Papers
Fri 14 Jul 2023
174 papers
- NIFTY: Neural Object Interaction Fields for Guided Human Motion SynthesisDiffusion models → Video generation
- Multimodal Distillation for Egocentric Action RecognitionKnowledge distillation → Multimodal distillation
- Improving Zero-Shot Generalization for CLIP with Synthesized PromptsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- PiTL: Cross-modal Retrieval with Weakly-supervised Vision-language Pre-training via PromptingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Dialogue Agents 101: A Beginner's Guide to Critical Ingredients for Designing Effective Conversational SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
- Knowledge Boosting: Rethinking Medical Contrastive Vision-Language Pre-TrainingMultimodal LLMs / vision-language models → Medical vision-language models
- Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly DetectionDiffusion models → Flow matching, time series and science
- SafeDreamer: Safe Reinforcement Learning with World ModelsWorld models → Latent dynamics models and model-based RL
- Drive Like a Human: Rethinking Autonomous Driving with Large Language ModelsLLM reasoning → Chain-of-thought reasoning for driving +1
- Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute ManipulationLLM reasoning → Prompting and chain-of-thought reasoning
- ISAC-NET: Model-driven Deep Learning for Integrated Passive Sensing and Communication
- Drug Discovery under Covariate Shift with Domain-Informed Prior Distributions over Functions
- CAMP: A Context-Aware Cricket Players Performance Metric
- A Topical Approach to Capturing Customer Insight In Social Media
- Sensi-BERT: Towards Sensitivity Driven Fine-Tuning for Parameter-Efficient BERT
- Rethinking Trust Repair in Human-Robot Interaction
- Similarity-based Memory Enhanced Joint Entity and Relation Extraction
- Fairness of ChatGPT and the Role Of Explainable-Guided Prompts
- Large Language Models Understand and Can be Enhanced by Emotional Stimuli
- Reinforcement Learning for Photonic Component Design
- `It is currently hodgepodge'': Examining AI/ML Practitioners' Challenges during Co-production of Responsible AI Values
- Temporal Fact Reasoning over Hyper-Relational Knowledge Graphs
- Time for aCTIon: Automated Analysis of Cyber Threat Intelligence in the Wild
- Mitigating Bias in Conversations: A Hate Speech Classifier and Debiaser with Prompts
- Capsule network with shortcut routing
- Unsupervised Domain Adaptation using Lexical Transformations and Label Injection for Twitter Data
- On the Sensitivity of Deep Load Disaggregation to Adversarial Attacks
- NEAT: Distilling 3D Wireframes from Neural Attraction Fields
- Alleviating the Effect of Data Imbalance on Adversarial Training
- An IPW-based Unbiased Ranking Metric in Two-sided Markets
- Scalable Deep Learning for RNA Secondary Structure Prediction
- Ethics in the Age of AI: An Analysis of AI Practitioners' Awareness and Challenges
- FaIRGP: A Bayesian Energy Balance Model for Surface Temperatures Emulation
- Deteksi Sampah di Permukaan dan Dalam Perairan pada Objek Video dengan Metode Robust and Efficient Post-Processing dan Tubelet-Level Bounding Box Linking
- Source-Free Domain Adaptive Fundus Image Segmentation with Class-Balanced Mean Teacher
- Fine-grained Text-Video Retrieval with Frozen Image Encoders
- Looking deeper into interpretable deep learning in neuroimaging: a comprehensive survey
- Understanding Multi-Turn Toxic Behaviors in Open-Domain Chatbots
- Transient Neural Radiance Fields for Lidar View Synthesis and 3D Reconstruction
- The Role of Transparency in Repeated First-Price Auctions with Unknown Valuations
- LEST: Large-scale LiDAR Semantic Segmentation with Transformer
- Efficient Strongly Polynomial Algorithms for Quantile Regression
- Global path preference and local response: A reward decomposition approach for network path choice analysis in the presence of locally perceived attributes
- HYTREL: Hypergraph-enhanced Tabular Data Representation Learning
- Brain in the Dark: Design Principles for Neuro-mimetic Learning and Inference
- Omnipotent Adversarial Training in the Wild
- Visual Explanations with Attributions and Counterfactuals on Time Series Classification
- MPDIoU: A Loss for Efficient and Accurate Bounding Box Regression
- Machine learning for option pricing: an empirical investigation of network architectures
- RFLA: A Stealthy Reflected Light Adversarial Attack in the Physical World
- DIGEST: Fast and Communication Efficient Decentralized Learning with Local Updates
- SALC: Skeleton-Assisted Learning-Based Clustering for Time-Varying Indoor Localization
- DistTGL: Distributed Memory-Based Temporal Graph Neural Network Training
