Papers
Wed 17 May 2023
285 papers
- Tree of Thoughts: Deliberate Problem Solving with Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
- ReasonNet: End-to-End Driving with Temporal and Global ReasoningEnd-to-end autonomous driving → VLMs for autonomous driving
- Incorporating Attribution Importance for Improving Faithfulness MetricsLLM reasoning → Test-time compute and efficient thinking
- Preserve Your Own Correlation: A Noise Prior for Video Diffusion ModelsDiffusion models → Video generation
- FastComposer: Tuning-Free Multi-Subject Image Generation with Localized AttentionDiffusion models → Image generation, text-to-image and editing
- Rethinking the Open-Loop Evaluation of End-to-End Autonomous Driving in nuScenesEnd-to-end autonomous driving → End-to-end system architecture
- Accelerating Transformer Inference for Translation via Parallel DecodingEfficient LLM inference and serving → Speculative decoding
- SLiC-HF: Sequence Likelihood Calibration with Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- PaLM 2 Technical ReportLLM reasoning → Reasoning benchmarks and evaluation
- What You See is What You Read? Improving Text-Image Alignment EvaluationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
- End-To-End Latent Variational Diffusion Models for Inverse Problems in High Energy PhysicsDiffusion models → Flow matching, time series and science
- Raising the Bar for Certified Adversarial Robustness with Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
- Human Choice Prediction in Language-based Persuasion Games: Simulation-based Off-Policy EvaluationLLM agents and tool use → Social simulation and multi-agent debate
- Evaluating Object Hallucination in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
- Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Improving Language Model Negotiation with Self-Play and In-Context Learning from AI FeedbackSynthetic data and self-improvement for LLMs → Self-play RL for reasoning
- Controllable Mind Visual Diffusion ModelDiffusion models → Medical imaging and segmentation
- A proof of imitation of Wasserstein inverse reinforcement learning for multi-objective optimizationOffline RL and imitation learning from data → Inverse reinforcement learning
- Probing the Role of Positional Information in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Can Language Models Solve Graph Problems in Natural Language?LLM reasoning → Knowledge- and tool-augmented reasoning
- Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor WatermarkLLM safety and security → Watermarking generated content and models
- Pyramid Diffusion Models For Low-light Image EnhancementDiffusion models → Inverse problems and image restoration
- AD-KD: Attribution-Driven Knowledge Distillation for Language Model CompressionKnowledge distillation → Knowledge distillation for LLMs
- DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation LearningKnowledge distillation → Speech and audio distillation
- Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs SamplingLLM reasoning → Prompting and chain-of-thought reasoning
- Short-Term Stock Price Forecasting using exogenous variables and Machine Learning Algorithms
- Interpretable Graph Networks Formulate Universal Algebra Conjectures
- PrivaScissors: Enhance the Privacy of Collaborative Inference through the Lens of Mutual Information
- Leveraging Machine Learning for Multichain DeFi Fraud Detection
- Instruction Tuned Models are Quick Learners
- Motion-Scenario Decoupling for Rat-Aware Video Position Prediction: Strategy and Benchmark
- Prompt Engineering for Transformer-based Chemical Similarity Search Identifies Structurally Distinct Functional Analogues
- Transcending Grids: Point Clouds and Surface Representations Powering Neurological Processing
- Language Model Tokenizers Introduce Unfairness Between Languages
- PulseNet: Deep Learning ECG-signal classification using random augmentation policy and continous wavelet transform for canines
