Papers
Sun 28 May 2023
146 papers
- Conditional score-based diffusion models for Bayesian inference in infinite dimensionsDiffusion models → Inverse problems and image restoration
- Cognitively Inspired Cross-Modal Data Generation Using Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
- Semantic Segmentation with Bidirectional Language Models Improves Long-form ASRKnowledge distillation → Speech and audio distillation
- Learning to Learn from APIs: Black-Box Data-Free Meta-LearningKnowledge distillation → General knowledge distillation methods
- Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive TasksLLM reasoning → Prompting and chain-of-thought reasoning +1
- Potential-based Credit Assignment for Cooperative RL-based Testing of Autonomous VehiclesEnd-to-end autonomous driving → Reinforcement learning for driving
- KAFA: Rethinking Image Ad Understanding with Knowledge-Augmented Feature Adaptation of Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
- NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP ModelsLLM safety and security → Backdoor and data poisoning attacks
- Tab-CoT: Zero-shot Tabular Chain of ThoughtLLM reasoning → Prompting and chain-of-thought reasoning
- Language Models are Bounded Pragmatic Speakers: Understanding RLHF from a Bayesian Cognitive Modeling PerspectiveLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Learning a Structural Causal Model for Intuition Reasoning in ConversationLLM reasoning → Causal reasoning in LLMs
- Rethinking Masked Language Modeling for Chinese Spelling CorrectionLLM reasoning → Reasoning benchmarks and evaluation
- FuseCap: Leveraging Large Language Models for Enriched Fused Image CaptionsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Prompt-Guided Retrieval Augmentation for Non-Knowledge-Intensive TasksRetrieval-augmented generation → RAG robustness and adaptive retrieval
- In-Context Analogical Reasoning with Pre-Trained Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
- AI Coach Assist: An Automated Approach for Call Recommendation in Contact Centers for Agent CoachingLLM agents and tool use → General LLM agent frameworks and benchmarks
- Reward Collapse in Aligning Large Language ModelsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- JutePestDetect: An Intelligent Approach for Jute Pest Identification Using Fine-Tuned Transfer Learning
- Geometric Epitope and Paratope Prediction
- GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning
- A Method for Detecting Murmurous Heart Sounds based on Self-similar Properties
- ChatGPT Informed Graph Neural Network for Stock Movement Prediction
- Towards a Technology-Driven Adaptive Decision Support System for Integrated Pavement and Maintenance strategies (TDADSS-IPM): focus on risk assessment framework for climate change adaptation
- A Quantitative Review on Language Model Efficiency Research
- Reconstructing Sea Surface Temperature Images: A Masked Autoencoder Approach for Cloud Masking and Reconstruction
- Mitigating Label Biases for In-context Learning
- ASU-CNN: An Efficient Deep Architecture for Image Classification and Feature Visualizations
- Key-Value Transformer
- Parallel Coordinates for Discovery of Interpretable Machine Learning Models
- Interactive Decision Tree Creation and Enhancement with Complete Visualization for Explainable Modeling
- Optimizing Airbnb Search Journey with Multi-task Learning
- Scalable and Weakly Supervised Bank Transaction Classification
- Visual Knowledge Discovery with General Line Coordinates
- Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approach
- Employing Explainable Artificial Intelligence (XAI) Methodologies to Analyze the Correlation between Input Variables and Tensile Strength in Additively Manufactured Samples
- Efficient Storage of Fine-Tuned Models via Low-Rank Approximation of Weight Residuals
- Repeated Random Sampling for Minimizing the Time-to-Accuracy of Learning
- On the Role of Noise in the Sample Complexity of Learning Recurrent Neural Networks: Exponential Gaps for Long Sequences
- HyperTime: Hyperparameter Optimization for Combating Temporal Distribution Shifts
- Sample Complexity of Variance-reduced Distributionally Robust Q-learning
- Just a Glimpse: Rethinking Temporal Information for Video Continual Learning
- Determinantal Point Process Attention Over Grid Cell Code Supports Out of Distribution Generalization
- Examining the Role and Limits of Batchnorm Optimization to Mitigate Diverse Hardware-noise in In-memory Computing
- Geometric Algebra Transformer
- StEik: Stabilizing the Optimization of Neural Signed Distance Functions and Finer Shape Representation
- Short-term Temporal Dependency Detection under Heterogeneous Event Dynamic with Hawkes Processes
- Feature-Learning Networks Are Consistent Across Widths At Realistic Scales
- Understanding Breast Cancer Survival: Using Causality and Language Models on Multi-omics Data
- Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithms
- A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretraining
- A machine learning approach to the prediction of heat-transfer coefficients in micro-channels
- Dink-Net: Neural Clustering on Large Graphs
- Conformal Prediction with Large Language Models for Multi-Choice Question Answering
- LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning
- Neural Sculpting: Uncovering hierarchically modular task structure in neural networks through pruning and network analysis
- A Meta-learning Framework for Tuning Parameters of Protection Mechanisms in Trustworthy Federated Learning
- On the impact of activation and normalization in obtaining isometric embeddings at initialization
- Mitigating Inappropriateness in Image Generation: Can there be Value in Reflecting the World's Ugliness?
