language Models
Prof. Otto NomosMay 25, 2024 ∙ 2 min readAbstract Commentary & RatingLanguage Modeling Is Compression
Language Modeling Is Compression
Prof. Otto NomosMay 25, 2024 ∙ 2 min readAbstract Commentary & RatingBaichuan 2: Open Large-scale Language Models
Baichuan 2: Open Large-scale Language Models
Prof. Otto NomosMay 24, 2024 ∙ 2 min readAbstract Commentary & RatingStabilizing RLHF through Advantage Model and Selective Rehearsal
Stabilizing RLHF through Advantage Model and Selective Rehearsal
Prof. Otto NomosMay 24, 2024 ∙ 2 min readAbstract Commentary & RatingChain-of-Verification Reduces Hallucination in Large Language Models
Chain-of-Verification Reduces Hallucination in Large Language Models
Prof. Otto NomosMay 24, 2024 ∙ 1 min readAbstract Commentary & RatingLMDX: Language Model-based Document Information Extraction and Localization
LMDX: Language Model-based Document Information Extraction and Localization
Prof. Otto NomosMay 24, 2024 ∙ 2 min readAbstract Commentary & RatingSlimPajama-DC: Understanding Data Combinations for LLM Training
SlimPajama-DC: Understanding Data Combinations for LLM Training
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingContrastive Decoding Improves Reasoning in Large Language Models
Contrastive Decoding Improves Reasoning in Large Language Models
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingCulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages
CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingA Data Source for Reasoning Embodied Agents
A Data Source for Reasoning Embodied Agents
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingLeveraging Contextual Information for Effective Entity Salience Detection
Leveraging Contextual Information for Effective Entity Salience Detection
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingLASER: LLM Agent with State-Space Exploration for Web Navigation
LASER: LLM Agent with State-Space Exploration for Web Navigation
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingSparse Autoencoders Find Highly Interpretable Features in Language Models
Sparse Autoencoders Find Highly Interpretable Features in Language Models
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingInvestigating Answerability of LLMs for Long-Form Question Answering
Investigating Answerability of LLMs for Long-Form Question Answering
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingScaling Laws for Sparsely-Connected Foundation Models
Scaling Laws for Sparsely-Connected Foundation Models
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingConnecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers
Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingAmbiguity-Aware In-Context Learning with Large Language Models
Ambiguity-Aware In-Context Learning with Large Language Models
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingAre Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation?
Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation?
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingClinical Text Summarization: Adapting Large Language Models Can Outperform Human Experts
Clinical Text Summarization: Adapting Large Language Models Can Outperform Human Experts
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingAgents: An Open-source Framework for Autonomous Language Agents
Agents: An Open-source Framework for Autonomous Language Agents
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingStatistical Rejection Sampling Improves Preference Optimization
Statistical Rejection Sampling Improves Preference Optimization
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingLarge Language Models for Compiler Optimization
Large Language Models for Compiler Optimization
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingAstroLLaMA: Towards Specialized Foundation Models in Astronomy
AstroLLaMA: Towards Specialized Foundation Models in Astronomy
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingLarge Language Model for Science: A Study on P vs. NP
Large Language Model for Science: A Study on P vs. NP
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingEfficient Memory Management for Large Language Model Serving with PagedAttention
Efficient Memory Management for Large Language Model Serving with PagedAttention
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingFIAT: Fusing learning paradigms with Instruction-Accelerated Tuning
FIAT: Fusing learning paradigms with Instruction-Accelerated Tuning
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingOptimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs
Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingWhen Less is More: Investigating Data Pruning for Pretraining LLMs at Scale
When Less is More: Investigating Data Pruning for Pretraining LLMs at Scale
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingNeurons in Large Language Models: Dead, N-gram, Positional
Neurons in Large Language Models: Dead, N-gram, Positional
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingTextbooks Are All You Need II: phi-1.5 technical report
Textbooks Are All You Need II: phi-1.5 technical report
Prof. Otto NomosOct 03, 2023 ∙ 3 min readAbstract Commentary & RatingDrugChat: Towards Enabling ChatGPT-Like Capabilities on Drug Molecule Graphs
