Search Results for author:
Found 275 papers, 79 papers with code
Surrogate Signals from Format and Length: Reinforcement Learning for Solving Mathematical Problems without Ground Truth Answers
The resulting GRPO approach, leveraging format-length surrogate signals, not only matches but surpasses the performance of the standard GRPO algorithm relying on ground truth answers in certain scenarios, achieving 40. 0\% accuracy on AIME2024 with a 7B base model.
Minimalist Softmax Attention Provably Learns Constrained Boolean Functions
We study the computational limits of learning $k$-bit Boolean functions (specifically, $\mathrm{AND}$, $\mathrm{OR}$, and their noisy variants), using a minimalist single-head softmax-attention mechanism, where $k=\Theta(d)$ relevant bits are selected from $d$ inputs.
A Survey of Large Language Models for Text-Guided Molecular Discovery: from Molecule Generation to Optimization
Large language models (LLMs) are introducing a paradigm shift in molecular discovery by enabling text-guided interaction with chemical spaces through natural language, symbolic notations, with emerging extensions to incorporate multi-modal inputs.
Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought
As Large Language Models (LLMs) rapidly advance, we introduce Hunyuan-TurboS, a novel large hybrid Transformer-Mamba Mixture of Experts (MoE) model.
GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Models
We propose the first unified adversarial attack benchmark for Genomic Foundation Models (GFMs), named GenoArmory.
VIViT: Variable-Input Vision Transformer Framework for 3D MR Image Segmentation
Self-supervised pretrain techniques have been widely used to improve the downstream tasks' performance.
Fast and Low-Cost Genomic Foundation Models via Outlier Removal
Unlike existing GFM benchmarks, GERM offers the first comprehensive evaluation framework to systematically assess the vulnerability of GFMs to adversarial attacks.
Attention Mechanism, Max-Affine Partition, and Universal Approximation
We establish the universal approximation capability of single-layer, single-head self- and cross-attention mechanisms with minimal attached structures.
Universal Approximation with Softmax Attention
We prove that with linear transformations, both (i) two-layer self-attention and (ii) one-layer self-attention followed by a softmax function are universal approximators for continuous sequence-to-sequence functions on compact domains.
AdaViT: Adaptive Vision Transformer for Flexible Pretrain and Finetune with Variable 3D Medical Image Modalities
Pretrain techniques, whether supervised or self-supervised, are widely used in deep learning to enhance model performance.
MetaSpatial: Reinforcing 3D Spatial Reasoning in VLMs for the Metaverse
We present MetaSpatial, the first reinforcement learning (RL)-based framework designed to enhance 3D spatial reasoning in vision-language models (VLMs), enabling real-time 3D scene generation without the need for hard-coded optimizations.
AI-assisted Early Detection of Pancreatic Ductal Adenocarcinoma on Contrast-enhanced CT
However, due to the lack of early and disease-specific symptoms, most patients with PDAC are diagnosed at an advanced disease stage.
A Non-contrast Head CT Foundation Model for Comprehensive Neuro-Trauma Triage
Recent advancements in AI and medical imaging offer transformative potential in emergency head CT interpretation for reducing assessment times and improving accuracy in the face of an increasing request of such scans and a global shortage in radiologists.
Baichuan-M1: Pushing the Medical Capability of Large Language Models
The current generation of large language models (LLMs) is typically designed for broad, general-purpose applications, while domain-specific LLMs, especially in vertical fields like medicine, remain relatively scarce.
Can Domain Experts Rely on AI Appropriately? A Case Study on AI-Assisted Prostate Cancer MRI Diagnosis
Building on existing tools for teaching prostate cancer diagnosis, we develop an interface and conduct two experiments to study how AI assistance and performance feedback shape the decision making of domain experts.
Automating High Quality RT Planning at Scale
Radiotherapy (RT) planning is complex, subjective, and time-intensive.
Self Pre-training with Adaptive Mask Autoencoders for Variable-Contrast 3D Medical Imaging
To address this limitation, we propose a 3D Adaptive Masked Autoencoders (AMAE) architecture that accommodates a variable number of 3D input contrasts per subject.
Dynamic Multimodal Fusion via Meta-Learning Towards Micro-Video Recommendation
In this paper, we develop a novel meta-learning-based multimodal fusion framework called Meta Multimodal Fusion (MetaMMF), which dynamically assigns parameters to the multimodal fusion function for each micro-video during its representation learning.
A Text-Based Knowledge-Embedded Soft Sensing Modeling Approach for General Industrial Process Tasks Based on Large Language Model
To address these challenges, we propose a general framework named LLM-TKESS (large language model for text-based knowledge-embedded soft sensing), harnessing the powerful general problem-solving capabilities, cross-modal knowledge transfer abilities, and few-shot capabilities of LLM for enhanced soft sensing modeling.
Do Code LLMs Understand Design Patterns?
Code Large Language Models (LLMs) demonstrate great versatility in adapting to various downstream tasks, including code generation and completion, as well as bug detection and fixing.
A Soft Sensor Method with Uncertainty-Awareness and Self-Explanation Based on Large Language Models Enhanced by Domain Knowledge Retrieval
To achieve this, we propose a novel framework called the Few-shot Uncertainty-aware and self-Explaining Soft Sensor (LLM-FUESS), which includes the Zero-shot Auxiliary Variable Selector (LLM-ZAVS) and the Uncertainty-aware Few-shot Soft Sensor (LLM-UFSS).