- Facial Expression Recognition at the Edge: CPU vs GPU vs VPU vs TPU
- Information processing via human soft tissue
- Machine Learning and VIIRS Satellite Retrievals for Skillful Fuel Moisture Content Monitoring in Wildfire Management
- Sequential Best-Arm Identification with Application to Brain-Computer Interface
- Properties of the ENCE and other MAD-based calibration metrics
- Compress, Then Prompt: Improving Accuracy-Efficiency Trade-off of LLM Inference with Transferable Prompt
- Assessing the predicting power of GPS data for aftershocks forecasting
- Comparison of Transfer Learning based Additive Manufacturing Models via A Case Study
- Token-wise Decomposition of Autoregressive Language Model Hidden States for Analyzing Model Predictions
- Temporal Knowledge Graph Forecasting Without Knowledge Using In-Context Learning
- ACRoBat: Optimizing Auto-batching of Dynamic Deep Learning at Compile Time
- Solving Cosine Similarity Underestimation between High Frequency Words by L2 Norm Discounting
- Improving Extrinsics between RADAR and LIDAR using Learning
- Inverted Non-maximum Suppression for more Accurate and Neater Face Detection
- INCLG: Inpainting for Non-Cleft Lip Generation with a Multi-Task Image Processing Network
- A Better Way to Do Masked Language Model Scoring
- Sim-MEES: Modular End-Effector System Grasping Dataset for Mobile Manipulators in Cluttered Environments
- MultiPlaneNeRF: Neural Radiance Field with Non-Trainable Representation
- Tensor Products and Hyperdimensional Computing
- Self-Supervised Learning for Physiologically-Based Pharmacokinetic Modeling in Dynamic PET
- From chocolate bunny to chocolate crocodile: Do Language Models Understand Noun Compounds?
- Smiling Women Pitching Down: Auditing Representational and Presentational Gender Biases in Image Generative AI
- Counterfactually Comparing Abstaining Classifiers
- HaSa: Hardness and Structure-Aware Contrastive Knowledge Graph Embedding
- Massively Multi-Lingual Event Understanding: Extraction, Visualization, and Search
- Short-Term Electricity Load Forecasting Using the Temporal Fusion Transformer: Effect of Grid Hierarchies and Data Sources
- Bring More Attention to Syntactic Symmetry for Automatic Postediting of High-Quality Machine Translations
- Integrated Conflict Management for UAM with Strategic Demand Capacity Balancing and Learning-based Tactical Deconfliction
- Deep Multiple Instance Learning with Distance-Aware Self-Attention
- Sparsity-depth Tradeoff in Infinitely Wide Deep Neural Networks
- Discovering Individual Rewards in Collective Behavior through Inverse Multi-Agent Reinforcement Learning
- Rethinking Multimodal Content Moderation from an Asymmetric Angle with Mixed-modality
- Tractable Probabilistic Graph Representation Learning with Graph-Induced Sum-Product Networks
- Generalization Bounds for Neural Belief Propagation Decoders
- Generating Bayesian Network Models from Data Using Tsetlin Machines
- Online List Labeling with Predictions
- Scalable and Safe Remediation of Defective Actions in Self-Learning Conversational Systems
- Statistical Knowledge Assessment for Large Language Models
- Learning Pose Image Manifolds Using Geometry-Preserving GANs and Elasticae
- IMAD: IMage-Augmented multi-modal Dialogue
- ChatGPT Perpetuates Gender Bias in Machine Translation and Ignores Non-Gendered Pronouns: Findings across Bengali and Five other Low-Resource Languages
- Exact Recovery for System Identification with More Corrupt Data than Clean Data
- Model-Free Robust Average-Reward Reinforcement Learning
- OR-NeRF: Object Removing from 3D Scenes Guided by Multiview Segmentation with Neural Radiance Fields
- EENED: End-to-End Neural Epilepsy Detection based on Convolutional Transformer
- Learning Likelihood Ratios with Neural Network Classifiers
- Edge Directionality Improves Learning on Heterophilic Graphs
- Bayesian Renormalization
- Predicting Side Effect of Drug Molecules using Recurrent Neural Networks
- Nine tips for ecologists using machine learning