DrugChat: Towards Enabling ChatGPT-Like Capabilities on Drug Molecule Graphs
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingFrom Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting
From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingXGen-7B Technical Report
XGen-7B Technical Report
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingDoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & Rating
GPT Can Solve Mathematical Problems Without a Calculator
GPT Can Solve Mathematical Problems Without a Calculator
Prof. Otto NomosOct 03, 2023 ∙ 1 min readAbstract Commentary & RatingLarge Language Models as Optimizers
Large Language Models as Optimizers
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingEfficient RLHF: Reducing the Memory Usage of PPO
Efficient RLHF: Reducing the Memory Usage of PPO
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingModelScope-Agent: Building Your Customizable Agent System with Open-source Large Language Models
ModelScope-Agent: Building Your Customizable Agent System with Open-source Large Language Models
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & Rating![Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback [Summary]](/_next/image?url=https%3A%2F%2Fwww.datocms-assets.com%2F101962%2F1690837480-abr6-img1.png&w=3840&q=75)
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback [Summary]
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback [Summary]
Prof. Otto NomosOct 02, 2023 ∙ 8 min readUncover the challenges, limitations, and future of Reinforcement Learning from Human Feedback (RLHF) in AI systems. Explore governance, safety, and more.![Llama 2: Open Foundation and Fine-Tuned Chat Models [Commentary]](/_next/image?url=https%3A%2F%2Fwww.datocms-assets.com%2F101962%2F1690935728-abr7-img1.png&w=3840&q=75)
Llama 2: Open Foundation and Fine-Tuned Chat Models [Commentary]
Llama 2: Open Foundation and Fine-Tuned Chat Models [Commentary]
Prof. Otto NomosOct 02, 2023 ∙ 5 min readDeep dive into Llama 2: Explore the pretraining, fine-tuning, safety measures, and insightful discussions in our comprehensive summary.![Challenges and Applications of Large Language Models [Summary]](/_next/image?url=https%3A%2F%2Fwww.datocms-assets.com%2F101962%2F1690575713-abr-img1.png&w=3840&q=75)
Challenges and Applications of Large Language Models [Summary]
Challenges and Applications of Large Language Models [Summary]
Prof. Otto NomosOct 02, 2023 ∙ 20 min readExplore our summary and key insights of 'Challenges and Applications of Large Language Models', a research paper that delves into the potential, challenges, and applications of LLMs.LoraHub: Efficient Cross-Task Generalization Via Dynamic LoRA Composition [Commentary]
LoraHub: Efficient Cross-Task Generalization Via Dynamic LoRA Composition [Commentary]
Prof. Otto NomosOct 02, 2023 ∙ 8 min readExplore the dynamic composition of LoRA modules with LoraHub for adaptable LLM performance. Dive into problem statements, methodology, evaluation, and more.ToolLLM: Facilitating Large Language Models To Master 16000+ Real-World APIs [Commentary]
ToolLLM: Facilitating Large Language Models To Master 16000+ Real-World APIs [Commentary]
Prof. Otto NomosOct 02, 2023 ∙ 4 min readExplore the power of Large Language Models (LLMs) in API interaction with our summary of 'Tool LLM'FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios
FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingGraph of Thoughts: Solving Elaborate Problems with Large Language Models
Graph of Thoughts: Solving Elaborate Problems with Large Language Models
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingEfficient Guided Generation for Large Language Models
Efficient Guided Generation for Large Language Models
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingPredicting transcriptional outcomes of novel multigene perturbations with GEARS
Predicting transcriptional outcomes of novel multigene perturbations with GEARS
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingA Survey on Model Compression for Large Language Models
A Survey on Model Compression for Large Language Models
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingFrom Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models
From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingLLM As DBA
LLM As DBA
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingSelf-Alignment with Instruction Backtranslation
Self-Alignment with Instruction Backtranslation
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingRLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingLarge Content And Behavior Models To Understand, Simulate, And Optimize Content And Behavior
Large Content And Behavior Models To Understand, Simulate, And Optimize Content And Behavior
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingBioCoder: A Benchmark for Bioinformatics Code Generation with Contextual Pragmatic Knowledge
BioCoder: A Benchmark for Bioinformatics Code Generation with Contextual Pragmatic Knowledge
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingThe Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants
The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingCan Programming Languages Boost Each Other via Instruction Tuning?
Can Programming Languages Boost Each Other via Instruction Tuning?