Transformers Simulate MLE for Sequence Generation in Bayesian Networks
We demonstrate that there exists a simple transformer model that can (i) estimate the conditional probabilities of the Bayesian network according to the context, and (ii) autoregressively generate a new sample according to the Bayesian network with estimated conditional probabilities.
Learning Spectral Methods by Transformers
In this work, we study the capacities of Transformers in performing unsupervised learning.
Improving Accuracy and Calibration via Differentiated Deep Mutual Learning
Deep Neural Networks (DNNs) have achieved remarkable success in a variety of tasks, particularly in terms of prediction accuracy.
AlignAb: Pareto-Optimal Energy Alignment for Designing Nature-Like Antibodies
We present a three-stage framework for training deep learning models specializing in antibody sequence-structure co-design.
Adaptive Batch Size Schedules for Distributed Training of Language Models with Data and Model Parallelism
Despite this dilemma, the common practice of choosing batch sizes in language model training often prioritizes training efficiency -- employing either constant large sizes with data parallelism or implementing batch size warmup schedules.
EGSRAL: An Enhanced 3D Gaussian Splatting based Renderer with Automated Labeling for Large-Scale Driving Scene
To address these issues, we propose EGSRAL, a 3D GS-based method that relies solely on training images without extra annotations.
FTP: A Fine-grained Token-wise Pruner for Large Language Models via Token Routing
To address these issues, we propose a fine-grained token-wise pruning approach for the LLMs, which presents a learnable router to adaptively identify the less important tokens and skip them across model blocks to reduce computational cost during inference.
On Statistical Rates of Conditional Diffusion Transformers: Approximation, Estimation and Minimax Optimality
We investigate the approximation and estimation rates of conditional diffusion transformers (DiTs) with classifier-free guidance.
Transformers are Deep Optimizers: Provable In-Context Learning for Deep Model Training
We investigate the transformer's capability for in-context learning (ICL) to simulate the training process of deep models.
Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency
Our key contributions are prompt tuning on \textit{single-head} transformers with only a \textit{single} self-attention layer: (i) is universal, and (ii) supports efficient (even almost-linear time) algorithms under the Strong Exponential Time Hypothesis (SETH).
One-Layer Transformer Provably Learns One-Nearest Neighbor In Context
Transformers have achieved great success in recent years.
On Differentially Private String Distances
Given a database of bit strings $A_1,\ldots, A_m\in \{0, 1\}^n$, a fundamental data structure task is to estimate the distances between a given query $B\in \{0, 1\}^n$ with all the strings in the database.
Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent
In this paper, we introduce Hunyuan-Large, which is currently the largest open-source Transformer-based mixture of experts model, with a total of 389 billion parameters and 52 billion activation parameters, capable of handling up to 256K tokens.
Statistical Guarantees for Lifelong Reinforcement Learning using PAC-Bayes Theory
Lifelong reinforcement learning (RL) has been developed as a paradigm for extending single-task RL to more realistic, dynamic settings.
Global Convergence in Training Large-Scale Transformers
First, we construct the mean-field limit of large-scale Transformers, showing that as the model width and depth go to infinity, gradient flow converges to the Wasserstein gradient flow, which is represented by a partial differential equation.
Provably Optimal Memory Capacity for Modern Hopfield Models: Transformer-Compatible Dense Associative Memories as Spherical Codes
We show that the optimal capacity of KHMs occurs when the feature space allows memories to form an optimal spherical code.
TGCA-PVT: Topic-Guided Context-Aware Pyramid Vision Transformer for Sticker Emotion Recognition
Our approach encompasses a novel topic-guided context-aware module and a topic-guided attention mechanism, enabling the extraction of comprehensive topic context features from stickers sharing the same topic ID, significantly enhancing emotion recognition accuracy.
Sequential LLM Framework for Fashion Recommendation
The fashion industry is one of the leading domains in the global e-commerce sector, prompting major online retailers to employ recommendation systems for product suggestions and customer convenience.
Let's Ask GNN: Empowering Large Language Model for Graph In-Context Learning
Textual Attributed Graphs (TAGs) are crucial for modeling complex real-world systems, yet leveraging large language models (LLMs) for TAGs presents unique challenges due to the gap between sequential text processing and graph-structured data.
AdaptDiff: Cross-Modality Domain Adaptation via Weak Conditional Semantic Diffusion for Retinal Vessel Segmentation
Subsequently, we sample on the target domain with binary vessel masks from the source domain to get paired data, i. e., target domain synthetic images conditioned on the binary vessel map.
BIPEFT: Budget-Guided Iterative Search for Parameter Efficient Fine-Tuning of Large Pretrained Language Models
Parameter Efficient Fine-Tuning (PEFT) offers an efficient solution for fine-tuning large pretrained language models for downstream tasks.
Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?
Code completion, a key downstream task in code generation, is one of the most frequent and impactful methods for enhancing developer productivity in software development.
Scalable Multi-agent Reinforcement Learning for Factory-wide Dynamic Scheduling
Real-time dynamic scheduling is a crucial but notoriously challenging task in modern manufacturing processes due to its high decision complexity.
Multi-agent Reinforcement Learning
reinforcement-learning
+3
SoK: Security and Privacy Risks of Healthcare AI
The integration of artificial intelligence (AI) and machine learning (ML) into healthcare systems holds great promise for enhancing patient care and care delivery efficiency; however, it also exposes sensitive data and system integrity to potential cyberattacks.
Influence of Early through Late Fusion on Pancreas Segmentation from Imperfectly Registered Multimodal MRI
We trained a collection of basic UNets with different fusion points, spanning from early to late, to assess how early through late fusion influenced segmentation performance on imperfectly aligned images.