- Bike2Vec: Vector Embedding Representations of Road Cycling Riders and Races
- Object Segmentation by Mining Cross-Modal Semantics
- CHNNet: An Artificial Neural Network With Connected Hidden Neurons
- Analysing Biomedical Knowledge Graphs using Prime Adjacency Matrices
- Solitary pulmonary nodules prediction for lung cancer patients using nomogram and machine learning
- Towards Robust Probabilistic Modeling on SO(3) via Rotation Laplace Distribution
- Reconstruction Error-based Anomaly Detection with Few Outlying Examples
- DualVector: Unsupervised Vector Font Synthesis with Dual-Part Representation
- Topology Optimization using Neural Networks with Conditioning Field Initialization for Improved Efficiency
- AnalogNAS: A Neural Network Design Framework for Accurate Inference with Analog In-Memory Computing
- Time Series Clustering With Random Convolutional Kernels
- LPMM: Intuitive Pose Control for Neural Talking-Head Model via Landmark-Parameter Morphable Model
- Towards Generalist Robots: A Promising Paradigm via Generative Simulation
- VVC+M: Plug and Play Scalable Image Coding for Humans and Machines
- DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining
All 285
- ZeroFlow: Scalable Scene Flow via Distillation
- Evolving Tsukamoto Neuro Fuzzy Model for Multiclass Covid 19 Classification with Chest X Ray Images
- CLIP-GCD: Simple Language Guided Generalized Category Discovery
- Towards Multi-Layered 3D Garments Animation
- Scratch Copilot Evaluation: Assessing AI-Assisted Creative Coding for Families
- PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering
- On Consistency of Signature Using Lasso
- AI Friends: A Design Framework for AI-Powered Creative Programming for Youth
- Wasserstein Gradient Flows for Optimizing Gaussian Mixture Policies
- BAD: BiAs Detection for Large Language Models in the context of candidate screening
- Variational Classification
- RelationMatch: Matching In-batch Relationships for Semi-supervised Learning
- Optimality of Message-Passing Architectures for Sparse Graphs
- Elaborative Simplification as Implicit Questions Under Discussion
- Logit-Based Ensemble Distribution Distillation for Robust Autoregressive Sequence Uncertainties
- Large-Scale Text Analysis Using Generative Language Models: A Case Study in Discovering Public Value Expressions in AI Patents
- Active Learning in Symbolic Regression with Physical Constraints
- Explainable Multi-Agent Reinforcement Learning for Temporal Queries
- Interactive Learning of Hierarchical Tasks from Dialog with GPT
- Confidence-Guided Semi-supervised Learning in Land Cover Classification
- Extracting a functional representation from a dictionary for non-rigid shape matching
- G-Adapter: Towards Structure-Aware Parameter-Efficient Transfer Learning for Graph Transformer Networks
- Joint Denoising and Few-angle Reconstruction for Low-dose Cardiac SPECT Using a Dual-domain Iterative Network with Adaptive Data Consistency
- Cross-domain Iterative Network for Simultaneous Denoising, Limited-angle Reconstruction, and Attenuation Correction of Low-dose Cardiac SPECT
- Controllable Speaking Styles Using a Large Language Model
- CostFormer:Cost Transformer for Cost Aggregation in Multi-view Stereo
- Automatic Photo Orientation Detection with Convolutional Neural Networks
- LeTI: Learning to Generate from Textual Interactions
- Investigating image-based fallow weed detection performance on Raphanus sativus and Avena sativa at speeds up to 30 km h-1
- MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Tasks
- Rethinking Data Augmentation for Tabular Data in Deep Learning
- FACE: Evaluating Natural Language Generation with Fourier Analysis of Cross-Entropy
- UniEX: An Effective and Efficient Framework for Unified Information Extraction via a Span-extractive Perspective
- One-Prompt to Segment All Medical Images
- Binarized Spectral Compressive Imaging
- Estimation of Remaining Useful Life and SOH of Lithium Ion Batteries (For EV Vehicles)