- Prediction of the 2023 Turkish Presidential Election Results Using Social Media Data
- LLMs Can Understand Encrypted Prompt: Towards Privacy-Computing Friendly Transformers
- On Optimal Regularization Parameters via Bilevel Learning
- Training Private Models That Know What They Don't Know
- Speech Intelligibility Assessment of Dysarthric Speech by using Goodness of Pronunciation with Uncertainty Quantification
- MemeGraphs: Linking Memes to Knowledge Graphs
- Emergent Modularity in Pre-trained Transformers
- AnoRand: A Semi Supervised Deep Learning Anomaly Detection Method by Random Labeling
- The Statistical Benefits of Quantile Temporal-Difference Learning for Value Estimation
- Augmenting Character Designers Creativity Using Generative Adversarial Networks
- A Synergistic Framework Leveraging Autoencoders and Generative Adversarial Networks for the Synthesis of Computational Fluid Dynamics Results in Aerofoil Aerodynamics
- Self-attention Dual Embedding for Graphs with Heterophily
- Backdoor Attacks Against Incremental Learners: An Empirical Evaluation Study
- A Three-regime Model of Network Pruning
- Adaptive Sparsity Level during Training for Efficient Time Series Forecasting with Transformers
- Distill Gold from Massive Ores: Bi-level Data Pruning towards Efficient Dataset Distillation
- Constrained Optimization via Exact Augmented Lagrangian and Randomized Iterative Sketching
- Disentanglement via Latent Quantization
- BadLabel: A Robust Perspective on Evaluating and Enhancing Label-noise Learning
- Fast and Accurate Dual-Way Streaming PARAFAC2 for Irregular Tensors -- Algorithm and Application
- Learning to Jump: Thinning and Thickening Latent Counts for Generative Modeling
- Pure Spectral Graph Embeddings: Reinterpreting Graph Convolution for Top-N Recommendation
- Counter-Hypothetical Particle Filters for Single Object Pose Tracking
- Multinomial Logistic Regression: Asymptotic Normality on Null Covariates in High-Dimensions
- Analysis of ROC for Edge Detectors
- Large Language Models, scientific knowledge and factuality: A framework to streamline human expert evaluation
- Transfer Learning for Power Outage Detection Task with Limited Training Data
- The Computational Complexity of Single-Player Imperfect-Recall Games
- Targeted Data Generation: Finding and Fixing Model Weaknesses
- T2FNorm: Extremely Simple Scaled Train-time Feature Normalization for OOD Detection
- LowDINO -- A Low Parameter Self Supervised Learning Model
- Real-time Object Detection: YOLOv1 Re-Implementation in PyTorch
- Lighting and Rotation Invariant Real-time Vehicle Wheel Detector based on YOLOv5
- ConvGenVisMo: Evaluation of Conversational Generative Vision Models
- Visual Affordance Prediction for Guiding Robot Exploration
- RASR2: The RWTH ASR Toolkit for Generic Sequence-to-sequence Speech Recognition
- Generating EDU Extracts for Plan-Guided Summary Re-Ranking
- Point Cloud Completion Guided by Prior Knowledge via Causal Inference
- AIMS: All-Inclusive Multi-Level Segmentation
- NeurOCS: Neural NOCS Supervision for Monocular 3D Object Localization
- Towards Confidential Computing: A Secure Cloud Architecture for Big Data Analytics and AI
- Reliable and Interpretable Drift Detection in Streams of Short Texts
All 146
- Bayesian inference and neural estimation of acoustic wave propagation
- Image Hash Minimization for Tamper Detection
