research
∙
06/04/2023
Fine-Tuning Language Models with Advantage-Induced Policy Alignment
Reinforcement learning from human feedback (RLHF) has emerged as a relia...
share
research
∙
05/23/2023
i-Code Studio: A Configurable and Composable Framework for Integrative AI
Artificial General Intelligence (AGI) requires comprehensive understandi...
research
∙
05/21/2023
i-Code V2: An Autoregressive Generation Framework over Vision, Language, and Speech Data
The convergence of text, visual, and audio data is a key step towards hu...
research
∙
05/19/2023
Any-to-Any Generation via Composable Diffusion
We present Composable Diffusion (CoDi), a novel generative model capable...
research
∙
05/15/2023
CompSuite: A Dataset of Java Library Upgrade Incompatibility Issues
Modern software systems heavily rely on external libraries developed by ...
research
∙
05/04/2023
Automatic Prompt Optimization with "Gradient Descent" and Beam Search
Large Language Models (LLMs) have shown impressive performance as genera...
research
∙
12/19/2022
APOLLO: A Simple Approach for Adaptive Pretraining of Language Models for Logical Reasoning
Logical reasoning of text is an important ability that requires understa...
research
∙
11/29/2022
Improving Commonsense in Vision-Language Models via Knowledge Graph Riddles
This paper focuses on analyzing and improving the commonsense ability of...
research
∙
11/15/2022
Empowering Language Models with Knowledge Graph Reasoning for Question Answering
Answering open-domain questions requires world knowledge about in-contex...
research
∙
10/23/2022
Retrieval Augmentation for Commonsense Reasoning: A Unified Approach
A common thread of retrieval-augmented methods in the existing literatur...
research
∙
10/23/2022
Tail Batch Sampling: Approximating Global Contrastive Losses as Optimization over Batch Assignments
Contrastive Learning has recently achieved state-of-the-art performance ...
research
∙
10/07/2022
A Unified Encoder-Decoder Framework with Entity Memory
Entities, as important carriers of real-world knowledge, play a key role...
research
∙
10/06/2022
FAST: Improving Controllability for Text Generation with Feedback Aware Self-Training
Controllable text generation systems often leverage control codes to dir...
research
∙
09/21/2022
Generate rather than Retrieve: Large Language Models are Strong Context Generators
Knowledge-intensive tasks, such as open-domain question answering (QA), ...
research
∙
06/02/2022
REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering
This paper revisits visual representation in knowledge-based visual ques...
research
∙
05/25/2022
Leveraging Locality in Abstractive Text Summarization
Despite the successes of neural attention models for natural language ge...
research
∙
05/22/2022
Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners
The goal of this work is to build flexible video-language models that ca...
research
∙
05/18/2022
Automatic Rule Induction for Efficient Semi-Supervised Learning
Semi-supervised learning has shown promise in allowing NLP models to gen...
research
∙
05/03/2022
i-Code: An Integrative and Composable Multimodal Learning Framework
Human intelligence is multimodal; we integrate visual, linguistic, and a...
research
∙
04/13/2022
Impossible Triangle: What's Next for Pre-trained Language Models?
Recent development of large-scale pre-trained language models (PLM) have...
research
∙
03/14/2022
Leveraging Visual Knowledge in Language Tasks: An Empirical Study on Intermediate Pre-training for Cross-modal Knowledge Transfer
Pre-trained language models are still far from human performance in task...
research
∙
03/14/2022
Diversifying Content Generation for Commonsense Reasoning with Mixture of Knowledge Graph Experts
Generative commonsense reasoning (GCR) in natural language is to reason ...
research
∙
02/18/2022
SapientML: Synthesizing Machine Learning Pipelines by Learning from Human-Written Solutions
Automatic machine learning, or AutoML, holds the promise of truly democr...
research
∙
01/13/2022
CLIP-Event: Connecting Text and Images with Event Structures
Vision-language (V+L) pretraining models have achieved great success in ...