- DualFL: A Duality-based Federated Learning Algorithm with Communication Acceleration in the General Convex Regime
- Infinite Class Mixup
- Linear Query Approximation Algorithms for Non-monotone Submodular Maximization under Knapsack Constraint
- Explain Any Concept: Segment Anything Meets Concept-Based Explanation
- Towards More Robust NLP System Evaluation: Handling Missing Scores in Benchmarks
- Chain-of-Symbol Prompting Elicits Planning in Large Langauge Models
- Demonstrating Large-Scale Package Manipulation via Learned Metrics of Pick Success
- Boosting Local Spectro-Temporal Features for Speech Analysis
- State Representation Learning Using an Unbalanced Atlas
- Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM's Translation Capability
- M3KE: A Massive Multi-Level Multi-Subject Knowledge Evaluation Benchmark for Chinese Large Language Models
- From Region to Patch: Attribute-Aware Foreground-Background Contrastive Learning for Fine-Grained Fashion Retrieval
- Runtime Analyses of Multi-Objective Evolutionary Algorithms in the Presence of Noise
- Improving Link Prediction in Social Networks Using Local and Global Features: A Clustering-based Approach
- SAM for Poultry Science
- Sharpness & Shift-Aware Self-Supervised Learning
- MemoryBank: Enhancing Large Language Models with Long-Term Memory
- Can Deep Network Balance Copy-Move Forgery Detection and Distinguishment?
- A quantitative study of NLP approaches to question difficulty estimation
- OpenSLU: A Unified, Modularized, and Extensible Toolkit for Spoken Language Understanding
- How does Contrastive Learning Organize Images?
- Reaching Kesten-Stigum Threshold in the Stochastic Block Model under Node Corruptions
- Advancing Unsupervised Low-light Image Enhancement: Noise Estimation, Illumination Interpolation, and Self-Regulation
- rWISDM: Repaired WISDM, a Public Dataset for Human Activity Recognition
- Separability and Scatteredness (S&S) Ratio-Based Efficient SVM Regularization Parameter, Kernel, and Kernel Parameter Selection
- Deep Learning Applications Based on WISE Infrared Data: Classification of Stars, Galaxies and Quasars
- CHMMOTv1 -- Cardiac and Hepatic Multi-Echo (T2*) MRI Images and Clinical Dataset for Iron Overload on Thalassemia Patients
- A Novel Stochastic LSTM Model Inspired by Quantum Machine Learning
- Object Re-Identification from Point Clouds
- Shielded Representations: Protecting Sensitive Attributes Through Iterative Gradient-Based Projection
- Exploring the Space of Key-Value-Query Models with Intention
- Echoes of Biases: How Stigmatizing Language Affects AI Performance
- IDO-VFI: Identifying Dynamics via Optical Flow Guidance for Video Frame Interpolation with Events
- Deep and Fast Approximate Order Independent Transparency
- A Survey on Zero Pronoun Translation
- Boosting Distress Support Dialogue Responses with Motivational Interviewing Strategy
- Curriculum Learning in Job Shop Scheduling using Reinforcement Learning
- Variable-length Neural Interlingua Representations for Zero-shot Neural Machine Translation
- Evaluating Dynamic Conditional Quantile Treatment Effects with Applications in Ridesharing
- Algorithms for Boolean Matrix Factorization using Integer Programming
- Exploring the cloud of feature interaction scores in a Rashomon set
- Knowledge-enhanced Mixed-initiative Dialogue System for Emotional Support Conversations
- Goal-Conditioned Supervised Learning with Sub-Goal Prediction
- Pragmatic Reasoning in Structured Signaling Games
- Large Language Models Leverage External Knowledge to Extend Clinical Insight Beyond Language Boundaries
- Collective Large-scale Wind Farm Multivariate Power Output Control Based on Hierarchical Communication Multi-Agent Proximal Policy Optimization
- Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarks
- A Global-Local Approximation Framework for Large-Scale Gaussian Process Modeling
- Efficient Error Certification for Physics-Informed Neural Networks
- Personality Understanding of Fictional Characters during Book Reading
