Search Results for author:
Found 67 papers, 25 papers with code
Few-Shot Class-Incremental Learning for Named Entity Recognition
In this work, we study a more challenging but practical problem, i. e., few-shot class-incremental learning for NER, where an NER model is trained with only few labeled samples of the new classes, without forgetting knowledge of the old ones.
Influence Diagram Bandits
We experiment with three structured bandit problems: cascading bandits, online learning to rank in the position-based model, and rank-1 bandits.
Learn When (not) to Trust Language Models: A Privacy-Centric Adaptive Model-Aware Approach
Despite their great success, the knowledge provided by the retrieval process is not always useful for improving the model prediction, since in some samples LLMs may already be quite knowledgeable and thus be able to answer the question correctly without retrieval.
Hallucination Diversity-Aware Active Learning for Text Summarization
Large Language Models (LLMs) have shown propensity to generate hallucinated outputs, i. e., texts that are factually incorrect or unsupported.
Uncertainty-aware Distributional Offline Reinforcement Learning
Offline reinforcement learning (RL) presents distinct challenges as it relies solely on observational data.
SciCapenter: Supporting Caption Composition for Scientific Figures with Machine-Generated Captions and Ratings
Crafting effective captions for figures is important.
Large Language Models and Causal Inference in Collaboration: A Comprehensive Survey
Causal inference has shown potential in enhancing the predictive accuracy, fairness, robustness, and explainability of Natural Language Processing (NLP) models by capturing causal relationships among variables.
Which LLM to Play? Convergence-Aware Online Model Selection with Time-Increasing Bandits
In this paper, we propose a time-increasing bandit algorithm TI-UCB, which effectively predicts the increase of model performances due to finetuning and efficiently balances exploration and exploitation in model selection.
CoRAL: Collaborative Retrieval-Augmented Large Language Models Improve Long-tail Recommendation
Based on the retrieved user-item interactions, the LLM can analyze shared and distinct preferences among users, and summarize the patterns indicating which types of users would be attracted by certain items.
Learning to Reduce: Optimal Representations of Structured Data in Prompting Large Language Models
The model learns to reduce the input context using On-Policy Reinforcement Learning and aims to improve the reasoning performance of a fixed LLM.
Foundation Models for Recommender Systems: A Survey and New Perspectives
Recently, Foundation Models (FMs), with their extensive knowledge bases and complex architectures, have offered unique opportunities within the realm of recommender systems (RSs).
Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes
Large language models (LLMs) have shown remarkable advances in language generation and understanding but are also prone to exhibiting harmful social biases.
Augment before You Try: Knowledge-Enhanced Table Question Answering via Table Expansion
Table question answering is a popular task that assesses a model's ability to understand and interact with structured data.
Discovering Low-rank Subspaces for Language-agnostic Multilingual Representations
While these results are promising, follow-up works found that, within the multilingual embedding spaces, there exists strong language identity information which hinders the expression of linguistic factors shared across languages.
CLAPP: Contrastive Language-Audio Pre-training in Passive Underwater Vessel Classification
Existing research on audio classification faces challenges in recognizing attributes of passive underwater vessel scenarios and lacks well-annotated datasets due to data privacy concerns.
Leveraging Graph Diffusion Models for Network Refinement Tasks
Most real-world networks are noisy and incomplete samples from an unknown target distribution.
YUAN 2.0: A Large Language Model with Localized Filtering-based Attention
In this work, we develop and release Yuan 2. 0, a series of large language models with parameters ranging from 2. 1 billion to 102. 6 billion.
Improving a Named Entity Recognizer Trained on Noisy Data with a Few Clean Instances
To achieve state-of-the-art performance, one still needs to train NER models on large-scale, high-quality annotated data, an asset that is both costly and time-intensive to accumulate.
ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search
It formulates the entire action space as a decision tree, where each node represents a possible API function call involved in a solution plan.
Bias and Fairness in Large Language Models: A Survey
Rapid advancements of large language models (LLMs) have enabled the processing, understanding, and generation of human-like text, with increasing integration into systems that touch our social sphere.
Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures
SurgVLP constructs a new contrastive learning objective to align video clip embeddings with the corresponding multiple text embeddings by bringing them together within a joint latent space.
FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedback
Captions are crucial for understanding scientific visualizations and documents.
Fairness-Aware Graph Neural Networks: A Survey
In this article, we examine and categorize fairness techniques for improving the fairness of GNNs.
Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels
Remarkably, by incorporating conditional information from the powerful CLIP model, our method can boost the current SOTA accuracy by 10-20 absolute points in many cases.
