Papers
Fri 21 Apr 2023
160 papers
- Speed Is All You Need: On-Device Acceleration of Large Diffusion Models via GPU-Aware OptimizationsDiffusion models → Diffusion foundations and sampling
- Multi-Modal World Model for Physical Robot Interactions: Simultaneous Visual and Tactile Predictions for Enhanced AccuracyWorld models → Embodied and robot world models
- ChatABL: Abductive Learning via Natural Language Interaction with ChatGPTLLM reasoning → Reasoning benchmarks and evaluation
- Improved Diffusion-based Image Colorization via Piggybacked ModelsDiffusion models → Image generation, text-to-image and editing
- Self-Supervised Adversarial Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
- SILVR: Guided Diffusion for Molecule GenerationDiffusion models → Flow matching, time series and science
- RoCOCO: Robustness Benchmark of MS-COCO to Stress-test Image-Text Matching ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision TransformersEfficient LLM inference and serving → Token pruning and merging for ViTs
- ReCEval: Evaluating Reasoning Chains via Correctness and InformativenessLLM reasoning → Reasoning benchmarks and evaluation
- Long-Term Photometric Consistent Novel View Synthesis with Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
- Cross-Gate MLP with Protein Complex Invariant Embedding is A One-Shot Antibody Designer
- ANALYSE -- Learning to Attack Cyber-Physical Energy Systems With Intelligent Agents
- Reconstruction-based LSTM-Autoencoder for Anomaly-based DDoS Attack Detection over Multivariate Time-Series Data
- Deep learning models for price forecasting of financial time series: A review of recent advancements: 2020-2022
- Score-based Transport Modeling for Mean-Field Fokker-Planck Equations
- Building Multimodal AI Chatbots
- Hybrid Deepfake Detection Utilizing MLP and LSTM
- Generative AI Perceptions: A Survey to Measure the Perceptions of Faculty, Staff, and Students on Generative AI Tools in Academia
- The Dark Side of ChatGPT: Legal and Ethical Challenges from Stochastic Parrots and Hallucination
- Shot Optimization in Quantum Machine Learning Architectures to Accelerate Training
- Optimizing fairness tradeoffs in machine learning with multiobjective meta-models
- Small-footprint slimmable networks for keyword spotting
- Variance-Reduced Gradient Estimation via Noise-Reuse in Online Evolution Strategies
- PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel
- The Role of AI in Human-AI Creative Writing for Hong Kong Secondary Students
- Semantic-Aware Graph Matching Mechanism for Multi-Label Image Recognition
- Estimating Motor Symptom Presence and Severity in Parkinson's Disease from Wrist Accelerometer Time Series using ROCKET and InceptionTime
- Benchmarking Low-Shot Robustness to Natural Distribution Shifts
- Who's the Best Detective? LLMs vs. MLs in Detecting Incoherent Fourth Grade Math Answers
- UBC-DLNLP at SemEval-2023 Task 12: Impact of Transfer Learning on African Sentiment Analysis
- Machine Learning and the Future of Bayesian Computation
- eWaSR -- an embedded-compute-ready maritime obstacle detection network
- Hybrid quantum physics-informed neural networks for simulating computational fluid dynamics in complex shapes
- AutoNeRF: Training Implicit Scene Representations with Autonomous Agents
- Adapting model-based deep learning to multiple acquisition conditions: Ada-MoDL
- Effective Neural Network L0 Regularization With BinMask
- Spatial-Language Attention Policies for Efficient Robot Learning
- Advances in Deep Concealed Scene Understanding
- Probabilistic selection and design of concrete using machine learning
- A Group-Specific Approach to NLP for Hate Speech Detection
- Learn What NOT to Learn: Towards Generative Safety in Chatbots
- DP-Adam: Correcting DP Bias in Adam's Second Moment Estimation
- SSS3D: Fast Neural Architecture Search For Efficient Three-Dimensional Semantic Segmentation
- Fast GraspNeXt: A Fast Self-Attention Neural Network Architecture for Multi-task Learning in Computer Vision Tasks for Robotic Grasping on the Edge
- Automatically identifying ordinary differential equations from data
- Task-Adaptive Pseudo Labeling for Transductive Meta-Learning
- Granular-ball computing: an efficient, robust, and interpretable adaptive multi-granularity representation and computation method
- ChatGPT, Large Language Technologies, and the Bumpy Road of Benefiting Humanity
- Isotonic Mechanism for Exponential Family Estimation in Machine Learning Peer Review
