Search Results for author:
Found 84 papers, 30 papers with code
SQL-GEN: Bridging the Dialect Gap for Text-to-SQL Via Synthetic Data And Model Merging
Text-to-SQL systems, which convert natural language queries into SQL commands, have seen significant progress primarily for the SQLite dialect.
CROME: Cross-Modal Adapters for Efficient Multimodal LLM
Multimodal Large Language Models (MLLMs) demonstrate remarkable image-language capabilities, but their widespread use faces challenges in cost-effective training and adaptation.
Re-Invoke: Tool Invocation Rewriting for Zero-Shot Tool Retrieval
Recent advances in large language models (LLMs) have enabled autonomous agents with complex reasoning and task-fulfillment capabilities using a wide range of tools.
Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization
Large language models (LLMs), even when specifically trained to process long input contexts, struggle to capture relevant information located in the middle of their input.
CaLM: Contrasting Large and Small Language Models to Verify Grounded Generation
Grounded generation aims to equip language models (LMs) with the ability to produce more credible and accountable responses by accurately citing verifiable sources.
Learned Feature Importance Scores for Automated Feature Engineering
Feature engineering has demonstrated substantial utility for many machine learning workflows, such as in the small data regime or when distribution shifts are severe.
Chain of Agents: Large Language Models Collaborating on Long-Context Tasks
Addressing the challenge of effectively processing long contexts has become a critical issue for Large Language Models (LLMs).
Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training
Large language models (LLMs) aligned through reinforcement learning from human feedback (RLHF) have quickly become one of the dominant paradigms for building intelligent conversational assistant agents.
Mitigating Object Hallucination via Data Augmented Contrastive Tuning
For a given factual token, we create a hallucinated token through generative data augmentation by selectively altering the ground-truth information.
Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning
The proposed FeatLLM framework only uses this simple predictive model with the discovered features at inference time.
CodecLM: Aligning Language Models with Tailored Synthetic Data
To this end, we introduce CodecLM, a general framework for adaptively generating high-quality synthetic data for LLM alignment with different downstream instruction distributions and LLMs.
Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding
We propose the Chain-of-Table framework, where tabular data is explicitly used in the reasoning chain as a proxy for intermediate thoughts.
Ranked #3 on
Table-based Fact Verification
on TabFact
TextGenSHAP: Scalable Post-hoc Explanations in Text Generation with Long Documents
Given their nature as black-boxes using complex reasoning processes on their inputs, it is inevitable that the demand for scalable and faithful explanations for LLMs' generated content will continue to grow.
Effective Large Language Model Adaptation for Improved Grounding and Citation Generation
Our framework tunes LLMs to selfground the claims in their responses and provide accurate citations to retrieved documents.
SQLPrompt: In-Context Text-to-SQL with Minimal Labeled Data
Text-to-SQL aims to automate the process of generating SQL queries on a database from natural language text.
COSTAR: Improved Temporal Counterfactual Estimation with Self-Supervised Learning
Estimation of temporal counterfactual outcomes from observed history is crucial for decision-making in many domains such as healthcare and e-commerce, particularly when randomized controlled trials (RCTs) suffer from high cost or impracticality.
Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs
Large language models (LLMs) have recently shown great advances in a variety of tasks, including natural language understanding and generation.
Search-Adaptor: Embedding Customization for Information Retrieval
Embeddings extracted by pre-trained Large Language Models (LLMs) have significant potential to improve information retrieval and search.
TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting
The past decade has witnessed significant advances in time series modeling with deep learning.
Ranked #11 on
Time Series Forecasting
on ETTh1 (336) Multivariate
PAITS: Pretraining and Augmentation for Irregularly-Sampled Time Series
In this paper, we present PAITS (Pretraining and Augmentation for Irregularly-sampled Time Series), a framework for identifying suitable pretraining strategies for sparse and irregularly sampled time series datasets.
Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models
Today, large language models (LLMs) are taught to use new tools by providing a few demonstrations of the tool's usage.
SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL (extended)
Text-to-SQL, the process of translating natural language into Structured Query Language (SQL), represents a transformative application of large language models (LLMs), potentially revolutionizing how humans interact with data.
LANISTR: Multimodal Learning from Structured and Unstructured Data
To bridge this gap, we propose LANISTR, an attention-based framework to learn from LANguage, Image, and STRuctured data.
Universal Self-Adaptive Prompting
A hallmark of modern large language models (LLMs) is their impressive general zero-shot and few-shot abilities, often elicited through in-context learning (ICL) via prompting.
Better Zero-Shot Reasoning with Self-Adaptive Prompting
Modern large language models (LLMs) have demonstrated impressive capabilities at sophisticated tasks, often through step-by-step reasoning similar to humans.
FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction
In FormNetV2, we introduce a centralized multimodal graph contrastive learning strategy to unify self-supervised pre-training for all modalities in one loss.
Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes
Third, we reduce both the model size and the amount of data required to outperform LLMs; our finetuned 770M T5 model outperforms the few-shot prompted 540B PaLM model using only 80% of available data on a benchmark, whereas standard finetuning the same T5 model struggles to match even by using 100% of the dataset.
ASPEST: Bridging the Gap Between Active Learning and Selective Prediction
In this work, we introduce a new learning paradigm, active selective prediction, which aims to query more informative samples from the shifted target domain while increasing accuracy and coverage.
TSMixer: An All-MLP Architecture for Time Series Forecasting
Extending them, in this paper, we investigate the capabilities of linear models for time-series forecasting and present Time-Series Mixer (TSMixer), a novel architecture designed by stacking multi-layer perceptrons (MLPs).
Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval
Existing methods rely on supervised learning of CIR models using labeled triplets consisting of the query image, text specification, and the target image.
Ranked #1 on
Zero-shot Image Retrieval
on ImageNet-R
Neural Spline Search for Quantile Probabilistic Modeling
Accurate estimation of output quantiles is crucial in many use cases, where it is desired to model the range of possibility.
SPADE: Semi-supervised Anomaly Detection under Distribution Mismatch
Semi-supervised anomaly detection is a common problem, as often the datasets containing anomalies are partially labeled.
Semi-supervised Anomaly Detection
Supervised Anomaly Detection
QueryForm: A Simple Zero-shot Form Entity Query Framework
Zero-shot transfer learning for document understanding is a crucial yet under-investigated scenario to help reduce the high cost involved in annotating document entities.
Test-Time Adaptation for Visual Document Understanding
For visual document understanding (VDU), self-supervised pretraining has been shown to successfully generate transferable representations, yet, effective adaptation of such representations to distribution shifts at test-time remains to be an unexplored area.
Invariant Structure Learning for Better Generalization and Causal Explainability
ISL splits the data into different environments, and learns a structure that is invariant to the target across different environments by imposing a consistency constraint.
Interpretable Mixture of Experts
In addition to constituting a standalone inherently-interpretable architecture, IME has the premise of being integrated with existing DNNs to offer interpretability to a subset of samples while maintaining the accuracy of the DNNs.
Prefix Conditioning Unifies Language and Label Supervision
In experiments, we show that this simple technique improves the performance in zero-shot image recognition accuracy and robustness to the image-level distribution shift.
DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning
Continual learning aims to enable a single model to learn a sequence of tasks without catastrophic forgetting.
Learning Instance-Specific Adaptation for Cross-Domain Segmentation
We propose a test-time adaptation method for cross-domain image segmentation.
FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction
Sequence modeling has demonstrated state-of-the-art performance on natural language and document understanding tasks.
Data-Efficient and Interpretable Tabular Anomaly Detection
In addition, the proposed framework, DIAD, can incorporate a small amount of labeled data to further boost anomaly detection performances in semi-supervised settings.
Decoupling Local and Global Representations of Time Series
Learning representations that capture the factors contributing to this variability enables a better understanding of the data via its underlying generative process and improves performance on downstream machine learning tasks.
