Search Results for author:
Found 322 papers, 190 papers with code
Pseudo-Masked Language Models for Unified Language Model Pre-Training
We propose to pre-train a unified language model for both autoencoding and partially autoregressive language modeling tasks using a novel training procedure, referred to as a pseudo-masked language model (PMLM).
Few-Shot Named Entity Recognition: An Empirical Baseline Study
This paper presents an empirical study to efficiently build named entity recognition (NER) systems when a small amount of in-domain labeled data is available.
NICE: Neural Image Commenting with Empathy
Based on these annotations, we define two different tasks for the NICE dataset.
Training Small Multimodal Models to Bridge Biomedical Competency Gap: A Case Study in Radiology Imaging
Frontier models such as GPT-4V still have major competency gaps in multimodal capabilities for biomedical applications.
Pix2Gif: Motion-Guided Diffusion for GIF Generation
We present Pix2Gif, a motion-guided diffusion model for image-to-GIF (video) generation.
Attribute Structuring Improves LLM-Based Evaluation of Clinical Text Summaries
Summarizing clinical text is crucial in health decision-support and clinical research.
Position Paper: Agent AI Towards a Holistic Intelligence
Recent advancements in large foundation models have remarkably enhanced our understanding of sensory information in open-world environments.
Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models
Sora is a text-to-video generative AI model, released by OpenAI in February 2024.
Large Language Models: A Survey
Large Language Models (LLMs) have drawn a lot of attention due to their strong performance on a wide range of natural language tasks, since the release of ChatGPT in November 2022.
An Interactive Agent Foundation Model
We propose an Interactive Agent Foundation Model that uses a novel multi-task agent training paradigm for training AI agents across a wide range of domains, datasets, and tasks.
Learning a Decision Tree Algorithm with Transformers
We then train MetaTree to produce the trees that achieve strong generalization performance.
The Essential Role of Causality in Foundation World Models for Embodied AI
This paper focuses on the prospects of building foundation world models for the upcoming generation of embodied agents and presents a novel viewpoint on the significance of causality within these.
Rethinking Interpretability in the Era of Large Language Models
We highlight two emerging research priorities for LLM interpretation: using LLMs to directly analyze new datasets and to generate interactive explanations.
Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning
We propose explanation-consistency finetuning (EC-finetuning), a method that adapts LLMs to generate more consistent natural-language explanations on related examples.
TrustLLM: Trustworthiness in Large Language Models
This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions.
Agent AI: Surveying the Horizons of Multimodal Interaction
To accelerate research on agent-based multimodal intelligence, we define "Agent AI" as a class of interactive systems that can perceive visual stimuli, language inputs, and other environmentally-grounded data, and can produce meaningful embodied actions.
Localized Symbolic Knowledge Distillation for Visual Commonsense Models
Empirical results and human evaluations in a zero-shot setup demonstrate that our distillation method results in more precise VL models of reasoning compared to a baseline of passing a generated referring expression to an LLM.
LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models
To address this issue, we have created GVC data that allows for the combination of grounding and chat capabilities.
IMProv: Inpainting-based Multimodal Prompting for Computer Vision Tasks
Given a textual description of a visual task (e. g. "Left: input image, Right: foreground segmentation"), a few input-output visual examples, or both, the model in-context learns to solve it for a new test input.
Visual In-Context Prompting
In-context prompting in large language models (LLMs) has become a prevalent approach to improve zero-shot capabilities, but this idea is less explored in the vision domain.
GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation
We first benchmark MM-Navigator on our collected iOS screen dataset.
LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents
LLaVA-Plus is a general-purpose multimodal assistant that expands the capabilities of large multimodal models.
Ranked #1 on
LMM real-life tasks
on Leaderboard
Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs
In human-written articles, we often leverage the subtleties of text style, such as bold and italics, to guide the attention of readers.
LLaVA-Interactive: An All-in-One Demo for Image Chat, Segmentation, Generation and Editing
LLaVA-Interactive is a research prototype for multimodal human-AI interaction.
Tree Prompting: Efficient Task Adaptation without Fine-Tuning
Prompting language models (LMs) is the main interface for applying them to new tasks.
Teaching Language Models to Self-Improve through Interactive Demonstrations
The self-improving ability of large language models (LLMs), enabled by prompting them to analyze and revise their own outputs, has garnered significant interest in recent research.
Automatic Hallucination Assessment for Aligned Large Language Models via Transferable Adversarial Attacks
Finally, we find that the adversarial examples generated by our method are transferable across all considered LLMs.
Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
We present Set-of-Mark (SoM), a new visual prompting method, to unleash the visual grounding abilities of large multimodal models (LMMs), such as GPT-4V.
BiomedJourney: Counterfactual Biomedical Image Generation by Instruction-Learning from Multimodal Patient Journeys
In a comprehensive battery of tests on counterfactual medical image generation, BiomedJourney substantially outperforms prior state-of-the-art methods in instruction image editing and medical image generation such as InstructPix2Pix and RoentGen.
