Search Results for author:
Found 16 papers, 7 papers with code
ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation
We adopt a weakly-supervised approach to directly generate visual event structures from captions for ViStruct training, capitalizing on abundant image-caption pairs from the web.
Prudent Silence or Foolish Babble? Examining Large Language Models' Responses to the Unknown
When presented with such unanswerable questions, an LLM should appropriately convey uncertainty, and be able to challenge the premise and refuse to generate a response.
R-Tuning: Teaching Large Language Models to Refuse Unknown Questions
This approach is formalized by first identifying the knowledge gap between parametric knowledge and the instruction tuning data.
Defining a New NLP Playground
The recent explosion of performance of large language models (LLMs) has changed the field of Natural Language Processing (NLP) more abruptly and seismically than any other shift in the field's 80-year history.
CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets
It creates toolsets specifically curated for the tasks and equips LLMs with a component that retrieves tools from these sets to enhance their capability to solve complex tasks.
MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback
However, current evaluation protocols often emphasize benchmark performance with single-turn exchanges, neglecting the nuanced interactions among the user, LLMs, and external tools, while also underestimating the importance of natural language feedback from users.
Making Pre-trained Language Models both Task-solvers and Self-calibrators
In this work, we consider the practical scenario that we need to effectively utilize training samples to make PLMs both task-solvers and self-calibrators.
LeTI: Learning to Generate from Textual Interactions
LeTI iteratively fine-tunes the model, using the LM objective, on a concatenation of natural language instructions, LM-generated programs, and textual feedback, which is only provided when the generated program fails to solve the task.
ECG-CL: A Comprehensive Electrocardiogram Interpretation Method Based on Continual Learning
From the perspective of intelligent wearable applications, the possibility of a comprehensive ECG interpretation algorithm based on single-lead ECGs is also confirmed.
POTATO: The Portable Text Annotation Tool
We present POTATO, the Portable text annotation tool, a free, fully open-sourced annotation system that 1) supports labeling many types of text and multimodal data; 2) offers easy-to-configure features to maximize the productivity of both deployers and annotators (convenient templates for common ML/NLP tasks, active learning, keypress shortcuts, keyword highlights, tooltips); and 3) supports a high degree of customization (editable UI, inserting pre-screening questions, attention and qualification tests).
Code4Struct: Code Generation for Few-Shot Event Structure Prediction
As a case study, we formulate Event Argument Extraction (EAE) as converting text into event-argument structures that can be represented as a class object using code.
A Causal Intervention Scheme for Semantic Segmentation of Quasi-periodic Cardiovascular Signals
To address this issue, we establish a structural causal model as the foundation to customize the intervention approaches on Am and Ar, respectively.
An animated picture says at least a thousand words: Selecting Gif-based Replies in Multimodal Dialog
Online conversations include more than just text.
Ranked #1 on
Multimodal GIF Dialog
on GIF Reply Dataset
Towards Scalable Distributed Training of Deep Learning on Public Cloud Clusters
Distributed training techniques have been widely deployed in large-scale deep neural networks (DNNs) training on dense-GPU clusters.
Sequence-to-Sequence Load Disaggregation Using Multi-Scale Residual Neural Network
Secondly, we propose dilated convolution to curtail the excessive quantity of model parameters and obtain bigger receptive field, and multi-scale structure to learn mixed data features in a more targeted way.
Temporal-Framing Adaptive Network for Heart Sound Segmentation without Prior Knowledge of State Duration
Moreover, the TFAN-based method achieved an overall F1 score of 99. 2%, 94. 4%, 91. 4% on LEVEL-I, -II and -III data respectively, compared to 98. 4%, 88. 54% and 79. 80% for the current state-of-the-art method.