Self-Adaptive Forecasting for Improved Deep Learning on Non-Stationary Time-Series
Real-world time-series datasets often violate the assumptions of standard supervised learning for forecasting -- their distributions evolve over time, rendering the conventional training and model selection procedures suboptimal.
Towards Group Robustness in the presence of Partial Group Labels
Such a requirement is impractical in situations where the data labeling efforts for minority or rare groups are significantly laborious or where the individuals comprising the dataset choose to conceal sensitive information.
Anomaly Clustering: Grouping Images into Coherent Clusters of Anomaly Types
We define a distance function between images, each of which is represented as a bag of embeddings, by the Euclidean distance between weighted averaged embeddings.
Learning to Prompt for Continual Learning
The mainstream paradigm behind continual learning has been to adapt the model parameters to non-stationary data distributions, where catastrophic forgetting is the central challenge.
Unifying Distribution Alignment as a Loss for Imbalanced Semi-supervised Learning
While remarkable progress in imbalanced supervised learning has been made recently, less attention has been given to the setting of imbalanced semi-supervised learning (SSL) where not only is a few labeled data provided, but the underlying data distribution can be severely imbalanced.
Invariant Learning with Partial Group Labels
Such a requirement is impractical in situations where the data labelling efforts for minority or rare groups is significantly laborious or where the individuals comprising the dataset choose to conceal sensitive information.
Learning Fast Sample Re-weighting Without Reward Data
Training sample re-weighting is an effective approach for tackling data biases such as imbalanced and corrupted labels.
ROPE: Reading Order Equivariant Positional Encoding for Graph-based Document Information Extraction
Natural reading orders of words are crucial for information extraction from form-like documents.
Controlling Neural Networks with Rule Representations
The key aspect of DeepCTRL is that it does not require retraining to adapt the rule strength -- at inference, the user can adjust it based on the desired operation point on accuracy vs. rule verification ratio.
Self-supervise, Refine, Repeat: Improving Unsupervised Anomaly Detection
We demonstrate our method on various unsupervised AD tasks with image and tabular data.
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding
Hierarchical structures are popular in recent vision transformers, however, they require sophisticated designs and massive datasets to work well.
Ranked #91 on
Image Classification
on CIFAR-10
CutPaste: Self-Supervised Learning for Anomaly Detection and Localization
We aim at constructing a high performance model for defect detection that detects unknown anomalous patterns of an image without anomalous data.
Ranked #68 on
Anomaly Detection
on MVTec AD
Learning from Weakly-labeled Web Videos via Exploring Sub-Concepts
To address this issue, we introduce a new method for pre-training video action recognition models using queried web videos.
Exploring Sub-Pseudo Labels for Learning from Weakly-Labeled Web Videos
To address this issue, we introduce a new method for pre-training video action recognition models using queried web videos.
Differentiable Top-k with Optimal Transport
Finding the k largest or smallest elements from a collection of scores, i. e., top-k operation, is an important model component widely used in information retrieval, machine learning, and data mining.
Learning and Evaluating Representations for Deep One-class Classification
We first learn self-supervised representations from one-class data, and then build one-class classifiers on learned representations.
Ranked #8 on
Anomaly Detection
on One-class CIFAR-100
PseudoSeg: Designing Pseudo Labels for Semantic Segmentation
We demonstrate the effectiveness of the proposed pseudo-labeling strategy in both low-data and high-data regimes.
Differentiable Top-$k$ with Optimal Transport
The top-$k$ operation, i. e., finding the $k$ largest or smallest elements from a collection of scores, is an important model component, which is widely used in information retrieval, machine learning, and data mining.
Interpretable Sequence Learning for COVID-19 Forecasting
We propose a novel approach that integrates machine learning into compartmental disease modeling to predict the progression of COVID-19.
A Simple Semi-Supervised Learning Framework for Object Detection
Semi-supervised learning (SSL) has a potential to improve the predictive performance of machine learning models using unlabeled data.
Ranked #13 on
Semi-Supervised Object Detection
on COCO 100% labeled data
(using extra training data)
Differentiable Top-k Operator with Optimal Transport
The top-k operation, i. e., finding the k largest or smallest elements from a collection of scores, is an important model component, which is widely used in information retrieval, machine learning, and data mining.
Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting
Multi-horizon forecasting problems often contain a complex mix of inputs -- including static (i. e. time-invariant) covariates, known future inputs, and other exogenous time series that are only observed historically -- without any prior information on how they interact with the target.
Distance-Based Learning from Errors for Confidence Calibration
To circumvent this by inferring the distance for every test sample, we propose to train a confidence model jointly with the classification model.
On Completeness-aware Concept-Based Explanations in Deep Neural Networks
Next, we propose a concept discovery method that aims to infer a complete set of concepts that are additionally encouraged to be interpretable, which addresses the limitations of existing methods on concept explanations.
Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost
Active learning (AL) combines data labeling and model training to minimize the labeling cost by prioritizing the selection of high value data that can best improve model performance.
Generative Modeling for Small-Data Object Detection
This paper explores object detection in the small data regime, where only a limited number of annotated bounding boxes are available due to data rarity and annotation expense.
Distilling Effective Supervision from Severe Label Noise
For instance, on CIFAR100 with a $40\%$ uniform noise ratio and only 10 trusted labeled data per class, our method achieves $80. 2{\pm}0. 3\%$ classification accuracy, where the error rate is only $1. 4\%$ higher than a neural network trained without label noise.
LIMIS: Locally Interpretable Modeling using Instance-wise Subsampling
Understanding black-box machine learning models is crucial for their widespread adoption.
On Concept-Based Explanations in Deep Neural Networks
Next, we propose a concept discovery method that considers two additional constraints to encourage the interpretability of the discovered concepts.
Data Valuation using Reinforcement Learning
To adaptively learn data values jointly with the target task predictor model, we propose a meta learning framework which we name Data Valuation using Reinforcement Learning (DVRL).
Consistency-Based Semi-Supervised Active Learning: Towards Minimizing Labeling Budget
Active learning (AL) aims to integrate data labeling and model training in a unified way, and to minimize the labeling budget by prioritizing the selection of high value data that can best improve model performance.
A Simple yet Effective Baseline for Robust Deep Learning with Noisy Labels
Recently deep neural networks have shown their capacity to memorize training data, even with noisy labels, which hurts generalization performance.
Learning to Transfer Learn: Reinforcement Learning-Based Selection for Adaptive Transfer Learning
We propose a novel adaptive transfer learning framework, learning to transfer learn (L2TL), to improve performance on a target dataset by careful extraction of the related information from a source dataset.
TabNet: Attentive Interpretable Tabular Learning
We propose a novel high-performance and interpretable canonical deep tabular data learning architecture, TabNet.
Ranked #1 on
Poker Hand Classification
on Poker Hand
Inserting Videos into Videos
To synthesize a realistic video, the network renders each frame based on the current input and previous frames.
Harmonic Unpaired Image-to-image Translation
The recent direction of unpaired image-to-image translation is on one hand very exciting as it alleviates the big burden in obtaining label-intensive pixel-to-pixel supervision, but it is on the other hand not fully satisfactory due to the presence of artifacts and degenerated transformations.
ProtoAttend: Attention-Based Prototypical Learning
We propose a novel inherently interpretable machine learning method that bases decisions on few relevant examples that we call prototypes.
Learning from Simulated and Unsupervised Images through Adversarial Training
With recent progress in graphics, it has become more tractable to train models on synthetic images, potentially avoiding the need for expensive annotations.
Ranked #3 on
Image-to-Image Translation
on Cityscapes Labels-to-Photo
(Per-class Accuracy metric)
Personalizing Human Video Pose Estimation
The outcome is a substantial improvement in the pose estimates for the target video using the personalized ConvNet compared to the original generic ConvNet.
Towards Reading Hidden Emotions: A comparative Study of Spontaneous Micro-expression Spotting and Recognition Methods
For ME recognition, the performance of previous studies is low.
Flowing ConvNets for Human Pose Estimation in Videos
The objective of this work is human pose estimation in videos, where multiple frames are available.
