Writings, Papers and Blogs on Text Models

Apparate: Early-Exit Models for ML Latency and Throughput Optimization – Comparisons | HackerNoon

Authors: (1) Yinwei Dai, Princeton University (Equal contributions); (2) Rui Pan, Princeton University (Equal contributions); (3) Anand Iyer, Georgia Institute of Technology; (4) Ravi Netravali, Georgia Institute of Technology. Table of Links Abstract and 1 Introduction 2 Background and Motivation and 2.1 Model Serving Platforms 2.2 Early-Exit Models 2.3 Challenges 3 Design 3.1 Preparing Models with Early Exits 3.2 Accuracy-Aware Threshold Tuning 3.3 Latency-Focused Ramp Adjustments 4 Implementation 5 Evaluation and 5.1 Methodology 5.2 Overall

Read More »

Human Study Validates GPT-4 Win Rates for TL;DR Summarization | HackerNoon

Authors: (1) Rafael Rafailo, Stanford University and Equal contribution; more junior authors listed earlier; (2) Archit Sharma, Stanford University and Equal contribution; more junior authors listed earlier; (3) Eric Mitchel, Stanford University and Equal contribution; more junior authors listed earlier; (4) Stefano Ermon, CZ Biohub; (5) Christopher D. Manning, Stanford University; (6) Chelsea Finn, Stanford University. Table of Links Abstract and 1. Introduction 2 Related Work 3 Preliminaries 4 Direct Preference Optimization 5 Theoretical Analysis

Read More »

Performance of Best of N Baseline for Various N and Sample Responses and GPT-4 Judgments | HackerNoon

Authors: (1) Rafael Rafailo, Stanford University and Equal contribution; more junior authors listed earlier; (2) Archit Sharma, Stanford University and Equal contribution; more junior authors listed earlier; (3) Eric Mitchel, Stanford University and Equal contribution; more junior authors listed earlier; (4) Stefano Ermon, CZ Biohub; (5) Christopher D. Manning, Stanford University; (6) Chelsea Finn, Stanford University. Table of Links Abstract and 1. Introduction 2 Related Work 3 Preliminaries 4 Direct Preference Optimization 5 Theoretical Analysis

Read More »
Software

The Unlikelihood Baseline in Sentiment Experiments | HackerNoon

Authors: (1) Rafael Rafailo, Stanford University and Equal contribution; more junior authors listed earlier; (2) Archit Sharma, Stanford University and Equal contribution; more junior authors listed earlier; (3) Eric Mitchel, Stanford University and Equal contribution; more junior authors listed earlier; (4) Stefano Ermon, CZ Biohub; (5) Christopher D. Manning, Stanford University; (6) Chelsea Finn, Stanford University.

Read More »

Deriving the DPO Objective Under the Plackett-Luce Model | HackerNoon

Authors: (1) Rafael Rafailo, Stanford University and Equal contribution; more junior authors listed earlier; (2) Archit Sharma, Stanford University and Equal contribution; more junior authors listed earlier; (3) Eric Mitchel, Stanford University and Equal contribution; more junior authors listed earlier; (4) Stefano Ermon, CZ Biohub; (5) Christopher D. Manning, Stanford University; (6) Chelsea Finn, Stanford University. Table of Links Abstract and 1. Introduction 2 Related Work 3 Preliminaries 4 Direct Preference Optimization 5 Theoretical Analysis

Read More »

Deriving the DPO Objective Under the Bradley-Terry Model | HackerNoon

Authors: (1) Rafael Rafailo, Stanford University and Equal contribution; more junior authors listed earlier; (2) Archit Sharma, Stanford University and Equal contribution; more junior authors listed earlier; (3) Eric Mitchel, Stanford University and Equal contribution; more junior authors listed earlier; (4) Stefano Ermon, CZ Biohub; (5) Christopher D. Manning, Stanford University; (6) Chelsea Finn, Stanford University. Table of Links Abstract and 1. Introduction 2 Related Work 3 Preliminaries 4 Direct Preference Optimization 5 Theoretical Analysis

Read More »

Deriving the Optimum of the KL-Constrained Reward Maximization Objective | HackerNoon

Authors: (1) Rafael Rafailo, Stanford University and Equal contribution; more junior authors listed earlier; (2) Archit Sharma, Stanford University and Equal contribution; more junior authors listed earlier; (3) Eric Mitchel, Stanford University and Equal contribution; more junior authors listed earlier; (4) Stefano Ermon, CZ Biohub; (5) Christopher D. Manning, Stanford University; (6) Chelsea Finn, Stanford University. Table of Links Abstract and 1. Introduction 2 Related Work 3 Preliminaries 4 Direct Preference Optimization 5 Theoretical Analysis

Read More »
Software

Behind the Scenes: The Team Behind DPO | HackerNoon

Authors: (1) Rafael Rafailo, Stanford University and Equal contribution; more junior authors listed earlier; (2) Archit Sharma, Stanford University and Equal contribution; more junior authors listed earlier; (3) Eric Mitchel, Stanford University and Equal contribution; more junior authors listed earlier; (4) Stefano Ermon, CZ Biohub; (5) Christopher D. Manning, Stanford University; (6) Chelsea Finn, Stanford University. Table of Links Abstract and 1. Introduction 2 Related Work 3 Preliminaries 4 Direct Preference Optimization 5 Theoretical Analysis

Read More »

GPT-4 vs. Humans: Validating AI Judgment in Language Model Training | HackerNoon

Authors: (1) Rafael Rafailo, Stanford University and Equal contribution; more junior authors listed earlier; (2) Archit Sharma, Stanford University and Equal contribution; more junior authors listed earlier; (3) Eric Mitchel, Stanford University and Equal contribution; more junior authors listed earlier; (4) Stefano Ermon, CZ Biohub; (5) Christopher D. Manning, Stanford University; (6) Chelsea Finn, Stanford University. Table of Links Abstract and 1. Introduction 2 Related Work 3 Preliminaries 4 Direct Preference Optimization 5 Theoretical Analysis

Read More »
Software

NeRF Editing and Inpainting Techniques: Experiments and Qualitative results | HackerNoon

Table of Links Abstract and 1. Introduction 2. Related Work 2.1. NeRF Editing and 2.2. Inpainting Techniques 2.3. Text-Guided Visual Content Generation 3. Method 3.1. Training View Pre-processing 3.2. Progressive Training 3.3. 4D Extension 4. Experiments and 4.1. Experimental Setups 4.2. Ablation and comparison 5. Conclusion and 6. References 4. Experiments For our experiments, we select from dynamic scenes in the Nvidia Dynamic Scenes Dataset [35]. Scenes in this dataset are captured using a sparse

Read More »