Ranked #1 on
Image Classification
on Food-101N
(using extra training data)
Few-Shot Dialogue Summarization via Skeleton-Assisted Prompt Transfer in Prompt Tuning
In this paper, we focus on improving the prompt transfer from dialogue state tracking to dialogue summarization and propose Skeleton-Assisted Prompt Transfer (SAPT), which leverages skeleton generation as extra supervision that functions as a medium connecting the distinct source and target task and resulting in the model's better consumption of dialogue state information.
Towards Building the Federated GPT: Federated Instruction Tuning
This repository offers a foundational framework for exploring federated fine-tuning of LLMs using heterogeneous instructions across diverse categories.
The Closeness of In-Context Learning and Weight Shifting for Softmax Regression
Large language models (LLMs) are known for their exceptional performance in natural language processing, making them highly effective in many human life-related or even job-related tasks.
Structured Dynamic Pricing: Optimal Regret in a Global Shrinkage Model
We consider dynamic pricing strategies in a streamed longitudinal data set-up where the objective is to maximize, over time, the cumulative profit across a large number of customer segments.
Weakly Supervised Temporal Convolutional Networks for Fine-grained Surgical Activity Recognition
In this work, we propose to use coarser and easier-to-annotate activity labels, namely phases, as weak supervision to learn step recognition with fewer step annotated videos.
CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection
This paper presents the CholecTriplet2022 challenge, which extends surgical action triplet modeling from recognition to detection.
Ranked #1 on
Action Triplet Detection
on CholecT50 (Challenge)
Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models
Based on this finding, we further propose a simple, light-weight image editing algorithm where the mixing weights of the two text embeddings are optimized for style matching and content preservation.
Reinforced Approximate Exploratory Data Analysis
Exploratory data analytics (EDA) is a sequential decision making process where analysts choose subsequent queries that might lead to some interesting insights based on the previous queries and corresponding results.
Direct Embedding of Temporal Network Edges via Time-Decayed Line Graphs
We present a simple method that avoids both shortcomings: construct the line graph of the network, which includes a node for each interaction, and weigh the edges of this graph based on the difference in time between interactions.
Hierarchical Conversational Preference Elicitation with Bandit Feedback
To achieve this, the recommender system conducts conversations with users, asking their preferences for different items or item categories.
Federated Online Clustering of Bandits
Contextual multi-armed bandit (MAB) is an important sequential decision-making problem in recommendation systems.
Comparison-based Conversational Recommender System with Relative Bandit Feedback
To enable users to provide comparative preferences during conversational interactions, we propose a novel comparison-based conversational recommender system.
Bundle MCR: Towards Conversational Bundle Recommendation
MCR, which uses a conversational paradigm to elicit user interests by asking user preferences on tags (e. g., categories or attributes) and handling user feedback across multiple rounds, is an emerging recommendation setting to acquire user feedback and narrow down the output space, but has not been explored in the context of bundle recommendation.
Dissecting Self-Supervised Learning Methods for Surgical Computer Vision
Correct transfer of these methods to surgery, as described and conducted in this work, leads to substantial performance gains over generic uses of SSL - up to 7. 4% on phase recognition and 20% on tool presence detection - as well as state-of-the-art semi-supervised phase recognition approaches by up to 14%.
Ranked #1 on
Semantic Segmentation
on Endoscapes
ChordMixer: A Scalable Neural Attention Model for Sequences with Different Lengths
Sequential data naturally have different lengths in many domains, with some very long sequences.
Ranked #4 on
Long-range modeling
on LRA
Paramixer: Parameterizing Mixing Links in Sparse Factors Works Better than Dot-Product Self-Attention
The overall computing cost of the new building block is as low as $O(N \log N)$.
Ranked #18 on
Long-range modeling
on LRA
CholecTriplet2021: A benchmark challenge for surgical action triplet recognition
In this paper, we present the challenge setup and assessment of the state-of-the-art deep learning methods proposed by the participants during the challenge.
Ranked #1 on
Action Triplet Recognition
on CholecT50 (Challenge)
(using extra training data)
Live Laparoscopic Video Retrieval with Compressed Uncertainty
Searching through large volumes of medical data to retrieve relevant information is a challenging yet crucial task for clinical care.
Active and Passive Hybrid Detection Method for Power CPS False Data Injection Attacks with Improved AKF and GRU-CNN
Taking account of the fact that the existing knowledge-driven detection process for FDIAs has been in a passive detection state for a long time and ignores the advantages of data-driven active capture of features, an active and passive hybrid detection method for power CPS FDIAs with improved adaptive Kalman filter (AKF) and convolutional neural networks (CNN) is proposed in this paper.
Classification of Long Sequential Data using Circular Dilated Convolutional Neural Networks
Recurrent Neural Networks, Transformers, and Convolutional Neural Networks are three major techniques for learning from sequential data.
Towards Language-Free Training for Text-to-Image Generation
One of the major challenges in training text-to-image generation models is the need of a large number of high-quality text-image pairs.