- Emergent and Predictable Memorization in Large Language Models
- Low-Variance Gradient Estimation in Unrolled Computation Graphs with ES-Single
- H2TF for Hyperspectral Image Denoising: Where Hierarchical Nonlinear Transform Meets Hierarchical Matrix Factorization
- Convergence of Message Passing Graph Neural Networks with Generic Aggregation On Large Random Graphs
- Deep-Learning-based Fast and Accurate 3D CT Deformable Image Registration in Lung Cancer
- Plug-and-Play split Gibbs sampler: embedding deep generative priors in Bayesian inference
- Tree-Structured Parzen Estimator: Understanding Its Algorithm Components and Their Roles for Better Empirical Performance
- Semantics, Ontology and Explanation
- China and the U.S. produce more impactful AI research when collaborating together
- BoDiffusion: Diffusing Sparse Observations for Full-Body Human Motion Synthesis
- A vector quantized masked autoencoder for speech emotion recognition
- Implicit Neural Head Synthesis via Controllable Local Deformation Fields
- Inducing anxiety in large language models can induce bias
- A Convolutional Spiking Network for Gesture Recognition in Brain-Computer Interfaces
- Approximate Shielding of Atari Agents for Safe Exploration
- Federated Learning for Predictive Maintenance and Quality Inspection in Industrial Applications
- Prediction, Learning, Uniform Convergence, and Scale-sensitive Dimensions
- Analog Feedback-Controlled Memristor programming Circuit for analog Content Addressable Memory
- Exogenous Data in Forecasting: FARM -- A New Measure for Relevance Evaluation
- Robot-Enabled Construction Assembly with Automated Sequence Planning based on ChatGPT: RoboGPT
- DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction
- Self-Correcting Bayesian Optimization through Bayesian Active Learning
- BERT Based Clinical Knowledge Extraction for Biomedical Knowledge Graph Construction and Analysis
- Information Extraction from Documents: Question Answering vs Token Classification in real-world setups
- INK: Inheritable Natural Backdoor Attack Against Model Distillation
- IBBT: Informed Batch Belief Trees for Motion Planning Under Uncertainty
- Balancing Simulation-based Inference for Conservative Posteriors
- Evaluating Transformer Language Models on Arithmetic Operations Using Number Decomposition
- LEIA: Linguistic Embeddings for the Identification of Affect
- Can GPT-4 Perform Neural Architecture Search?
- An Incomplete Tensor Tucker decomposition based Traffic Speed Prediction Method
- A Cubic-regularized Policy Newton Algorithm for Reinforcement Learning
- Factored Neural Representation for Scene Understanding
- Deep Metric Learning Assisted by Intra-variance in A Semi-supervised View of Learning
- Gradient Derivation for Learnable Parameters in Graph Attention Networks
- Self-Attention in Colors: Another Take on Encoding Graph Structure in Transformers
- Learning Dictionaries from Physical-Based Interpolation for Water Network Leak Localization
- Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study
- Near-Optimal Decentralized Momentum Method for Nonconvex-PL Minimax Problems
- A Common Misassumption in Online Experiments with Machine Learning Models
- GCNH: A Simple Method For Representation Learning On Heterophilous Graphs
- FindVehicle and VehicleFinder: A NER dataset for natural language-based vehicle retrieval and a keyword-based cross-modal vehicle retrieval system
- Reconciling High Accuracy, Cost-Efficiency, and Low Latency of Inference Serving Systems
- Transformer-Based Autonomous Driving Models and Deployment-Oriented Compression: A Survey
- Learning Robust, Agile, Natural Legged Locomotion Skills in the Wild
- Med-Tuning: A New Parameter-Efficient Tuning Framework for Medical Volumetric Segmentation
- Ultra Sharp : Study of Single Image Super Resolution using Residual Dense Network
- Application of quantum-inspired generative models to small molecular datasets
- FreMIM: Fourier Transform Meets Masked Image Modeling for Medical Image Segmentation
- On the Importance of Exploration for Real Life Learned Algorithms
- Text2Time: Transformer-based Article Time Period Prediction
All 160
- SequeL: A Continual Learning Library in PyTorch and JAX
- HabitatDyn Dataset: Dynamic Object Detection to Kinematics Estimation
- What Do GNNs Actually Learn? Towards Understanding their Representations
- How Well Does the Metropolis Algorithm Cope With Local Optima?