Differentially Private Kernel Density Estimation
In this paper, we improve the best previous result [Backurs, Lin, Mahabadi, Silwal, and Tarnawski, ICLR 2024] in three aspects: - We reduce query time by a factor of $\alpha^{-1} \log n$.
Deep Learning-based Unsupervised Domain Adaptation via a Unified Model for Prostate Lesion Detection Using Multisite Bi-parametric MRI Datasets
This method translates diffusion-weighted imaging (DWI) acquisitions, including apparent diffusion coefficient (ADC) and individual DW images acquired using various b-values, to align with the style of images acquired using b-values recommended by Prostate Imaging Reporting and Data System (PI-RADS) guidelines.
PatchFinder: A Two-Phase Approach to Security Patch Tracing for Disclosed Vulnerabilities in Open-Source Software
In this paper, we propose PatchFinder, a two-phase framework with end-to-end correlation learning for better-tracing security patches.
On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs)
For backward computation, we leverage the low-rank structure within the gradient computation of DiTs training for possible algorithmic speedup.
Predicting fluorescent labels in label-free microscopy images with pix2pix and adaptive loss in Light My Cells challenge
Recently, in silico labeling has emerged as a promising alternative, aiming to use machine learning models to directly predict the fluorescently labeled images from label-free microscopy.
Communication-Efficient Adaptive Batch Size Strategies for Distributed Local Gradient Methods
Despite an understanding of their convergence and the importance of batch sizes for training efficiency and generalization, optimal batch sizes for local gradient methods are difficult to determine.
Enhancing Single-Slice Segmentation with 3D-to-2D Unpaired Scan Distillation
2D single-slice abdominal computed tomography (CT) enables the assessment of body habitus and organ health with low radiation exposure.
Full-ECE: A Metric For Token-level Calibration on Large Language Models
Deep Neural Networks (DNNs) excel in various domains but face challenges in providing accurate uncertainty estimates, which are crucial for high-stakes applications.
Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey
Large Language Models (LLMs) have achieved unparalleled success across diverse language modeling tasks in recent years.
Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models
We study the computational limits of Low-Rank Adaptation (LoRA) for finetuning transformer-based models using fine-grained complexity theory.
Decoupled Alignment for Robust Plug-and-Play Adaptation
We introduce a low-resource safety enhancement method for aligning large language models (LLMs) without the need for supervised fine-tuning (SFT) or reinforcement learning from human feedback (RLHF).
Enhancing Jailbreak Attack Against Large Language Models through Silent Tokens
Attackers carefully craft jailbreaking prompts such that a target LLM will respond to the harmful question.
Accurate and Reliable Predictions with Mutual-Transport Ensemble
Deep Neural Networks (DNNs) have achieved remarkable success in a variety of tasks, especially when it comes to prediction accuracy.
Conv-CoA: Improving Open-domain Question Answering in Large Language Models via Conversational Chain-of-Action
Methodologically, we propose a resource-efficiency Hopfield retriever to enhance the efficiency and accuracy of conversational information retrieval within our actions.
HeteGraph-Mamba: Heterogeneous Graph Learning via Selective State Space Model
We propose a heterogeneous graph mamba network (HGMN) as the first exploration in leveraging the selective state space models (SSSMs) for heterogeneous graph learning.
Input Snapshots Fusion for Scalable Discrete Dynamic Graph Nerual Networks
Additionally, for link prediction tasks on discrete dynamic graphs, the requirement of substantial GPU memory to store embeddings of all nodes hinders the scalability of existing models.
Liberating Seen Classes: Boosting Few-Shot and Zero-Shot Text Classification via Anchor Generation and Classification Reframing
Few-shot and zero-shot text classification aim to recognize samples from novel classes with limited labeled samples or no labeled samples at all.
MMGRec: Multimodal Generative Recommendation with Transformer Model
Multimodal recommendation aims to recommend user-preferred candidates based on her/his historically interacted items and associated multimodal information.
EIVEN: Efficient Implicit Attribute Value Extraction using Multimodal LLM
To address these issues, we introduce EIVEN, a data- and parameter-efficient generative framework that pioneers the use of multimodal LLM for implicit attribute value extraction.
Nonparametric Modern Hopfield Models
We present a nonparametric construction for deep learning compatible modern Hopfield models and utilize this framework to debut an efficient variant.
Outlier-Efficient Hopfield Layers for Large Transformer-Based Models
We introduce an Outlier-Efficient Modern Hopfield Model (termed $\mathrm{OutEffHop}$) and use it to address the outlier inefficiency problem of {training} gigantic transformer-based models.
Ranked #1 on
Quantization
on Wiki-40B
Uniform Memory Retrieval with Larger Capacity for Modern Hopfield Models
Specifically, we accomplish this by constructing a separation loss $\mathcal{L}_\Phi$ that separates the local minima of kernelized energy by separating stored memory patterns in kernel space.
BiSHop: Bi-Directional Cellular Learning for Tabular Data with Generalized Sparse Modern Hopfield Model
We introduce the \textbf{B}i-Directional \textbf{S}parse \textbf{Hop}field Network (\textbf{BiSHop}), a novel end-to-end framework for deep tabular learning.
Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models
We present a Chain-of-Action (CoA) framework for multimodal and retrieval-augmented Question-Answering (QA).
Ranked #1 on
Question Answering
on TruthfulQA
(EM metric)
USE: Dynamic User Modeling with Stateful Sequence Models
Furthermore, we introduce a novel training objective named future W-behavior prediction to transcend the limitations of next-token prediction by forecasting a broader horizon of upcoming user behaviors.
