Search Results for author:
Found 38 papers, 15 papers with code
Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG
Retrieval-augmented generation (RAG) empowers large language models (LLMs) to utilize external knowledge sources.
CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL
In tackling the challenges of large language model (LLM) performance for Text-to-SQL tasks, we introduce CHASE-SQL, a new framework that employs innovative strategies, using test-time compute in multi-agent modeling to improve candidate generation and selection.
SQL-GEN: Bridging the Dialect Gap for Text-to-SQL Via Synthetic Data And Model Merging
This leads to a versatile model optimized for multiple SQL dialects, outperforming single-dialect models and significantly enhancing overall performance.
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.
Ranked #31 on
Visual Question Answering
on MM-Vet
BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval
To better benchmark retrieval on such challenging queries, we introduce BRIGHT, the first text retrieval benchmark that requires intensive reasoning to retrieve relevant documents.
Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization
We conclude that studying exemplar optimization both as a standalone method and its optimal combination with instruction optimization remain a crucial aspect of APO and deserve greater consideration in future research, even in the era of highly capable instruction-following models.
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.
Business Metric-Aware Forecasting for Inventory Management
We explore a wide range of plausible cost trade-off scenarios, and empirically demonstrate that end-to-end optimization often outperforms optimization of standard business-agnostic forecasting metrics (by up to 45. 7% for a simple scaling model, and up to 54. 0% for an LSTM encoder-decoder model).
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.
SLM: End-to-end Feature Selection via Sparse Learnable Masks
Feature selection has been widely used to alleviate compute requirements during training, elucidate model interpretability, and improve model generalizability.
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).
Ranked #39 on
Time Series Forecasting
on ETTh1 (336) Multivariate
(MAE metric)
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
Provable Membership Inference Privacy
However, DP's strong theoretical guarantees often come at the cost of a large drop in its utility for machine learning, and DP guarantees themselves can be difficult to interpret.
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.
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.
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 #89 on
Image Classification
on CIFAR-10
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.
Explaining Deep Neural Networks using Unsupervised Clustering
We propose a novel method to explain trained deep neural networks (DNNs), by distilling them into surrogate models using unsupervised clustering.
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.
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.
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.
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.
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
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.
Fast Spectrogram Inversion using Multi-head Convolutional Neural Networks
We propose the multi-head convolutional neural network (MCNN) architecture for waveform synthesis from spectrograms.
Neural Voice Cloning with a Few Samples
Speaker adaptation is based on fine-tuning a multi-speaker generative model with a few cloning samples.
Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning
We present Deep Voice 3, a fully-convolutional attention-based neural text-to-speech (TTS) system.
Convolutional Recurrent Neural Networks for Small-Footprint Keyword Spotting
Keyword spotting (KWS) constitutes a major component of human-technology interfaces.
Deep Voice: Real-time Neural Text-to-Speech
We present Deep Voice, a production-quality text-to-speech system constructed entirely from deep neural networks.
