Picture for Lifu Tu

Lifu Tu

Unlocking Anticipatory Text Generation: A Constrained Approach for Faithful Decoding with Large Language Models

Add code
Dec 11, 2023
Figure 1 for Unlocking Anticipatory Text Generation: A Constrained Approach for Faithful Decoding with Large Language Models
Figure 2 for Unlocking Anticipatory Text Generation: A Constrained Approach for Faithful Decoding with Large Language Models
Figure 3 for Unlocking Anticipatory Text Generation: A Constrained Approach for Faithful Decoding with Large Language Models
Figure 4 for Unlocking Anticipatory Text Generation: A Constrained Approach for Faithful Decoding with Large Language Models
Viaarxiv icon

XGen-7B Technical Report

Add code
Sep 07, 2023
Figure 1 for XGen-7B Technical Report
Figure 2 for XGen-7B Technical Report
Figure 3 for XGen-7B Technical Report
Figure 4 for XGen-7B Technical Report
Viaarxiv icon

Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning

Add code
Apr 03, 2023
Figure 1 for Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning
Figure 2 for Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning
Figure 3 for Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning
Figure 4 for Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning
Viaarxiv icon

Unsupervised Dense Retrieval Deserves Better Positive Pairs: Scalable Augmentation with Query Extraction and Generation

Add code
Dec 17, 2022
Figure 1 for Unsupervised Dense Retrieval Deserves Better Positive Pairs: Scalable Augmentation with Query Extraction and Generation
Figure 2 for Unsupervised Dense Retrieval Deserves Better Positive Pairs: Scalable Augmentation with Query Extraction and Generation
Figure 3 for Unsupervised Dense Retrieval Deserves Better Positive Pairs: Scalable Augmentation with Query Extraction and Generation
Figure 4 for Unsupervised Dense Retrieval Deserves Better Positive Pairs: Scalable Augmentation with Query Extraction and Generation
Viaarxiv icon

A Conversational Paradigm for Program Synthesis

Add code
Mar 30, 2022
Figure 1 for A Conversational Paradigm for Program Synthesis
Figure 2 for A Conversational Paradigm for Program Synthesis
Figure 3 for A Conversational Paradigm for Program Synthesis
Figure 4 for A Conversational Paradigm for Program Synthesis
Viaarxiv icon

Learning Energy-Based Approximate Inference Networks for Structured Applications in NLP

Add code
Aug 27, 2021
Figure 1 for Learning Energy-Based Approximate Inference Networks for Structured Applications in NLP
Figure 2 for Learning Energy-Based Approximate Inference Networks for Structured Applications in NLP
Figure 3 for Learning Energy-Based Approximate Inference Networks for Structured Applications in NLP
Figure 4 for Learning Energy-Based Approximate Inference Networks for Structured Applications in NLP
Viaarxiv icon

An Exploration of Arbitrary-Order Sequence Labeling via Energy-Based Inference Networks

Add code
Oct 06, 2020
Figure 1 for An Exploration of Arbitrary-Order Sequence Labeling via Energy-Based Inference Networks
Figure 2 for An Exploration of Arbitrary-Order Sequence Labeling via Energy-Based Inference Networks
Figure 3 for An Exploration of Arbitrary-Order Sequence Labeling via Energy-Based Inference Networks
Figure 4 for An Exploration of Arbitrary-Order Sequence Labeling via Energy-Based Inference Networks
Viaarxiv icon

An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models

Add code
Aug 11, 2020
Figure 1 for An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models
Figure 2 for An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models
Figure 3 for An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models
Figure 4 for An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models
Viaarxiv icon

ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation

Add code
May 12, 2020
Figure 1 for ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation
Figure 2 for ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation
Figure 3 for ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation
Figure 4 for ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation
Viaarxiv icon

Improving Joint Training of Inference Networks and Structured Prediction Energy Networks

Add code
Nov 07, 2019
Figure 1 for Improving Joint Training of Inference Networks and Structured Prediction Energy Networks
Figure 2 for Improving Joint Training of Inference Networks and Structured Prediction Energy Networks
Figure 3 for Improving Joint Training of Inference Networks and Structured Prediction Energy Networks
Figure 4 for Improving Joint Training of Inference Networks and Structured Prediction Energy Networks
Viaarxiv icon