On Languaging a Simulation Engine
Language model intelligence is revolutionizing the way we program materials simulations.
AdAdaGrad: Adaptive Batch Size Schemes for Adaptive Gradient Methods
The choice of batch sizes in minibatch stochastic gradient optimizers is critical in large-scale model training for both optimization and generalization performance.
VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models
Correspondingly, we propose a novel VQAttack model, which can iteratively generate both image and text perturbations with the designed modules: the large language model (LLM)-enhanced image attack and the cross-modal joint attack module.
DNABERT-S: Pioneering Species Differentiation with Species-Aware DNA Embeddings
We introduce DNABERT-S, a tailored genome model that develops species-aware embeddings to naturally cluster and segregate DNA sequences of different species in the embedding space.
On Computational Limits of Modern Hopfield Models: A Fine-Grained Complexity Analysis
Specifically, we establish an upper bound criterion for the norm of input query patterns and memory patterns.
HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Text
Black-box hard-label adversarial attack on text is a practical and challenging task, as the text data space is inherently discrete and non-differentiable, and only the predicted label is accessible.
Two Heads Are Better Than One: Integrating Knowledge from Knowledge Graphs and Large Language Models for Entity Alignment
The final prediction of the equivalent entity is derived from the LLM's output.
LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs' Vulnerability Reasoning
In this paper, we aim to decouple LLMs' vulnerability reasoning from other capabilities, such as vulnerability knowledge adoption, context information retrieval, and advanced prompt schemes.
Automated Fusion of Multimodal Electronic Health Records for Better Medical Predictions
The widespread adoption of Electronic Health Record (EHR) systems in healthcare institutes has generated vast amounts of medical data, offering significant opportunities for improving healthcare services through deep learning techniques.
STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction
We present STanHop-Net (Sparse Tandem Hopfield Network) for multivariate time series prediction with memory-enhanced capabilities.
Beyond PID Controllers: PPO with Neuralized PID Policy for Proton Beam Intensity Control in Mu2e
We introduce a novel Proximal Policy Optimization (PPO) algorithm aimed at addressing the challenge of maintaining a uniform proton beam intensity delivery in the Muon to Electron Conversion Experiment (Mu2e) at Fermi National Accelerator Laboratory (Fermilab).
Sparse PCA with Oracle Property
In particular, under a weak assumption on the magnitude of the population projection matrix, one estimator within this family exactly recovers the true support with high probability, has exact rank-$k$, and attains a $\sqrt{s/n}$ statistical rate of convergence with $s$ being the subspace sparsity level and $n$ the sample size.
Learning Site-specific Styles for Multi-institutional Unsupervised Cross-modality Domain Adaptation
In this paper, we present our solution to tackle the multi-institutional unsupervised domain adaptation for the crossMoDA 2023 challenge.
Assessing Test-time Variability for Interactive 3D Medical Image Segmentation with Diverse Point Prompts
In this paper, we assess the test-time variability for interactive medical image segmentation with diverse point prompts.
Promise:Prompt-driven 3D Medical Image Segmentation Using Pretrained Image Foundation Models
To address prevalent issues in medical imaging, such as data acquisition challenges and label availability, transfer learning from natural to medical image domains serves as a viable strategy to produce reliable segmentation results.
Boosting Decision-Based Black-Box Adversarial Attack with Gradient Priors
Decision-based methods have shown to be effective in black-box adversarial attacks, as they can obtain satisfactory performance and only require to access the final model prediction.
VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models
In this paper, we aim to investigate a new yet practical task to craft image and text perturbations using pre-trained VL models to attack black-box fine-tuned models on different downstream tasks.
Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints
The increasing capabilities of large language models (LLMs) raise opportunities for artificial general intelligence but concurrently amplify safety concerns, such as potential misuse of AI systems, necessitating effective AI alignment.
On Sparse Modern Hopfield Model
Building upon this, we derive the sparse memory retrieval dynamics from the sparse energy function and show its one-step approximation is equivalent to the sparse-structured attention.
False Negative/Positive Control for SAM on Noisy Medical Images
The method couples multi-box prompt augmentation and an aleatoric uncertainty-based false-negative (FN) and false-positive (FP) correction (FNPC) strategy.
CATS v2: Hybrid encoders for robust medical segmentation
We fuse the information from the convolutional encoder and the transformer at the skip connections of different resolutions to form the final segmentation.
GPTScan: Detecting Logic Vulnerabilities in Smart Contracts by Combining GPT with Program Analysis
Instead of relying solely on GPT to identify vulnerabilities, which can lead to high false positives and is limited by GPT's pre-trained knowledge, we utilize GPT as a versatile code understanding tool.
COLosSAL: A Benchmark for Cold-start Active Learning for 3D Medical Image Segmentation
Cold-start AL is highly relevant in many practical scenarios but has been under-explored, especially for 3D medical segmentation tasks requiring substantial annotation effort.
Efficient Action Robust Reinforcement Learning with Probabilistic Policy Execution Uncertainty
Robust reinforcement learning (RL) aims to find a policy that optimizes the worst-case performance in the face of uncertainties.
Learning Multiple Coordinated Agents under Directed Acyclic Graph Constraints
This paper proposes a novel multi-agent reinforcement learning (MARL) method to learn multiple coordinated agents under directed acyclic graph (DAG) constraints.
VesselMorph: Domain-Generalized Retinal Vessel Segmentation via Shape-Aware Representation
We map the intensity image and the tensor field to a latent space for feature extraction.