Fast-ELECTRA for Efficient Pre-training
Although ELECTRA offers a significant boost in efficiency, its potential is constrained by the training cost brought by the auxiliary model.
Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
In this study, we introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language Models (LLMs).
MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
To bridge this gap, we present MathVista, a benchmark designed to combine challenges from diverse mathematical and visual tasks.
Sparse Backpropagation for MoE Training
One defining characteristic of Mixture-of-Expert (MoE) models is their capacity for conducting sparse computation via expert routing, leading to remarkable scalability.
An Empirical Study of Scaling Instruct-Tuned Large Multimodal Models
We find that scaling LMM consistently enhances model performance and improves language capabilities, and performance of LoRA/QLoRA tuning of LMM are comparable to the performance of full-model fine-tuning.
Ranked #45 on
Visual Question Answering
on MM-Vet
Multimodal Foundation Models: From Specialists to General-Purpose Assistants
This paper presents a comprehensive survey of the taxonomy and evolution of multimodal foundation models that demonstrate vision and vision-language capabilities, focusing on the transition from specialist models to general-purpose assistants.
MindAgent: Emergent Gaming Interaction
Large Language Models (LLMs) have the capacity of performing complex scheduling in a multi-agent system and can coordinate these agents into completing sophisticated tasks that require extensive collaboration.
Semantic-SAM: Segment and Recognize Anything at Any Granularity
In this paper, we introduce Semantic-SAM, a universal image segmentation model to enable segment and recognize anything at any desired granularity.
Is Self-Repair a Silver Bullet for Code Generation?
We hypothesize that this is because self-repair is bottlenecked by the model's ability to provide feedback on its own code; using a stronger model to artificially boost the quality of the feedback, we observe substantially larger performance gains.
Augmenting Language Models with Long-Term Memory
Such a decoupled memory design can easily cache and update long-term past contexts for memory retrieval without suffering from memory staleness.
Differentiable Tree Operations Promote Compositional Generalization
To facilitate the learning of these symbolic sequences, we introduce a differentiable tree interpreter that compiles high-level symbolic tree operations into subsymbolic matrix operations on tensors.
LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day
In this paper, we propose a cost-efficient approach for training a vision-language conversational assistant that can answer open-ended research questions of biomedical images.
Self-Verification Improves Few-Shot Clinical Information Extraction
Extracting patient information from unstructured text is a critical task in health decision-support and clinical research.
Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models
Fact-checking is an essential task in NLP that is commonly utilized for validating the factual accuracy of claims.
Pre-training Multi-task Contrastive Learning Models for Scientific Literature Understanding
Scientific literature understanding tasks have gained significant attention due to their potential to accelerate scientific discovery.
Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers
This paper explores the effectiveness of model-generated signals in improving zero-shot generalization of text-to-text Transformers such as T5.
Explaining black box text modules in natural language with language models
Here, we ask whether we can automatically obtain natural language explanations for black box text modules.
Chain-of-Skills: A Configurable Model for Open-domain Question Answering
Our approach outperforms recent self-supervised retrievers in zero-shot evaluations and achieves state-of-the-art fine-tuned retrieval performance on NQ, HotpotQA and OTT-QA.
Ranked #4 on
Question Answering
on HotpotQA
ArK: Augmented Reality with Knowledge Interactive Emergent Ability
In this study, we develop an infinite agent that learns to transfer knowledge memory from general foundation models (e. g. GPT4, DALLE) to novel domains or scenarios for scene understanding and generation in the physical or virtual world.
Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models
At the heart of Chameleon is an LLM-based planner that assembles a sequence of tools to execute to generate the final response.
Segment Everything Everywhere All at Once
In SEEM, we propose a novel decoding mechanism that enables diverse prompting for all types of segmentation tasks, aiming at a universal segmentation interface that behaves like large language models (LLMs).
Instruction Tuning with GPT-4
Prior work has shown that finetuning large language models (LLMs) using machine-generated instruction-following data enables such models to achieve remarkable zero-shot capabilities on new tasks, and no human-written instructions are needed.
Pre-training Transformers for Knowledge Graph Completion
Learning transferable representation of knowledge graphs (KGs) is challenging due to the heterogeneous, multi-relational nature of graph structures.
A Simple Framework for Open-Vocabulary Segmentation and Detection
We present OpenSeeD, a simple Open-vocabulary Segmentation and Detection framework that jointly learns from different segmentation and detection datasets.
Ranked #2 on
Instance Segmentation
on ADE20K val
(using extra training data)
BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs
Therefore, training an effective generalist biomedical model requires high-quality multimodal data, such as parallel image-text pairs.
Ranked #3 on
Medical Visual Question Answering
on SLAKE-English
Interactive Text Generation
Unfortunately, this means most of the research on text, code, and image generation has focused on non-interactive settings, whereby the model is expected to get everything right without accounting for any input from a user who may be willing to help.
Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback
Large language models (LLMs), such as ChatGPT, are able to generate human-like, fluent responses for many downstream tasks, e. g., task-oriented dialog and question answering.