research
∙
12/08/2021
MLP Architectures for Vision-and-Language Modeling: An Empirical Study
We initiate the first empirical study on the use of MLP architectures fo...
research
∙
12/06/2021
Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention
Most of today's AI systems focus on using self-attention mechanisms and ...
research
∙
11/03/2021
An Empirical Study of Training End-to-End Vision-and-Language Transformers
Vision-and-language (VL) pre-training has proven to be highly effective ...
research
∙
10/21/2021
SYNERGY: Building Task Bots at Scale Using Symbolic Knowledge and Machine Teaching
In this paper we explore the use of symbolic knowledge and machine teach...
research
∙
10/16/2021
Leveraging Knowledge in Multilingual Commonsense Reasoning
Commonsense reasoning (CSR) requires the model to be equipped with gener...
research
∙
10/13/2021
Dict-BERT: Enhancing Language Model Pre-training with Dictionary
Pre-trained language models (PLMs) aim to learn universal language repre...
research
∙
10/08/2021
KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering
Current Open-Domain Question Answering (ODQA) model paradigm often conta...
research
∙
09/01/2021
Does Knowledge Help General NLU? An Empirical Study
It is often observed in knowledge-centric tasks (e.g., common sense ques...
research
∙
04/15/2021
Sentence-Permuted Paragraph Generation
Generating paragraphs of diverse contents is important in many applicati...
research
∙
12/29/2020
RADDLE: An Evaluation Benchmark and Analysis Platform for Robust Task-oriented Dialog Systems
For task-oriented dialog systems to be maximally useful, it must be able...
research
∙
12/09/2020
Fusing Context Into Knowledge Graph for Commonsense Reasoning
Commonsense reasoning requires a model to make presumptions about world ...
research
∙
10/18/2020
Mixed-Lingual Pre-training for Cross-lingual Summarization
Cross-lingual Summarization (CLS) aims at producing a summary in the tar...
research
∙
10/09/2020
A Survey of Knowledge-Enhanced Text Generation
The goal of text generation is to make machines express in human languag...
research
∙
10/05/2020
Semi-Supervised Speech-Language Joint Pre-Training for Spoken Language Understanding
Spoken language understanding (SLU) requires a model to analyze input ac...
research
∙
10/02/2020
JAKET: Joint Pre-training of Knowledge Graph and Language Understanding
Knowledge graphs (KGs) contain rich information about world knowledge, e...
research
∙
09/28/2020
Injecting Entity Types into Entity-Guided Text Generation
Recent successes in deep generative modeling have led to significant adv...
research
∙
06/27/2020
Mind The Facts: Knowledge-Boosted Coherent Abstractive Text Summarization
Neural models have become successful at producing abstractive summaries ...
research
∙
06/05/2020
Filtered Inner Product Projection for Multilingual Embedding Alignment
Due to widespread interest in machine translation and transfer learning,...
research
∙
06/03/2020
Meta Dialogue Policy Learning
Dialog policy determines the next-step actions for agents and hence is c...
research
∙
04/30/2020
Boosting Naturalness of Language in Task-oriented Dialogues via Adversarial Training
The natural language generation (NLG) module in a task-oriented dialogue...
research
∙
04/29/2020
Data Augmentation for Spoken Language Understanding via Pretrained Models
The training of spoken language understanding (SLU) models often faces t...
research
∙
04/04/2020
End-to-End Abstractive Summarization for Meetings
With the abundance of automatic meeting transcripts, meeting summarizati...
research
∙
03/19/2020
Boosting Factual Correctness of Abstractive Summarization
A commonly observed problem with abstractive summarization is the distor...
research
∙
03/19/2020
Boosting Factual Correctness of Abstractive Summarization with Knowledge Graph
A commonly observed problem with abstractive summarization is the distor...
research
∙
02/27/2020
Few-shot Natural Language Generation for Task-Oriented Dialog
As a crucial component in task-oriented dialog systems, the Natural Lang...
research
∙
01/03/2020