Real-time High-Resolution Neural Network with Semantic Guidance for Crack Segmentation
Deep learning plays an important role in crack segmentation, but most work utilize off-the-shelf or improved models that have not been specifically developed for this task.
DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genome
Decoding the linguistic intricacies of the genome is a crucial problem in biology, and pre-trained foundational models such as DNABERT and Nucleotide Transformer have made significant strides in this area.
Ranked #1 on
Core Promoter Detection
on GUE
Feature Programming for Multivariate Time Series Prediction
We introduce the concept of programmable feature engineering for time series modeling and propose a feature programming framework.
Non-Log-Concave and Nonsmooth Sampling via Langevin Monte Carlo Algorithms
We study the problem of approximate sampling from non-log-concave distributions, e. g., Gaussian mixtures, which is often challenging even in low dimensions due to their multimodality.
COSST: Multi-organ Segmentation with Partially Labeled Datasets Using Comprehensive Supervisions and Self-training
We revisit the problem from a perspective of partial label supervision signals and identify two signals derived from ground truth and one from pseudo labels.
Boosting Few-Shot Text Classification via Distribution Estimation
Distribution estimation has been demonstrated as one of the most effective approaches in dealing with few-shot image classification, as the low-level patterns and underlying representations can be easily transferred across different tasks in computer vision domain.
Few-Shot Image Classification
Few-Shot Text Classification
+2
SSL^2: Self-Supervised Learning meets Semi-Supervised Learning: Multiple Sclerosis Segmentation in 7T-MRI from large-scale 3T-MRI
A potential solution is to leverage the information available in large public datasets in conjunction with a target dataset which only has limited labeled data.
Learning Human-Compatible Representations for Case-Based Decision Support
Despite the promising performance of supervised learning, representations learned by supervised models may not align well with human intuitions: what models consider as similar examples can be perceived as distinct by humans.
Real-Time Image Demoireing on Mobile Devices
In this paper, we launch the first study on accelerating demoireing networks and propose a dynamic demoireing acceleration method (DDA) towards a real-time deployment on mobile devices.
HS-GCN: Hamming Spatial Graph Convolutional Networks for Recommendation
Towards this end, existing methods tend to code users by modeling their Hamming similarities with the items they historically interact with, which are termed as the first-order similarities in this work.
SlowLiDAR: Increasing the Latency of LiDAR-Based Detection Using Adversarial Examples
LiDAR-based perception is a central component of autonomous driving, playing a key role in tasks such as vehicle localization and obstacle detection.
RIATIG: Reliable and Imperceptible Adversarial Text-to-Image Generation With Natural Prompts
The field of text-to-image generation has made remarkable strides in creating high-fidelity and photorealistic images.
Biomedical image analysis competitions: The state of current participation practice
Of these, 84% were based on standard architectures.
Interdisciplinary Discovery of Nanomaterials Based on Convolutional Neural Networks
The material science literature contains up-to-date and comprehensive scientific knowledge of materials.
KGML-xDTD: A Knowledge Graph-based Machine Learning Framework for Drug Treatment Prediction and Mechanism Description
We believe it can effectively reduce "black-box" concerns and increase prediction confidence for drug repurposing based on predicted path-based explanations, and further accelerate the process of drug discovery for emerging diseases.
Aligning Offline Metrics and Human Judgments of Value for Code Generation Models
Large language models have demonstrated great potential to assist programmers in generating code.
Drug repositioning for Alzheimer's disease with transfer learning
After training, the model is used for virtual screening to find potential drugs for Alzheimer's disease (AD) treatment.
Evaluation of Synthetically Generated CT for use in Transcranial Focused Ultrasound Procedures
Among 20 targets, differences in simulated peak pressure between rCT and sCT were largest without phase correction (12. 4$\pm$8. 1%) and smallest with Kranion phases (7. 3$\pm$6. 0%).
Adaptive Contrastive Learning with Dynamic Correlation for Multi-Phase Organ Segmentation
We evaluate our proposed approach on multi-organ segmentation with both non-contrast CT (NCCT) datasets and the MICCAI 2015 BTCV Challenge contrast-enhance CT (CECT) datasets.
Enhancing Data Diversity for Self-training Based Unsupervised Cross-modality Vestibular Schwannoma and Cochlea Segmentation
Automatic segmentation of vestibular schwannoma (VS) and cochlea from magnetic resonance imaging can facilitate VS treatment planning.
Cats: Complementary CNN and Transformer Encoders for Segmentation
We fuse the information from the convolutional encoder and the transformer, and pass it to the decoder to obtain the results.
HPS-Det: Dynamic Sample Assignment with Hyper-Parameter Search for Object Detection
Sample assignment plays a prominent part in modern object detection approaches.
A Real-time Fire Segmentation Method Based on A Deep Learning Approach
Different from deeplabv3+, in order to improve the segmentation speed, this paper uses the lightweight network mobilenetv3 to build a new deep convolutional neural network and does not use atrous convolution, but it will affect the segmentation accuracy.
Ranked #1 on
Real-Time Semantic Segmentation
on FLAME
Bregman Proximal Langevin Monte Carlo via Bregman--Moreau Envelopes
The proposed algorithms extend existing Langevin Monte Carlo algorithms in two aspects -- the ability to sample nonsmooth distributions with mirror descent-like algorithms, and the use of the more general Bregman--Moreau envelope in place of the Moreau envelope as a smooth approximation of the nonsmooth part of the potential.
Label-enhanced Prototypical Network with Contrastive Learning for Multi-label Few-shot Aspect Category Detection
Multi-label aspect category detection allows a given review sentence to contain multiple aspect categories, which is shown to be more practical in sentiment analysis and attracting increasing attention.