Learning Customized Visual Models with Retrieval-Augmented Knowledge
Image-text contrastive learning models such as CLIP have demonstrated strong task transfer ability.
Ranked #1 on
Semi-Supervised Image Classification
on ImageNet - 1% labeled data
(using extra training data)
GLIGEN: Open-Set Grounded Text-to-Image Generation
Large-scale text-to-image diffusion models have made amazing advances.
Ranked #4 on
Conditional Text-to-Image Synthesis
on COCO-MIG
Language Models as Inductive Reasoners
To this end, we propose a new paradigm (task) for inductive reasoning, which is to induce natural language rules from natural language facts, and create a dataset termed DEER containing 1. 2k rule-fact pairs for the task, where rules and facts are written in natural language.
Generalized Decoding for Pixel, Image, and Language
We present X-Decoder, a generalized decoding model that can predict pixel-level segmentation and language tokens seamlessly.
Ranked #4 on
Instance Segmentation
on ADE20K val
(using extra training data)
DIONYSUS: A Pre-trained Model for Low-Resource Dialogue Summarization
In this work, we propose DIONYSUS (dynamic input optimization in pre-training for dialogue summarization), a pre-trained encoder-decoder model for summarizing dialogues in any new domain.
Enhancing Task Bot Engagement with Synthesized Open-Domain Dialog
To better mimic human-level conversations that usually fuse various dialog modes, it is essential to build a system that can effectively handle both TOD and ODD and access different knowledge sources.
Efficient Long Sequence Modeling via State Space Augmented Transformer
Specifically, we augment a SSM into the bottom layer of SPADE, and we employ efficient local attention methods for the other layers.
Grounded Keys-to-Text Generation: Towards Factual Open-Ended Generation
We propose a new grounded keys-to-text generation task: the task is to generate a factual description about an entity given a set of guiding keys, and grounding passages.
ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Format
Task-oriented dialogue (TOD) systems function as digital assistants, guiding users through various tasks such as booking flights or finding restaurants.
CodeExp: Explanatory Code Document Generation
Our experiments show that (1) our refined training dataset lets models achieve better performance in the explanation generation tasks compared to larger unrefined data (15x larger), and (2) fine-tuned models can generate well-structured long docstrings comparable to human-written ones.
Execution-based Evaluation for Data Science Code Generation Models
Code generation models can benefit data scientists' productivity by automatically generating code from context and text descriptions.
AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning
Standard fine-tuning of large pre-trained language models (PLMs) for downstream tasks requires updating hundreds of millions to billions of parameters, and storing a large copy of the PLM weights for every task resulting in increased cost for storing, sharing and serving the models.
Lafite2: Few-shot Text-to-Image Generation
The low requirement of the proposed method yields high flexibility and usability: it can be beneficial to a wide range of settings, including the few-shot, semi-supervised and fully-supervised learning; it can be applied on different models including generative adversarial networks (GANs) and diffusion models.
Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledge
We propose a novel open-domain question answering (ODQA) framework for answering single/multi-hop questions across heterogeneous knowledge sources.
Vision-Language Pre-training: Basics, Recent Advances, and Future Trends
This paper surveys vision-language pre-training (VLP) methods for multimodal intelligence that have been developed in the last few years.
AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation
Furthermore, existing MoE works do not consider computational constraints (e. g., FLOPs, latency) to guide their design.
Task-Aware Specialization for Efficient and Robust Dense Retrieval for Open-Domain Question Answering
Given its effectiveness on knowledge-intensive natural language processing tasks, dense retrieval models have become increasingly popular.
Explaining Patterns in Data with Language Models via Interpretable Autoprompting
Large language models (LLMs) have displayed an impressive ability to harness natural language to perform complex tasks.
Augmenting Interpretable Models with LLMs during Training
Recent large language models (LLMs) have demonstrated remarkable prediction performance for a growing array of tasks.
Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learning
We present a bi-encoder framework for named entity recognition (NER), which applies contrastive learning to map candidate text spans and entity types into the same vector representation space.
Ranked #1 on
Named Entity Recognition (NER)
on BC5CDR
Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization
Z-Code++ creates new state of the art on 9 out of 13 text summarization tasks across 5 languages.
Interactive Code Generation via Test-Driven User-Intent Formalization
Large language models (LLMs) have shown great potential in automating significant aspects of coding by producing natural code from informal natural language (NL) intent.
Structural Biases for Improving Transformers on Translation into Morphologically Rich Languages
Machine translation has seen rapid progress with the advent of Transformer-based models.
OPERA: Harmonizing Task-Oriented Dialogs and Information Seeking Experience
Existing studies in conversational AI mostly treat task-oriented dialog (TOD) and question answering (QA) as separate tasks.
GODEL: Large-Scale Pre-Training for Goal-Directed Dialog
We introduce GODEL (Grounded Open Dialogue Language Model), a large pre-trained language model for dialog.
Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone
Vision-language (VL) pre-training has recently received considerable attention.