- Whitening-based Contrastive Learning of Sentence Embeddings
- Bridging the Language Gap: Dynamic Learning Strategies for Improving Multilingual Performance in LLMs
- Range-Based Equal Error Rate for Spoof Localization
- Investigating Pre-trained Audio Encoders in the Low-Resource Condition
- Tri-level Joint Natural Language Understanding for Multi-turn Conversational Datasets
- Predictability and Fairness in Load Aggregation with Deadband
- InDL: A New Dataset and Benchmark for In-Diagram Logic Interpretation based on Visual Illusion
- An Open-Source Gloss-Based Baseline for Spoken to Signed Language Translation
- OccCasNet: Occlusion-aware Cascade Cost Volume for Light Field Depth Estimation
- Parallel Data Helps Neural Entity Coreference Resolution
- Spot keywords from very noisy and mixed speech
- Towards Autonomous and Safe Last-mile Deliveries with AI-augmented Self-driving Delivery Robots
- KoSBi: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Application
- Decoupling Pseudo Label Disambiguation and Representation Learning for Generalized Intent Discovery
- Neural Machine Translation with Dynamic Graph Convolutional Decoder
- SQuARe: A Large-Scale Dataset of Sensitive Questions and Acceptable Responses Created Through Human-Machine Collaboration
- k-NNN: Nearest Neighbors of Neighbors for Anomaly Detection
- Plug-and-Play Knowledge Injection for Pre-trained Language Models
- HaVQA: A Dataset for Visual Question Answering and Multimodal Research in Hausa Language
- Amplification trojan network: Attack deep neural networks by amplifying their inherent weakness
- One Network, Many Masks: Towards More Parameter-Efficient Transfer Learning
- Evaluating GPT-3 Generated Explanations for Hateful Content Moderation
- RuSentNE-2023: Evaluating Entity-Oriented Sentiment Analysis on Russian News Texts
- Decoding the Underlying Meaning of Multimodal Hateful Memes
- OSPC: Online Sequential Photometric Calibration
- Stochastic Bridges as Effective Regularizers for Parameter-Efficient Tuning
- Choose your Data Wisely: A Framework for Semantic Counterfactuals
- Acceleration of stochastic gradient descent with momentum by averaging: finite-sample rates and asymptotic normality
- Lexical Retrieval Hypothesis in Multimodal Context
- Plug-and-Play Document Modules for Pre-trained Models
- MixDehazeNet : Mix Structure Block For Image Dehazing Network
- ConaCLIP: Exploring Distillation of Fully-Connected Knowledge Interaction Graph for Lightweight Text-Image Retrieval
- DPHuBERT: Joint Distillation and Pruning of Self-Supervised Speech Models
- Z-GMOT: Zero-shot Generic Multiple Object Tracking
- Caterpillar: A Pure-MLP Architecture with Shifted-Pillars-Concatenation
- DPFormer: Learning Differentially Private Transformer on Long-Tailed Data
- Robust Natural Language Understanding with Residual Attention Debiasing
- Cross-Domain Policy Adaptation via Value-Guided Data Filtering
- SimpSON: Simplifying Photo Cleanup with Single-Click Distracting Object Segmentation Network
- On the Value of Myopic Behavior in Policy Reuse
- Bayesian Decision Making to Localize Visual Queries in 2D
- More than Classification: A Unified Framework for Event Temporal Relation Extraction
- Incentivizing honest performative predictions with proper scoring rules
- NashFormer: Leveraging Local Nash Equilibria for Semantically Diverse Trajectory Prediction