Bridging the Gap Between Training and Inference of Bayesian Controllable Language Models
Large-scale pre-trained language models have achieved great success on natural language generation tasks.
A Simple Meta-learning Paradigm for Zero-shot Intent Classification with Mixture Attention Mechanism
Zero-shot intent classification is a vital and challenging task in dialogue systems, which aims to deal with numerous fast-emerging unacquainted intents without annotated training data.
Large-Scale Multi-Document Summarization with Information Extraction and Compression
We develop an abstractive summarization framework independent of labeled data for multiple heterogeneous documents.
Wasserstein Distributionally Robust Optimization with Wasserstein Barycenters
On the other hand, in distributionally robust optimization, we seek data-driven decisions which perform well under the most adverse distribution from a nominal distribution constructed from data samples within a certain discrepancy of probability distributions.
Learning to Infer Belief Embedded Communication
In multi-agent collaboration problems with communication, an agent's ability to encode their intention and interpret other agents' strategies is critical for planning their future actions.
Switch Trajectory Transformer with Distributional Value Approximation for Multi-Task Reinforcement Learning
Our results also demonstrate the advantage of the switch transformer model for absorbing expert knowledge and the importance of value distribution in evaluating the trajectory.
Survival Prediction of Brain Cancer with Incomplete Radiology, Pathology, Genomics, and Demographic Data
Thus, there are still open questions on how to effectively predict brain cancer survival from the incomplete radiological, pathological, genomic, and demographic data (e. g., one or more modalities might not be collected for a patient).
ModDrop++: A Dynamic Filter Network with Intra-subject Co-training for Multiple Sclerosis Lesion Segmentation with Missing Modalities
Previously, a training strategy termed Modality Dropout (ModDrop) has been applied to MS lesion segmentation to achieve the state-of-the-art performance with missing modality.
Modeling and Validating Temporal Rules with Semantic Petri-Net for Digital Twins
Semantic rule checking on RDFS/OWL data has been widely used in the construction industry.
Synthetic CT Skull Generation for Transcranial MR Imaging-Guided Focused Ultrasound Interventions with Conditional Adversarial Networks
Transcranial MRI-guided focused ultrasound (TcMRgFUS) is a therapeutic ultrasound method that focuses sound through the skull to a small region noninvasively under MRI guidance.
A Multi-rater Comparative Study of Automatic Target Localization Methods for Epilepsy Deep Brain Stimulation Procedures
Epilepsy is the fourth most common neurological disorder and affects people of all ages worldwide.
Unsupervised Domain Adaptation for Vestibular Schwannoma and Cochlea Segmentation via Semi-supervised Learning and Label Fusion
Automatic methods to segment the vestibular schwannoma (VS) tumors and the cochlea from magnetic resonance imaging (MRI) are critical to VS treatment planning.
CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea Segmentation
The aim was to automatically perform unilateral VS and bilateral cochlea segmentation on hrT2 as provided in the testing set (N=137).
A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applications
This paper provides a comprehensive review of epistemic uncertainty learning techniques in supervised learning over the last five years.
An Explicit-Joint and Supervised-Contrastive Learning Framework for Few-Shot Intent Classification and Slot Filling
Intent classification (IC) and slot filling (SF) are critical building blocks in task-oriented dialogue systems.
Learning Predictive, Online Approximations of Explanatory, Offline Algorithms
In this work, we introduce a general methodology for approximating offline algorithms in online settings.
Reinforcement Learning under a Multi-agent Predictive State Representation Model: Method and Theory
This paper proposes a new algorithm for learning the optimal policies under a novel multi-agent predictive state representation reinforcement learning model.
Cross-Modality Domain Adaptation for Vestibular Schwannoma and Cochlea Segmentation
Automatic methods to segment the vestibular schwannoma (VS) tumors and the cochlea from magnetic resonance imaging (MRI) are critical to VS treatment planning.
Posterior Promoted GAN With Distribution Discriminator for Unsupervised Image Synthesis
In this paper, we propose a novel variant of GAN, Posterior Promoted GAN (P2GAN), which promotes generator with the real information in the posterior distribution produced by discriminator.
Review Polarity-wise Recommender
To be specific, in this model, positive and negative reviews are separately gathered and utilized to model the user-preferred and user-rejected aspects, respectively.
Trade the Event: Corporate Events Detection for News-Based Event-Driven Trading
In this paper, we introduce an event-driven trading strategy that predicts stock movements by detecting corporate events from news articles.
Cross-Dataset Collaborative Learning for Semantic Segmentation in Autonomous Driving
Our goal is to train a unified model for improving the performance in each dataset by leveraging information from all the datasets.
BLOCKEYE: Hunting For DeFi Attacks on Blockchain
We applied BLOCKEYE in several popular DeFi projects and managed to discover potential security attacks that are unreported before.
Cryptography and Security Computers and Society
Converse, Focus and Guess -- Towards Multi-Document Driven Dialogue
We propose a novel task, Multi-Document Driven Dialogue (MD3), in which an agent can guess the target document that the user is interested in by leading a dialogue.
Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Making
Although AI holds promise for improving human decision making in societally critical domains, it remains an open question how human-AI teams can reliably outperform AI alone and human alone in challenging prediction tasks (also known as complementary performance).
Morphology Matters: A Multilingual Language Modeling Analysis
We fill in missing typological data for several languages and consider corpus-based measures of morphological complexity in addition to expert-produced typological features.