Ranked #1 on
Phrase Grounding
on Flickr30k Entities Dev
GLIPv2: Unifying Localization and Vision-Language Understanding
We present GLIPv2, a grounded VL understanding model, that serves both localization tasks (e. g., object detection, instance segmentation) and Vision-Language (VL) understanding tasks (e. g., VQA, image captioning).
Ranked #1 on
Phrase Grounding
on Flickr30k Entities Test
(using extra training data)
Fault-Aware Neural Code Rankers
Large language models (LLMs) have demonstrated an impressive ability to generate code for various programming tasks.
Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutions
We show that our use of self-sampled correct and partially-correct solutions can benefit learning and help guide the sampling process, leading to more efficient exploration of the solution space.
Ranked #138 on
Arithmetic Reasoning
on GSM8K
AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning
Standard fine-tuning of large pre-trained language models (PLMs) for downstream tasks requires updating hundreds of millions to billions of parameters, and storing a large copy of the PLM weights for every task resulting in increased cost for storing, sharing and serving the models.
Visually-Augmented Language Modeling
With the visually-augmented context, VaLM uses a visual knowledge fusion layer to enable multimodal grounded language modeling by attending to both text context and visual knowledge in images.
Training Vision-Language Transformers from Captions
Vision-Language Transformers can be learned without low-level human labels (e. g. class labels, bounding boxes, etc).
Neurocompositional computing: From the Central Paradox of Cognition to a new generation of AI systems
What explains the dramatic progress from 20th-century to 21st-century AI, and how can the remaining limitations of current AI be overcome?
K-LITE: Learning Transferable Visual Models with External Knowledge
We propose K-LITE, a simple strategy to leverage external knowledge for building transferable visual systems: In training, it enriches entities in text with WordNet and Wiktionary knowledge, leading to an efficient and scalable approach to learning image representations that uses knowledge about the visual concepts.
ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models
In general, these language-augmented visual models demonstrate strong transferability to a variety of datasets and tasks.
Ranked #1 on
Object Detection
on ELEVATER
Sparsely Activated Mixture-of-Experts are Robust Multi-Task Learners
Traditional multi-task learning (MTL) methods use dense networks that use the same set of shared weights across several different tasks.
METRO: Efficient Denoising Pretraining of Large Scale Autoencoding Language Models with Model Generated Signals
We present an efficient method of pretraining large-scale autoencoding language models using training signals generated by an auxiliary model.
Unified Contrastive Learning in Image-Text-Label Space
Particularly, it attains gains up to 9. 2% and 14. 5% in average on zero-shot recognition benchmarks over the language-image contrastive learning and supervised learning methods, respectively.
Focal Modulation Networks
For semantic segmentation with UPerNet, FocalNet base at single-scale outperforms Swin by 2. 4, and beats Swin at multi-scale (50. 5 v. s.
Ranked #8 on
Object Detection
on COCO minival
(using extra training data)
Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer
Hyperparameter (HP) tuning in deep learning is an expensive process, prohibitively so for neural networks (NNs) with billions of parameters.
A Survey of Knowledge-Intensive NLP with Pre-Trained Language Models
With the increasing of model capacity brought by pre-trained language models, there emerges boosting needs for more knowledgeable natural language processing (NLP) models with advanced functionalities including providing and making flexible use of encyclopedic and commonsense knowledge.
No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer Models
Analysis shows that the proposed schedule indeed reduces the redundancy and improves generalization performance.
AutoDistil: Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models
Our framework AutoDistil addresses above challenges with the following steps: (a) Incorporates inductive bias and heuristics to partition Transformer search space into K compact sub-spaces (K=3 for typical student sizes of base, small and tiny); (b) Trains one SuperLM for each sub-space using task-agnostic objective (e. g., self-attention distillation) with weight-sharing of students; (c) Lightweight search for the optimal student without re-training.
Toward Self-learning End-to-End Task-Oriented Dialog Systems
In this paper, we study the problem of automatically adapting task bots to changing environments by learning from human-bot interactions with minimum or zero human annotations.
Neural Approaches to Conversational Information Retrieval
A conversational information retrieval (CIR) system is an information retrieval (IR) system with a conversational interface which allows users to interact with the system to seek information via multi-turn conversations of natural language, in spoken or written form.
RegionCLIP: Region-based Language-Image Pretraining
However, we show that directly applying such models to recognize image regions for object detection leads to poor performance due to a domain shift: CLIP was trained to match an image as a whole to a text description, without capturing the fine-grained alignment between image regions and text spans.
Ranked #11 on
Open Vocabulary Object Detection
on MSCOCO
(using extra training data)
KAT: A Knowledge Augmented Transformer for Vision-and-Language
The primary focus of recent work with largescale transformers has been on optimizing the amount of information packed into the model's parameters.
Knowledge-Rich Self-Supervision for Biomedical Entity Linking
Zero-shot entity linking has emerged as a promising direction for generalizing to new entities, but it still requires example gold entity mentions during training and canonical descriptions for all entities, both of which are rarely available outside of Wikipedia.
Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representation
To address these challenges, we present PLUG, a language model that homogenizes different knowledge sources to a unified knowledge representation for knowledge-grounded dialogue generation tasks.