EI-CLIP: Entity-Aware Interventional Contrastive Learning for E-Commerce Cross-Modal Retrieval
recommendation, and marketing services.
Dynamic Exploitation Gaussian Bare-Bones Bat Algorithm for Optimal Reactive Power Dispatch to Improve the Safety and Stability of Power System
DeGBBBA is an advanced variant of GBBBA in which a modified Gaussian distribution is introduced so as to allow the dynamic adaptation of exploitation and exploitation in the proposed algorithm.
LAFITE: Towards Language-Free Training for Text-to-Image Generation
One of the major challenges in training text-to-image generation models is the need of a large number of high-quality image-text pairs.
Ranked #2 on
Text-to-Image Generation
on Multi-Modal-CelebA-HQ
Deconfounded and Explainable Interactive Vision-Language Retrieval of Complex Scenes
Vision-language explanations in the systems can better guide users to provide feedback and thus improve the retrieval.
Yuan 1.0: Large-Scale Pre-trained Language Model in Zero-Shot and Few-Shot Learning
With this method, Yuan 1. 0, the current largest singleton language model with 245B parameters, achieves excellent performance on thousands GPUs during training, and the state-of-the-art results on NLP tasks.
Comparative Validation of Machine Learning Algorithms for Surgical Workflow and Skill Analysis with the HeiChole Benchmark
PURPOSE: Surgical workflow and skill analysis are key technologies for the next generation of cognitive surgical assistance systems.
Ranked #1 on
Surgical phase recognition
on HeiChole Benchmark
Sparse Factorization of Large Square Matrices
The sparse factorization method is tested for a variety of synthetic and real-world square matrices.
Ranked #17 on
Long-range modeling
on LRA
Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos
To achieve this task, we introduce our new model, the Rendezvous (RDV), which recognizes triplets directly from surgical videos by leveraging attention at two different levels.
Ranked #1 on
Action Triplet Recognition
on CholecT50
Multi-Task Temporal Convolutional Networks for Joint Recognition of Surgical Phases and Steps in Gastric Bypass Procedures
Conclusion: In this work, we present a multi-task multi-stage temporal convolutional network for surgical activity recognition, which shows improved results compared to single-task models on the Bypass40 gastric bypass dataset with multi-level annotations.
Encode the Unseen: Predictive Video Hashing for Scalable Mid-Stream Retrieval
This paper tackles a new problem in computer vision: mid-stream video-to-video retrieval.
Recognition of Instrument-Tissue Interactions in Endoscopic Videos via Action Triplets
Recognition of surgical activity is an essential component to develop context-aware decision support for the operating room.
Ranked #1 on
Action Triplet Recognition
on CholecT40
Influence Diagram Bandits: Variational Thompson Sampling for Structured Bandit Problems
We propose a novel framework for structured bandits, which we call an influence diagram bandit.
Reward Constrained Interactive Recommendation with Natural Language Feedback
Text-based interactive recommendation provides richer user feedback and has demonstrated advantages over traditional interactive recommender systems.
Hyper-Parameter Optimization: A Review of Algorithms and Applications
This study next reviews major services and toolkits for HPO, comparing their support for state-of-the-art searching algorithms, feasibility with major deep learning frameworks, and extensibility for new modules designed by users.
Text-Based Interactive Recommendation via Constraint-Augmented Reinforcement Learning
Text-based interactive recommendation provides richer user preferences and has demonstrated advantages over traditional interactive recommender systems.
Figure Captioning with Reasoning and Sequence-Level Training
In this work, we investigate the problem of figure captioning where the goal is to automatically generate a natural language description of the figure.
Privacy Partitioning: Protecting User Data During the Deep Learning Inference Phase
We present a practical method for protecting data during the inference phase of deep learning based on bipartite topology threat modeling and an interactive adversarial deep network construction.
Learning from a tiny dataset of manual annotations: a teacher/student approach for surgical phase recognition
Vision algorithms capable of interpreting scenes from a real-time video stream are necessary for computer-assisted surgery systems to achieve context-aware behavior.
Understanding and Improving Recurrent Networks for Human Activity Recognition by Continuous Attention
To address these issues, we propose two attention models for human activity recognition: temporal attention and sensor attention.
Semi-Supervised Convolutional Neural Networks for Human Activity Recognition
Labeled data used for training activity recognition classifiers are usually limited in terms of size and diversity.
Customized Nonlinear Bandits for Online Response Selection in Neural Conversation Models
Moreover, we report encouraging response selection performance of the proposed neural bandit model using the Recall@k metric for a small set of online training samples.
SpectralLeader: Online Spectral Learning for Single Topic Models
We study the problem of learning a latent variable model from a stream of data.