Uncertainty Estimation in Medical Image Localization: Towards Robust Anterior Thalamus Targeting for Deep Brain Stimulation
Atlas-based methods are the standard approaches for automatic targeting of the Anterior Nucleus of the Thalamus (ANT) for Deep Brain Stimulation (DBS), but these are known to lack robustness when anatomic differences between atlases and subjects are large.
Label-Wise Document Pre-Training for Multi-Label Text Classification
A major challenge of multi-label text classification (MLTC) is to stimulatingly exploit possible label differences and label correlations.
Ranked #1 on
Multi-Label Text Classification
on AAPD
(Micro F1 metric)
Unknown Intent Detection Using Gaussian Mixture Model with an Application to Zero-shot Intent Classification
User intent classification plays a vital role in dialogue systems.
Picasso: A Sparse Learning Library for High Dimensional Data Analysis in R and Python
We describe a new library named picasso, which implements a unified framework of pathwise coordinate optimization for a variety of sparse learning problems (e. g., sparse linear regression, sparse logistic regression, sparse Poisson regression and scaled sparse linear regression) combined with efficient active set selection strategies.
The flare Package for High Dimensional Linear Regression and Precision Matrix Estimation in R
This paper describes an R package named flare, which implements a family of new high dimensional regression methods (LAD Lasso, SQRT Lasso, $\ell_q$ Lasso, and Dantzig selector) and their extensions to sparse precision matrix estimation (TIGER and CLIME).
The huge Package for High-dimensional Undirected Graph Estimation in R
We describe an R package named huge which provides easy-to-use functions for estimating high dimensional undirected graphs from data.
Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network
In this paper, we explore the slot tagging with only a few labeled support sentences (a. k. a.
A Deep Learning based Wearable Healthcare IoT Device for AI-enabled Hearing Assistance Automation
With the recent booming of artificial intelligence (AI), particularly deep learning techniques, digital healthcare is one of the prevalent areas that could gain benefits from AI-enabled functionality.
Neural Polysynthetic Language Modelling
In the literature, languages like Finnish or Turkish are held up as extreme examples of complexity that challenge common modelling assumptions.
FAME: 3D Shape Generation via Functionality-Aware Model Evolution
Our tool supports constrained modeling, allowing users to restrict or steer the model evolution with functionality labels.
Graphics
Scmhl5 at TRAC-2 Shared Task on Aggression Identification: Bert Based Ensemble Learning Approach
This paper presents a system developed during our participation (team name: scmhl5) in the TRAC-2 Shared Task on aggression identification.
EQL -- an extremely easy to learn knowledge graph query language, achieving highspeed and precise search
EQL, also named as Extremely Simple Query Language, can be widely used in the field of knowledge graph, precise search, strong artificial intelligence, database, smart speaker , patent search and other fields.
"Why is 'Chicago' deceptive?" Towards Building Model-Driven Tutorials for Humans
To support human decision making with machine learning models, we often need to elucidate patterns embedded in the models that are unsalient, unknown, or counterintuitive to humans.
Automatic quality assessment for 2D fetal sonographic standard plane based on multi-task learning
An essential criterion for FS image quality control is that all the essential anatomical structures in the section should appear full and remarkable with a clear boundary.
Reconstructing Capsule Networks for Zero-shot Intent Classification
With the burgeoning of conversational AI, existing systems are not capable of handling numerous fast-emerging intents, which motivates zero-shot intent classification.
Clustering Uncertain Data via Representative Possible Worlds with Consistency Learning
However, there are two issues in existing possible world based algorithms: (1) They rely on all the possible worlds and treat them equally, but some marginal possible worlds may cause negative effects.
Dimensionwise Separable 2-D Graph Convolution for Unsupervised and Semi-Supervised Learning on Graphs
Graph convolutional neural networks (GCN) have been the model of choice for graph representation learning, which is mainly due to the effective design of graph convolution that computes the representation of a node by aggregating those of its neighbors.
AdvCodec: Towards A Unified Framework for Adversarial Text Generation
In particular, we propose a tree based autoencoder to encode discrete text data into continuous vector space, upon which we optimize the adversarial perturbation.
Scalable Differentially Private Data Generation via Private Aggregation of Teacher Ensembles
We present a novel approach named G-PATE for training differentially private data generator.
Attributed Graph Learning with 2-D Graph Convolution
Graph convolutional neural networks have demonstrated promising performance in attributed graph learning, thanks to the use of graph convolution that effectively combines graph structures and node features for learning node representations.
Fast Low-rank Metric Learning for Large-scale and High-dimensional Data
Low-rank metric learning aims to learn better discrimination of data subject to low-rank constraints.
More Supervision, Less Computation: Statistical-Computational Tradeoffs in Weakly Supervised Learning
We consider the weakly supervised binary classification problem where the labels are randomly flipped with probability $1- {\alpha}$.
Few-Shot Sequence Labeling with Label Dependency Transfer and Pair-wise Embedding
It calculates emission score with similarity based methods and obtains transition score with a specially designed transfer mechanism.
Attributed Graph Clustering via Adaptive Graph Convolution
Attributed graph clustering is challenging as it requires joint modelling of graph structures and node attributes.
Ranked #3 on
Graph Clustering
on Cora
GLAD: Learning Sparse Graph Recovery
Recently, there is a surge of interest to learn algorithms directly based on data, and in this case, learn to map empirical covariance to the sparse precision matrix.
Estimating and Inferring the Maximum Degree of Stimulus-Locked Time-Varying Brain Connectivity Networks
To address this issue, neuroscientists have been measuring brain activity under natural viewing experiments in which the subjects are given continuous stimuli, such as watching a movie or listening to a story.