Fine-Tuning Large Neural Language Models for Biomedical Natural Language Processing
Overall, domainspecific vocabulary and pretraining facilitate more robust models for fine-tuning.
ValueNet: A New Dataset for Human Value Driven Dialogue System
To the best of our knowledge, ValueNet is the first large-scale text dataset for human value modeling, and we are the first one trying to incorporate a value model into emotionally intelligent dialogue systems.
Grounded Language-Image Pre-training
The unification brings two benefits: 1) it allows GLIP to learn from both detection and grounding data to improve both tasks and bootstrap a good grounding model; 2) GLIP can leverage massive image-text pairs by generating grounding boxes in a self-training fashion, making the learned representation semantic-rich.
Ranked #1 on
2D Object Detection
on RF100
Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention
In particular, we focus on the task of Commonsense Reasoning, demonstrating that the proposed external attention mechanism can augment existing transformer models and significantly improve the model's reasoning capabilities.
Ranked #1 on
Common Sense Reasoning
on CommonsenseQA
(using extra training data)
Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer
Hyperparameter (HP) tuning in deep learning is an expensive process, prohibitively so for neural networks (NNs) with billions of parameters. We show that, in the recently discovered Maximal Update Parametrization ($\mu$P), many optimal HPs remain stable even as model size changes.
Focal Attention for Long-Range Interactions in Vision Transformers
With focal attention, we propose a new variant of Vision Transformer models, called Focal Transformers, which achieve superior performance over the state-of-the-art (SoTA) Vision Transformers on a range of public image classification and object detection benchmarks.
Florence: A New Foundation Model for Computer Vision
Computer vision foundation models, which are trained on diverse, large-scale dataset and can be adapted to a wide range of downstream tasks, are critical for this mission to solve real-world computer vision applications.
Ranked #1 on
Action Recognition In Videos
on Kinetics-600
DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing
We thus propose a new gradient-disentangled embedding sharing method that avoids the tug-of-war dynamics, improving both training efficiency and the quality of the pre-trained model.
Ranked #1 on
Natural Language Inference
on MRPC
Natural Language Inference
Natural Language Understanding
+2
How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN
We apply these analyses to four neural language models (an LSTM, a Transformer, Transformer-XL, and GPT-2).
Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models
In this paper, we present Adversarial GLUE (AdvGLUE), a new multi-task benchmark to quantitatively and thoroughly explore and evaluate the vulnerabilities of modern large-scale language models under various types of adversarial attacks.
Ranked #1 on
Adversarial Robustness
on AdvGLUE
CLUES: Few-Shot Learning Evaluation in Natural Language Understanding
We demonstrate that while recent models reach human performance when they have access to large amounts of labeled data, there is a huge gap in performance in the few-shot setting for most tasks.
SYNERGY: Building Task Bots at Scale Using Symbolic Knowledge and Machine Teaching
We propose SYNERGY, a hybrid learning framework where a task bot is developed in two steps: (i) Symbolic knowledge to neural networks: Large amounts of simulated dialog sessions are generated based on task-specific symbolic knowledge which is represented as a task schema consisting of dialog flows and task-oriented databases.
Open Domain Question Answering with A Unified Knowledge Interface
The retriever-reader framework is popular for open-domain question answering (ODQA) due to its ability to use explicit knowledge.
LiST: Lite Prompted Self-training Makes Parameter-Efficient Few-shot Learners
The first is the use of self-training to leverage large amounts of unlabeled data for prompt-based FN in few-shot settings.
Taming Sparsely Activated Transformer with Stochastic Experts
While most on-going research focuses on improving SAMs models by exploring methods of routing inputs to experts, our analysis reveals that such research might not lead to the solution we expect, i. e., the commonly-used routing methods based on gating mechanisms do not work better than randomly routing inputs to experts.
ARCH: Efficient Adversarial Regularized Training with Caching
Adversarial regularization can improve model generalization in many natural language processing tasks.
WebQA: Multihop and Multimodal QA
Scaling Visual Question Answering (VQA) to the open-domain and multi-hop nature of web searches, requires fundamental advances in visual representation learning, knowledge aggregation, and language generation.
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment
This is motivated by the observation that for a video-text pair, the content words in the text, such as nouns and verbs, are more likely to be aligned with the visual contents in the video than the function words.
Ranked #3 on
Temporal Action Localization
on CrossTask
(using extra training data)
EmailSum: Abstractive Email Thread Summarization
Furthermore, we find that widely used automatic evaluation metrics (ROUGE, BERTScore) are weakly correlated with human judgments on this email thread summarization task.
Ranked #1 on
Email Thread Summarization
on EmailSum (short)
Image Scene Graph Generation (SGG) Benchmark
There is a surge of interest in image scene graph generation (object, attribute and relationship detection) due to the need of building fine-grained image understanding models that go beyond object detection.