- Othering and low status framing of immigrant cuisines in US restaurant reviews and large language models
- Attention-Enhanced Co-Interactive Fusion Network (AECIF-Net) for Automated Structural Condition Assessment in Visual Inspection
- Dissenting Explanations: Leveraging Disagreement to Reduce Model Overreliance
- CoTracker: It is Better to Track Together
- Towards Model-Size Agnostic, Compute-Free, Memorization-based Inference of Deep Learning
- Value-based Fast and Slow AI Nudging
- Generalizable Embeddings with Cross-batch Metric Learning
- Efficiently Factorizing Boolean Matrices using Proximal Gradient Descent
- Towards Generalizable Detection of Urgency of Discussion Forum Posts
- First-order Methods for Affinely Constrained Composite Non-convex Non-smooth Problems: Lower Complexity Bound and Near-optimal Methods
- Smooth Lower Bounds for Differentially Private Algorithms via Padding-and-Permuting Fingerprinting Codes
- Gastrointestinal Disease Classification through Explainable and Cost-Sensitive Deep Neural Networks with Supervised Contrastive Learning
- Training Discrete Energy-Based Models with Energy Discrepancy
- QontSum: On Contrasting Salient Content for Query-focused Summarization
- A Quantitative Approach to Predicting Representational Learning and Performance in Neural Networks
- Sparsified Simultaneous Confidence Intervals for High-Dimensional Linear Models
- High-Rate Phase Association with Travel Time Neural Fields
- Variational Prediction
- Reconstruction of 3-Axis Seismocardiogram from Right-to-left and Head-to-foot Components Using A Long Short-Term Memory Network
- Source-Free Domain Adaptation with Temporal Imputation for Time Series Data
- ConTrack: Contextual Transformer for Device Tracking in X-ray
- Flow-Guided Controllable Line Drawing Generation
- On the Sublinear Regret of GP-UCB
- Masked Autoencoders for Unsupervised Anomaly Detection in Medical Images
- Expressive Monotonic Neural Networks
- MGit: A Model Versioning and Management System
- Brain Tumor Detection using Convolutional Neural Networks with Skip Connections
- TALL: Thumbnail Layout for Deepfake Video Detection
- PseudoCal: A Source-Free Approach to Unsupervised Uncertainty Calibration in Domain Adaptation
- DreamTeacher: Pretraining Image Backbones with Deep Generative Models
- Dual-Query Multiple Instance Learning for Dynamic Meta-Embedding based Tumor Classification
- Population Expansion for Training Language Models with Private Federated Learning
- Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action Recognition
- Structured Pruning of Neural Networks for Constraints Learning
- Generative adversarial networks for data-scarce spectral applications
- Differentially Private Clustering in Data Streams
- Can Large Language Models Empower Molecular Property Prediction?
- Atlas-Based Interpretable Age Prediction In Whole-Body MR Images
- Towards spoken dialect identification of Irish
- Combining multitemporal optical and SAR data for LAI imputation with BiLSTM network
- Exploiting Counter-Examples for Active Learning with Partial labels
- HuCurl: Human-induced Curriculum Discovery
- Improved Convergence Analysis and SNR Control Strategies for Federated Learning in the Presence of Noise
- Performance of ℓ1 Regularization for Sparse Convex Optimization
- Visualizing Overlapping Biclusterings and Boolean Matrix Factorizations
- L-DAWA: Layer-wise Divergence Aware Weight Aggregation in Federated Self-Supervised Visual Representation Learning
- Rank Your Summaries: Enhancing Bengali Text Summarization via Ranking-based Approach
All 174
- Learning Sparse Neural Networks with Identity Layers
- Higher-order topological kernels via quantum computation
- Composition-contrastive Learning for Sentence Embeddings
- Defect Classification in Additive Manufacturing Using CNN-Based Vision Processing
- AIC-AB NET: A Neural Network for Image Captioning with Spatial Attention and Text Attributes
- Are Large Language Models a Threat to Digital Public Goods? Evidence from Activity on Stack Overflow
- A scoping review on multimodal deep learning in biomedical images and texts
- Gloss Attention for Gloss-free Sign Language Translation
- Inverse Optimization for Routing Problems
- Clusterability test for categorical data
- Inverse Evolution Layers: Physics-informed Regularizers for Deep Neural Networks
- MaxMin-L2-SVC-NCH: A Novel Approach for Support Vector Classifier Training and Parameter Selection
- Risk Controlled Image Retrieval
- SynTable: A Synthetic Data Generation Pipeline for Unseen Object Amodal Instance Segmentation of Cluttered Tabletop Scenes
- How Different Is Stereotypical Bias Across Languages?
- Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategy
- Representation Learning With Hidden Unit Clustering For Low Resource Speech Applications
- A Context-Aware Cutting Plane Selection Algorithm for Mixed-Integer Programming
- Adaptive Linear Estimating Equations
- Hybrid moderation in the newsroom: Recommending featured posts to content moderators
- HEAL-SWIN: A Vision Transformer On The Sphere
- Using Large Language Models for Zero-Shot Natural Language Generation from Knowledge Graphs
- C3: Zero-shot Text-to-SQL with ChatGPT
- Solving higher-order Lane-Emden-Fowler type equations using physics-informed neural networks: benchmark tests comparing soft and hard constraints
- 3D Shape-Based Myocardial Infarction Prediction Using Point Cloud Classification Networks
- Reinforcement Learning with Frontier-Based Exploration via Autonomous Environment
- Towards dialect-inclusive recognition in a low-resource language: are balanced corpora the answer?
- Sampling-Priors-Augmented Deep Unfolding Network for Robust Video Compressive Sensing
- Implicit Neural Feature Fusion Function for Multispectral and Hyperspectral Image Fusion
- One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching
- Cloud Detection in Multispectral Satellite Images Using Support Vector Machines With Quantum Kernels
- Replay to Remember: Continual Layer-Specific Fine-tuning for German Speech Recognition
- Are words equally surprising in audio and audio-visual comprehension?
- Frequency Domain Adversarial Training for Robust Volumetric Medical Segmentation
- AudioInceptionNeXt: TCL AI LAB Submission to EPIC-SOUND Audio-Based-Interaction-Recognition Challenge 2023
- On Interpolating Experts and Multi-Armed Bandits
- MorphPiece : A Linguistic Tokenizer for Large Language Models
- A Dynamic Points Removal Benchmark in Point Cloud Maps
- Improving BERT with Hybrid Pooling Network and Drop Mask
- cOOpD: Reformulating COPD classification on chest CT scans as anomaly detection using contrastive representations
- Mitigating Adversarial Vulnerability through Causal Parameter Estimation by Adversarial Double Machine Learning
- Rigorous Runtime Analysis of Diversity Optimization with GSEMO on OneMinMax
- FreeCOS: Self-Supervised Learning from Fractals and Unlabeled Images for Curvilinear Object Segmentation
- MaxSR: Image Super-Resolution Using Improved MaxViT
- Challenge Results Are Not Reproducible
- Complementary Frequency-Varying Awareness Network for Open-Set Fine-Grained Image Recognition
- Ed-Fed: A generic federated learning framework with resource-aware client selection for edge devices
- LightFormer: An End-to-End Model for Intersection Right-of-Way Recognition Using Traffic Light Signals and an Attention Mechanism
- Controlling dynamical systems to complex target states using machine learning: next-generation vs. classical reservoir computing
- Bridging AI and Energy Forecasting: An Autonomous Workflow with Customized Toolkit
- Multiplicative update rules for accelerating deep learning training and increasing robustness
- Erasing, Transforming, and Noising Defense Network for Occluded Person Re-Identification
- TVPR: Text-to-Video Person Retrieval and a New Benchmark
- DISPEL: Domain Generalization via Domain-Specific Liberating
- A Surrogate Data Assimilation Model for the Estimation of Dynamical System in a Limited Area
- TriFormer: A Multi-modal Transformer Framework For Mild Cognitive Impairment Conversion Prediction
- FedBIAD: Communication-Efficient and Accuracy-Guaranteed Federated Learning with Bayesian Inference-Based Adaptive Dropout
- Certified Robustness for Large Language Models with Self-Denoising
- Adaptive Region Selection for Active Learning in Whole Slide Image Semantic Segmentation
- Vulnerability-Aware Instance Reweighting For Adversarial Training
- Switching Head-Tail Funnel UNITER for Dual Referring Expression Comprehension with Fetch-and-Carry Tasks
- Learning to Retrieve In-Context Examples for Large Language Models
- Do not Mask Randomly: Effective Domain-adaptive Pre-training by Masking In-domain Keywords
- Linking vision and motion for self-supervised object-centric perception
- Federated Learning-Empowered AI-Generated Content in Wireless Networks
- Quantity-Aware Coarse-to-Fine Correspondence for Image-to-Point Cloud Registration
- MMSD2.0: Towards a Reliable Multi-modal Sarcasm Detection System
- Multi-Dimensional Ability Diagnosis for Machine Learning Algorithms
- CeRF: Convolutional Neural Radiance Fields for New View Synthesis with Derivatives of Ray Modeling
- Improved Flood Insights: Diffusion-Based SAR to EO Image Translation
- DataAssist: A Machine Learning Approach to Data Cleaning and Preparation
- Variance-reduced accelerated methods for decentralized stochastic double-regularized nonconvex strongly-concave minimax problems
- Graph Positional and Structural Encoder
- Achelous: A Fast Unified Water-surface Panoptic Perception Framework based on Fusion of Monocular Camera and 4D mmWave Radar