Learning to Plan in High Dimensions via Neural Exploration-Exploitation Trees
We propose a meta path planning algorithm named \emph{Neural Exploration-Exploitation Trees~(NEXT)} for learning from prior experience for solving new path planning problems in high dimensional continuous state and action spaces.
Label Efficient Semi-Supervised Learning via Graph Filtering
However, existing graph-based methods either are limited in their ability to jointly model graph structures and data features, such as the classical label propagation methods, or require a considerable amount of labeled data for training and validation due to high model complexity, such as the recent neural-network-based methods.
Finite-Sample Analysis For Decentralized Batch Multi-Agent Reinforcement Learning With Networked Agents
This work appears to be the first finite-sample analysis for batch MARL, a step towards rigorous theoretical understanding of general MARL algorithms in the finite-sample regime.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Sketching Method for Large Scale Combinatorial Inference
In order to test the hypotheses on their topological structures, we propose two adjacency matrix sketching frameworks: neighborhood sketching and subgraph sketching.
Exponentially Weighted Imitation Learning for Batched Historical Data
We consider deep policy learning with only batched historical trajectories.
Performance assessment of the deep learning technologies in grading glaucoma severity
Among these CNNs, the DenseNet had the highest classification accuracy (i. e., 75. 50%) based on pre-trained weights when using global ROIs, as compared to 65. 50% when using local ROIs.
SDFN: Segmentation-based Deep Fusion Network for Thoracic Disease Classification in Chest X-ray Images
Two CNN-based classification models were then used as feature extractors to obtain the discriminative features of the entire CXR images and the cropped lung region images.
Super-pixel cloud detection using Hierarchical Fusion CNN
Secondly, super-pixel level database is used to train our cloud detection models based on CNN and deep forest.
Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Space
Most existing deep reinforcement learning (DRL) frameworks consider either discrete action space or continuous action space solely.
Fully Implicit Online Learning
Regularized online learning is widely used in machine learning applications.
High-Temperature Structure Detection in Ferromagnets
The goal is to distinguish whether the underlying graph is empty, i. e., the model consists of independent Rademacher variables, versus the alternative that the underlying graph contains a subgraph of a certain structure.
TStarBots: Defeating the Cheating Level Builtin AI in StarCraft II in the Full Game
Both TStarBot1 and TStarBot2 are able to defeat the built-in AI agents from level 1 to level 10 in a full game (1v1 Zerg-vs-Zerg game on the AbyssalReef map), noting that level 8, level 9, and level 10 are cheating agents with unfair advantages such as full vision on the whole map and resource harvest boosting.
A convex formulation for high-dimensional sparse sliced inverse regression
Sliced inverse regression is a popular tool for sufficient dimension reduction, which replaces covariates with a minimal set of their linear combinations without loss of information on the conditional distribution of the response given the covariates.
Factorized Q-Learning for Large-Scale Multi-Agent Systems
Deep Q-learning has achieved a significant success in single-agent decision making tasks.
Multiagent Systems
Online ICA: Understanding Global Dynamics of Nonconvex Optimization via Diffusion Processes
Despite the empirical success of nonconvex statistical optimization methods, their global dynamics, especially convergence to the desirable local minima, remain less well understood in theory.
Diffusion Approximations for Online Principal Component Estimation and Global Convergence
In this paper, we propose to adopt the diffusion approximation tools to study the dynamics of Oja's iteration which is an online stochastic gradient descent method for the principal component analysis.
Curse of Heterogeneity: Computational Barriers in Sparse Mixture Models and Phase Retrieval
We study the fundamental tradeoffs between statistical accuracy and computational tractability in the analysis of high dimensional heterogeneous data.
Graphical Nonconvex Optimization via an Adaptive Convex Relaxation
Our proposal is computationally tractable and produces an estimator that achieves the oracle rate of convergence.
The Edge Density Barrier: Computational-Statistical Tradeoffs in Combinatorial Inference
We study the hypothesis testing problem of inferring the existence of combinatorial structures in undirected graphical models.
Marginal Policy Gradients: A Unified Family of Estimators for Bounded Action Spaces with Applications
In the former, an agent learns a policy over $\mathbb{R}^d$ and in the latter, over a discrete set of actions each of which is parametrized by a continuous parameter.
Efficient, Certifiably Optimal Clustering with Applications to Latent Variable Graphical Models
Compared to the naive interior point method, our method reduces the computational complexity of solving the SDP from $\tilde{O}(d^7\log\epsilon^{-1})$ to $\tilde{O}(d^{6}K^{-2}\epsilon^{-1})$ arithmetic operations for an $\epsilon$-optimal solution.
Feedback-Based Tree Search for Reinforcement Learning
Inspired by recent successes of Monte-Carlo tree search (MCTS) in a number of artificial intelligence (AI) application domains, we propose a model-based reinforcement learning (RL) technique that iteratively applies MCTS on batches of small, finite-horizon versions of the original infinite-horizon Markov decision process.
Discrete Factorization Machines for Fast Feature-based Recommendation
In this paper, we develop a generic feature-based recommendation model, called Discrete Factorization Machine (DFM), for fast and accurate recommendation.
Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents
To this end, we propose two decentralized actor-critic algorithms with function approximation, which are applicable to large-scale MARL problems where both the number of states and the number of agents are massively large.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
The Enemy Among Us: Detecting Hate Speech with Threats Based 'Othering' Language Embeddings
Offensive or antagonistic language targeted at individuals and social groups based on their personal characteristics (also known as cyber hate speech or cyberhate) has been frequently posted and widely circulated viathe World Wide Web.