Focal Self-attention for Local-Global Interactions in Vision Transformers
With focal self-attention, we propose a new variant of Vision Transformer models, called Focal Transformer, which achieves superior performance over the state-of-the-art vision Transformers on a range of public image classification and object detection benchmarks.
Ranked #17 on
Instance Segmentation
on COCO test-dev
Domain-Specific Pretraining for Vertical Search: Case Study on Biomedical Literature
A prominent case in point is the explosion of the biomedical literature on COVID-19, which swelled to hundreds of thousands of papers in a matter of months.
Efficient Self-supervised Vision Transformers for Representation Learning
This paper investigates two techniques for developing efficient self-supervised vision transformers (EsViT) for visual representation learning.
Ranked #16 on
Self-Supervised Image Classification
on ImageNet
Representation Learning
Self-Supervised Image Classification
XtremeDistilTransformers: Task Transfer for Task-agnostic Distillation
While deep and large pre-trained models are the state-of-the-art for various natural language processing tasks, their huge size poses significant challenges for practical uses in resource constrained settings.
Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization
On several syntactic and semantic probing tasks, we demonstrate the emergent structural information in the role vectors and improved syntactic interpretability in the TPR layer outputs.
Compositional Processing Emerges in Neural Networks Solving Math Problems
A longstanding question in cognitive science concerns the learning mechanisms underlying compositionality in human cognition.
RetGen: A Joint framework for Retrieval and Grounded Text Generation Modeling
We propose a framework that alleviates this data constraint by jointly training a grounded generator and document retriever on the language model signal.
Targeted Adversarial Training for Natural Language Understanding
We present a simple yet effective Targeted Adversarial Training (TAT) algorithm to improve adversarial training for natural language understanding.
Adversarial Regularization as Stackelberg Game: An Unrolled Optimization Approach
Adversarial regularization has been shown to improve the generalization performance of deep learning models in various natural language processing tasks.
Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding
This paper presents a new Vision Transformer (ViT) architecture Multi-Scale Vision Longformer, which significantly enhances the ViT of \cite{dosovitskiy2020image} for encoding high-resolution images using two techniques.
Ranked #45 on
Instance Segmentation
on COCO minival
Token-wise Curriculum Learning for Neural Machine Translation
Existing curriculum learning approaches to Neural Machine Translation (NMT) require sampling sufficient amounts of "easy" samples from training data at the early training stage.
Data Augmentation for Abstractive Query-Focused Multi-Document Summarization
The progress in Query-focused Multi-Document Summarization (QMDS) has been limited by the lack of sufficient largescale high-quality training datasets.
Learning to Shift Attention for Motion Generation
For multiple modes, we suggest to learn local latent representations of motion trajectories with a density estimation method based on real-valued non-volume preserving (RealNVP) transformations that provides a set of powerful, stably invertible, and learnable transformations.
VinVL: Revisiting Visual Representations in Vision-Language Models
In our experiments we feed the visual features generated by the new object detection model into a Transformer-based VL fusion model \oscar \cite{li2020oscar}, and utilize an improved approach \short\ to pre-train the VL model and fine-tune it on a wide range of downstream VL tasks.
Ranked #2 on
Image-text matching
on CommercialAdsDataset
NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
We review the EfficientQA competition from NeurIPS 2020.
UnitedQA: A Hybrid Approach for Open Domain Question Answering
To date, most of recent work under the retrieval-reader framework for open-domain QA focuses on either extractive or generative reader exclusively.
Ranked #1 on
Open-Domain Question Answering
on TriviaQA
Rider: Reader-Guided Passage Reranking for Open-Domain Question Answering
Current open-domain question answering systems often follow a Retriever-Reader architecture, where the retriever first retrieves relevant passages and the reader then reads the retrieved passages to form an answer.
Token-Level Contrast for Video and Language Alignment
Building video and language understanding models requires grounding linguistic concepts and video contents into a shared space.
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 to process conversations in a way that is (1) generalizable with a small number of training examples for new task domains, and (2) robust to user input in various styles, modalities or domains.
Few-Shot Named Entity Recognition: A Comprehensive Study
This paper presents a comprehensive study to efficiently build named entity recognition (NER) systems when a small number of in-domain labeled data is available.
Self-supervised Pre-training with Hard Examples Improves Visual Representations
Self-supervised pre-training (SSP) employs random image transformations to generate training data for visual representation learning.
Ranked #69 on
Self-Supervised Image Classification
on ImageNet
MiniVLM: A Smaller and Faster Vision-Language Model
We design a Two-stage Efficient feature Extractor (TEE), inspired by the one-stage EfficientDet network, to significantly reduce the time cost of visual feature extraction by $95\%$, compared to a baseline model.
Neuro-Symbolic Representations for Video Captioning: A Case for Leveraging Inductive Biases for Vision and Language
In this paper, we propose a new model architecture for learning multi-modal neuro-symbolic representations for video captioning.
Overview of the Ninth Dialog System Technology Challenge: DSTC9
Interactive evaluation of dialog, and 4.
CMT in TREC-COVID Round 2: Mitigating the Generalization Gaps from Web to Special Domain Search
Neural rankers based on deep pretrained language models (LMs) have been shown to improve many information retrieval benchmarks.