- Better Sign Language Translation with Monolingual Data
- Cross-domain Denoising for Low-dose Multi-frame Spiral Computed Tomography
- A Deep Learning algorithm to accelerate Algebraic Multigrid methods in Finite Element solvers of 3D elliptic PDEs
- Learn to Cluster Faces with Better Subgraphs
- Rolling Lookahead Learning for Optimal Classification Trees
- Deep Attention Unet: A Network Model with Global Feature Perception Ability
- Individual Fairness in Bayesian Neural Networks
- Don't worry about mistakes! Glass Segmentation Network via Mistake Correction
- Rethinking Benchmarks for Cross-modal Image-text Retrieval
- Auditing and Generating Synthetic Data with Controllable Trust Trade-offs
- Can SAM Count Anything? An Empirical Study on SAM Counting
- Automated Static Camera Calibration with Intelligent Vehicles
- Tokenization Preference for Human and Machine Learning Model: An Annotation Study
- Downstream Task-Oriented Neural Tokenizer Optimization with Vocabulary Restriction as Post Processing
- EPLKG: Efficient Prompt Learning with Knowledge Graph
- DeformableFormer: Classification of Endoscopic Ultrasound Guided Fine Needle Biopsy in Pancreatic Diseases
- Classical-to-Quantum Sequence Encoding in Genomics
- Which Factors Predict the Chat Experience of a Natural Language Generation Dialogue Service?
- Eyettention: An Attention-based Dual-Sequence Model for Predicting Human Scanpaths during Reading
- Denial-of-Service or Fine-Grained Control: Towards Flexible Model Poisoning Attacks on Federated Learning
- Contrastive Language, Action, and State Pre-training for Robot Learning
- Omni-Line-of-Sight Imaging for Holistic Shape Reconstruction
- A Revisit of the Normalized Eight-Point Algorithm and A Self-Supervised Deep Solution
- DEIR: Efficient and Robust Exploration through Discriminative-Model-Based Episodic Intrinsic Rewards
- Deep Multiview Clustering by Contrasting Cluster Assignments
- How good are variational autoencoders at transfer learning?
- BPJDet: Extended Object Representation for Generic Body-Part Joint Detection
- Hyperbolic Geometry in Computer Vision: A Survey
- Towards Realizing the Value of Labeled Target Samples: a Two-Stage Approach for Semi-Supervised Domain Adaptation
- GeoLayoutLM: Geometric Pre-training for Visual Information Extraction
- Missing Modality Robustness in Semi-Supervised Multi-Modal Semantic Segmentation
- Interpretable and Robust AI in EEG Systems: A Survey
- Algorithmic Information Forecastability
- Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedback
- Multi-scale Evolutionary Neural Architecture Search for Deep Spiking Neural Networks
- Joint Client Assignment and UAV Route Planning for Indirect-Communication Federated Learning
- Multi-Modal Deep Learning for Credit Rating Prediction Using Text and Numerical Data Streams
- KitchenScale: Learning to predict ingredient quantities from recipe contexts
- Schooling to Exploit Foolish Contracts
- Generate your neural signals from mine: individual-to-individual EEG converters
- Linear building pattern recognition via spatial knowledge graph
- Usenix'23 Extended Version: Smart Learning to Find Dumb Contracts
- Reinforcement Learning Approaches for Traffic Signal Control under Missing Data
- FSNet: Redesign Self-Supervised MonoDepth for Full-Scale Depth Prediction for Autonomous Driving
- Physics-informed Neural Network Combined with Characteristic-Based Split for Solving Navier-Stokes Equations
- Picking Up Quantization Steps for Compressed Image Classification
- Adversarial Infrared Blocks: A Multi-view Black-box Attack to Thermal Infrared Detectors in Physical World
- Persistently Trained, Diffusion-assisted Energy-based Models
- TC-GAT: Graph Attention Network for Temporal Causality Discovery
- Graph based Label Enhancement for Multi-instance Multi-label learning
- Interactive System-wise Anomaly Detection
- Power Grid Behavioral Patterns and Risks of Generalization in Applied Machine Learning
- GMValuator: Similarity-based Data Valuation for Generative Models
- SkinGPT-4: An Interactive Dermatology Diagnostic System with Visual Large Language Model
- VisFusion: Visibility-aware Online 3D Scene Reconstruction from Videos
- A generalised multi-factor deep learning electricity load forecasting model for wildfire-prone areas