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingWeatherBench 2: A benchmark for the next generation of data-driven global weather models
WeatherBench 2: A benchmark for the next generation of data-driven global weather models
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingJais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models
Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingMedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records
MedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingSoTaNa: The Open-Source Software Development Assistant
SoTaNa: The Open-Source Software Development Assistant
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingTeach LLMs to Personalize -- An Approach inspired by Writing Education
Teach LLMs to Personalize -- An Approach inspired by Writing Education
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingRAVEN: In-Context Learning with Retrieval Augmented Encoder-Decoder Language Models
RAVEN: In-Context Learning with Retrieval Augmented Encoder-Decoder Language Models
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingSolving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification
Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingThe Devil is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation
The Devil is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingCausalLM is not optimal for in-context learning
CausalLM is not optimal for in-context learning
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingPlatypus: Quick, Cheap, and Powerful Refinement of LLMs
Platypus: Quick, Cheap, and Powerful Refinement of LLMs
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingOctoPack: Instruction Tuning Code Large Language Models
OctoPack: Instruction Tuning Code Large Language Models
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingEnhancing Network Management Using Code Generated by Large Language Models
Enhancing Network Management Using Code Generated by Large Language Models
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingImproving Joint Speech-Text Representations Without Alignment
Improving Joint Speech-Text Representations Without Alignment
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingBOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents
BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingPIPPA: A Partially Synthetic Conversational Dataset
PIPPA: A Partially Synthetic Conversational Dataset
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingSelf-Alignment with Instruction Backtranslation
Self-Alignment with Instruction Backtranslation
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingOpenProteinSet: Training data for structural biology at scale
OpenProteinSet: Training data for structural biology at scale
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingTrustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingAccelerating LLM Inference with Staged Speculative Decoding
Accelerating LLM Inference with Staged Speculative Decoding
Prof. Otto NomosOct 02, 2023 ∙ 1 min readAbstract Commentary & RatingShepherd: A Critic for Language Model Generation
Shepherd: A Critic for Language Model Generation
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingSILO Language Models: Isolating Legal Risk In a Nonparametric Datastore
SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingSimple synthetic data reduces sycophancy in large language models
Simple synthetic data reduces sycophancy in large language models
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & Rating
/LORAGo to topic
StyleAdapter: A Single-Pass LoRA-Free Model for Stylized Image Generation
StyleAdapter: A Single-Pass LoRA-Free Model for Stylized Image Generation
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingLoraHub: Efficient Cross-Task Generalization Via Dynamic LoRA Composition [Commentary]
LoraHub: Efficient Cross-Task Generalization Via Dynamic LoRA Composition [Commentary]
Prof. Otto NomosOct 02, 2023 ∙ 8 min readExplore the dynamic composition of LoRA modules with LoraHub for adaptable LLM performance. Dive into problem statements, methodology, evaluation, and more.Platypus: Quick, Cheap, and Powerful Refinement of LLMs
Platypus: Quick, Cheap, and Powerful Refinement of LLMs
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & Rating
/MathGo to topic
Large Language Model for Science: A Study on P vs. NP
Large Language Model for Science: A Study on P vs. NP
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingGPT Can Solve Mathematical Problems Without a Calculator
GPT Can Solve Mathematical Problems Without a Calculator
Prof. Otto NomosOct 03, 2023 ∙ 1 min readAbstract Commentary & Rating
/MultilingualGo to topic
OpenBA: An Open-sourced 15B Bilingual Asymmetric seq2seq Model Pre-trained from Scratch
OpenBA: An Open-sourced 15B Bilingual Asymmetric seq2seq Model Pre-trained from Scratch
Prof. Otto NomosMay 27, 2024 ∙ 2 min readAbstract Commentary & RatingBaichuan 2: Open Large-scale Language Models
Baichuan 2: Open Large-scale Language Models
Prof. Otto NomosMay 24, 2024 ∙ 2 min readAbstract Commentary & RatingCulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages
CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingAre Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation?
Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation?
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingThe Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants
The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingJais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models
Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingThe Devil is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation
The Devil is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingImproving Joint Speech-Text Representations Without Alignment
Improving Joint Speech-Text Representations Without Alignment
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & Rating
/MultimodalGo to topic
An Empirical Study of Scaling Instruct-Tuned Large Multimodal Models
An Empirical Study of Scaling Instruct-Tuned Large Multimodal Models
Prof. Otto NomosMay 27, 2024 ∙ 2 min readAbstract Commentary & RatingNatural Language Supervision for General-Purpose Audio Representations
Natural Language Supervision for General-Purpose Audio Representations
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingImproving Joint Speech-Text Representations Without Alignment
Improving Joint Speech-Text Representations Without Alignment
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & Rating
/Open SourceGo to topic
/PersonalizationGo to topic
/PrivacyGo to topic
/PromptingGo to topic
Adapting Large Language Models via Reading Comprehension
Adapting Large Language Models via Reading Comprehension
Prof. Otto NomosMay 27, 2024 ∙ 2 min readAbstract Commentary & RatingConnecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers
Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingDrugChat: Towards Enabling ChatGPT-Like Capabilities on Drug Molecule Graphs
DrugChat: Towards Enabling ChatGPT-Like Capabilities on Drug Molecule Graphs
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingFrom Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting
From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingDoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingLarge Language Models as Optimizers
Large Language Models as Optimizers
Prof. Otto NomosOct 03, 2023 ∙ 2 min readAbstract Commentary & RatingGraph of Thoughts: Solving Elaborate Problems with Large Language Models
Graph of Thoughts: Solving Elaborate Problems with Large Language Models
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingSolving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification
Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & RatingThe Devil is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation
The Devil is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation
Prof. Otto NomosOct 02, 2023 ∙ 2 min readAbstract Commentary & Rating
/ReasoningGo to topic
Contrastive Decoding Improves Reasoning in Large Language Models
Contrastive Decoding Improves Reasoning in Large Language Models
Prof. Otto NomosOct 04, 2023 ∙ 2 min readAbstract Commentary & RatingGraph of Thoughts: Solving Elaborate Problems with Large Language Models
Graph of Thoughts: Solving Elaborate Problems with Large Language Models