Guided Dialogue Policy Learning without Adversarial Learning in the Loop
Reinforcement learning methods have emerged as a popular choice for training an efficient and effective dialogue policy.
RMM: A Recursive Mental Model for Dialogue Navigation
In this paper, we go beyond instruction following and introduce a two-agent task where one agent navigates and asks questions that a second, guiding agent answers.
GO FIGURE: A Meta Evaluation of Factuality in Summarization
While neural language models can generate text with remarkable fluency and coherence, controlling for factual correctness in generation remains an open research question.
Text Editing by Command
A prevailing paradigm in neural text generation is one-shot generation, where text is produced in a single step.
Posterior Differential Regularization with f-divergence for Improving Model Robustness
Theoretically, we provide a connection of two recent methods, Jacobian Regularization and Virtual Adversarial Training, under this framework.
MagGAN: High-Resolution Face Attribute Editing with Mask-Guided Generative Adversarial Network
We present Mask-guided Generative Adversarial Network (MagGAN) for high-resolution face attribute editing, in which semantic facial masks from a pre-trained face parser are used to guide the fine-grained image editing process.
VIVO: Visual Vocabulary Pre-Training for Novel Object Captioning
It is highly desirable yet challenging to generate image captions that can describe novel objects which are unseen in caption-labeled training data, a capability that is evaluated in the novel object captioning challenge (nocaps).
Ranked #3 on
Image Captioning
on nocaps-XD out-of-domain
Generation-Augmented Retrieval for Open-domain Question Answering
We demonstrate that the generated contexts substantially enrich the semantics of the queries and GAR with sparse representations (BM25) achieves comparable or better performance than state-of-the-art dense retrieval methods such as DPR.
Ranked #9 on
Passage Retrieval
on Natural Questions
Robust Conversational AI with Grounded Text Generation
This article provides an overview of this progress and discusses related methods and technologies that can be incorporated for building robust conversational AI systems.
HittER: Hierarchical Transformers for Knowledge Graph Embeddings
Our proposed model consists of two different Transformer blocks: the bottom block extracts features of each entity-relation pair in the local neighborhood of the source entity and the top block aggregates the relational information from outputs of the bottom block.
Ranked #1 on
Link Prediction
on FB15k-237
(Hit@10 metric)
Very Deep Transformers for Neural Machine Translation
We explore the application of very deep Transformer models for Neural Machine Translation (NMT).
Ranked #1 on
Machine Translation
on WMT2014 English-French
(using extra training data)
Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing
In this paper, we challenge this assumption by showing that for domains with abundant unlabeled text, such as biomedicine, pretraining language models from scratch results in substantial gains over continual pretraining of general-domain language models.
Ranked #2 on
Participant Intervention Comparison Outcome Extraction
on EBM-NLP
(using extra training data)
Conversation Learner - A Machine Teaching Tool for Building Dialog Managers for Task-Oriented Dialog Systems
Traditionally, industry solutions for building a task-oriented dialog system have relied on helping dialog authors define rule-based dialog managers, represented as dialog flows.
MIND: A Large-scale Dataset for News Recommendation
News recommendation is an important technique for personalized news service.
DIALOGPT : Large-Scale Generative Pre-training for Conversational Response Generation
We present a large, tunable neural conversational response generation model, DIALOGPT (dialogue generative pre-trained transformer).
Evaluation of Text Generation: A Survey
The paper surveys evaluation methods of natural language generation (NLG) systems that have been developed in the last few years.
Few-Shot Generative Conversational Query Rewriting
Conversational query rewriting aims to reformulate a concise conversational query to a fully specified, context-independent query that can be effectively handled by existing information retrieval systems.
DeBERTa: Decoding-enhanced BERT with Disentangled Attention
Recent progress in pre-trained neural language models has significantly improved the performance of many natural language processing (NLP) tasks.
Ranked #1 on
Common Sense Reasoning
on SWAG
M3P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-training
We present M3P, a Multitask Multilingual Multimodal Pre-trained model that combines multilingual pre-training and multimodal pre-training into a unified framework via multitask pre-training.
Novel Human-Object Interaction Detection via Adversarial Domain Generalization
We study in this paper the problem of novel human-object interaction (HOI) detection, aiming at improving the generalization ability of the model to unseen scenarios.
Is Your Goal-Oriented Dialog Model Performing Really Well? Empirical Analysis of System-wise Evaluation
There is a growing interest in developing goal-oriented dialog systems which serve users in accomplishing complex tasks through multi-turn conversations.
SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching
We present a new method SOLOIST that uses transfer learning and machine teaching to build task bots at scale.
Ranked #4 on
End-To-End Dialogue Modelling
on MULTIWOZ 2.0
RMM: A Recursive Mental Model for Dialog Navigation
In this paper, we go beyond instruction following and introduce a two-agent task where one agent navigates and asks questions that a second, guiding agent answers.
A Controllable Model of Grounded Response Generation
Current end-to-end neural conversation models inherently lack the flexibility to impose semantic control in the response generation process, often resulting in uninteresting responses.
RaCT: Toward Amortized Ranking-Critical Training For Collaborative Filtering
We investigate new methods for training collaborative filtering models based on actor-critic reinforcement learning, to more directly maximize ranking-based objective functions.
Learning Compliance Adaptation in Contact-Rich Manipulation
Compliant robot behavior is crucial for the realization of contact-rich manipulation tasks.
PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking
We propose the task of outline-conditioned story generation: given an outline as a set of phrases that describe key characters and events to appear in a story, the task is to generate a coherent narrative that is consistent with the provided outline.
Data Augmentation for Spoken Language Understanding via Pretrained Language Models
The training of spoken language understanding (SLU) models often faces the problem of data scarcity.
Adversarial Training for Large Neural Language Models
In natural language processing (NLP), pre-training large neural language models such as BERT have demonstrated impressive gain in generalization for a variety of tasks, with further improvement from adversarial fine-tuning.
Ranked #6 on
Natural Language Inference
on ANLI test
(using extra training data)
Understanding the Difficulty of Training Transformers
Transformers have proved effective in many NLP tasks.
Ranked #5 on
Machine Translation
on WMT2014 English-French
Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks
Large-scale pre-training methods of learning cross-modal representations on image-text pairs are becoming popular for vision-language tasks.
Ranked #1 on
Image Retrieval
on MS COCO
(Recall@10 metric)
Conversation Learner -- A Machine Teaching Tool for Building Dialog Managers for Task-Oriented Dialog Systems
Traditionally, industry solutions for building a task-oriented dialog system have relied on helping dialog authors define rule-based dialog managers, represented as dialog flows.
Guided Dialog Policy Learning without Adversarial Learning in the Loop
Reinforcement Learning (RL) methods have emerged as a popular choice for training an efficient and effective dialogue policy.
Deep Learning Based Text Classification: A Comprehensive Review
Deep learning based models have surpassed classical machine learning based approaches in various text classification tasks, including sentiment analysis, news categorization, question answering, and natural language inference.
Feature Quantization Improves GAN Training
The instability in GAN training has been a long-standing problem despite remarkable research efforts.
Ranked #1 on
Conditional Image Generation
on CIFAR-100
Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space
We hope that our first pre-trained big VAE language model itself and results can help the NLP community renew the interests of deep generative models in the era of large-scale pre-training, and make these principled methods more practical.
Multi-View Learning for Vision-and-Language Navigation
Learning to navigate in a visual environment following natural language instructions is a challenging task because natural language instructions are highly variable, ambiguous, and under-specified.
UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training
We propose to pre-train a unified language model for both autoencoding and partially autoregressive language modeling tasks using a novel training procedure, referred to as a pseudo-masked language model (PMLM).
Ranked #4 on
Question Generation
on SQuAD1.1
(using extra training data)
Few-shot Natural Language Generation for Task-Oriented Dialog
It is pre-trained on a large set of annotated NLG corpus to acquire the controllable generation ability, and fine-tuned with only a few domain-specific labels to adapt to new domains.
Ranked #4 on
Data-to-Text Generation
on MULTIWOZ 2.1
Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training
By training on a large amount of image-text-action triplets in a self-supervised learning manner, the pre-trained model provides generic representations of visual environments and language instructions.
Ranked #1 on
Visual Navigation
on Help, Anna! (HANNA)
The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding
We present MT-DNN, an open-source natural language understanding (NLU) toolkit that makes it easy for researchers and developers to train customized deep learning models.
ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems
We present ConvLab-2, an open-source toolkit that enables researchers to build task-oriented dialogue systems with state-of-the-art models, perform an end-to-end evaluation, and diagnose the weakness of systems.
PIQA: Reasoning about Physical Commonsense in Natural Language
Questions requiring this kind of physical commonsense pose a challenge to today's natural language understanding systems.
Ranked #36 on
Question Answering
on PIQA
Natural Language Understanding
Physical Commonsense Reasoning
+1
The Eighth Dialog System Technology Challenge
This paper introduces the Eighth Dialog System Technology Challenge.
SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization
However, due to limited data resources from downstream tasks and the extremely large capacity of pre-trained models, aggressive fine-tuning often causes the adapted model to overfit the data of downstream tasks and forget the knowledge of the pre-trained model.
Ranked #1 on
Natural Language Inference
on QNLI
Contrastive Multi-document Question Generation
In the SL stage, a single-document question generator is trained.
DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation
We present a large, tunable neural conversational response generation model, DialoGPT (dialogue generative pre-trained transformer).
HUBERT Untangles BERT to Improve Transfer across NLP Tasks
We introduce HUBERT which combines the structured-representational power of Tensor-Product Representations (TPRs) and BERT, a pre-trained bidirectional Transformer language model.
Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving
We incorporate Tensor-Product Representations within the Transformer in order to better support the explicit representation of relation structure.
Ranked #1 on
Question Answering
on Mathematics Dataset