- Cultural evolution via iterated learning and communication explains efficient color naming systems
- Multi-Grained Knowledge Retrieval for End-to-End Task-Oriented Dialog
- CS-PCN: Context-Space Progressive Collaborative Network for Image Denoising
- An Empirical Study on the Language Modal in Visual Question Answering
- Additive manifesto decomposition: A policy domain aware method for understanding party positioning
- Generation of 3D Molecules in Pockets via Language Model
- Automatic 3D Registration of Dental CBCT and Face Scan Data using 2D Projection Images
- Fusion-S2iGan: An Efficient and Effective Single-Stage Framework for Speech-to-Image Generation
- Principal Uncertainty Quantification with Spatial Correlation for Image Restoration Problems
- Empirical Analysis of Oral and Nasal Vowels of Konkani
- FICNN: A Framework for the Interpretation of Deep Convolutional Neural Networks
- Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models
- Bridging the Gap: Enhancing the Utility of Synthetic Data via Post-Processing Techniques
- Can Deep Learning Reliably Recognize Abnormality Patterns on Chest X-rays? A Multi-Reader Study Examining One Month of AI Implementation in Everyday Radiology Clinical Practice
- An Ensemble Deep Learning Approach for COVID-19 Severity Prediction Using Chest CT Scans
- Automatic Hyperparameter Tuning in Sparse Matrix Factorization
- Neuro-Symbolic AI for Compliance Checking of Electrical Control Panels
- Adaptive aggregation of Monte Carlo augmented decomposed filters for efficient group-equivariant convolutional neural network
- Predicting Tweet Engagement with Graph Neural Networks
- Use of a Taxonomy of Empathetic Response Intents to Control and Interpret Empathy in Neural Chatbots
- Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challenges
- Semi-supervised Quality Evaluation of Colonoscopy Procedures
- CWD30: A Comprehensive and Holistic Dataset for Crop Weed Recognition in Precision Agriculture
- Imbalanced Aircraft Data Anomaly Detection
- Face Recognition Using Synthetic Face Data
- Dynamic Structural Brain Network Construction by Hierarchical Prototype Embedding GCN using T1-MRI
- Cold PAWS: Unsupervised class discovery and addressing the cold-start problem for semi-supervised learning
- Unveiling the Potential of Counterfactuals Explanations in Employability
- Rethinking Boundary Discontinuity Problem for Oriented Object Detection
- XAI for Self-supervised Clustering of Wireless Spectrum Activity
- A hybrid feature learning approach based on convolutional kernels for ATM fault prediction using event-log data
- Physics-driven machine learning for the prediction of coronal mass ejections' travel times
- Finding an ε-close Variation of Parameters in Bayesian Networks
- The Impact of Missing Data on Causal Discovery: A Multicentric Clinical Study
- TG-VQA: Ternary Game of Video Question Answering
- Two-Stream Regression Network for Dental Implant Position Prediction
- Optimal Weighted Random Forests
- Risk Assessment of Lymph Node Metastases in Endometrial Cancer Patients: A Causal Approach
- SHoP: A Deep Learning Framework for Solving High-order Partial Differential Equations
- A Survey on Causal Discovery: Theory and Practice
- TextSLAM: Visual SLAM with Semantic Planar Text Features
- Colonoscopy Coverage Revisited: Identifying Scanning Gaps in Real-Time
- An efficient solver for ASP(Q)
- Transfer Learning for Fine-grained Classification Using Semi-supervised Learning and Visual Transformers
- Utility Theory of Synthetic Data Generation
- A Survey on Multi-Objective based Parameter Optimization for Deep Learning
- When Gradient Descent Meets Derivative-Free Optimization: A Match Made in Black-Box Scenario
- EfficientSCI: Densely Connected Network with Space-time Factorization for Large-scale Video Snapshot Compressive Imaging
- An Interactively Reinforced Paradigm for Joint Infrared-Visible Image Fusion and Saliency Object Detection
- Restoring Images Captured in Arbitrary Hybrid Adverse Weather Conditions in One Go
- BASEN: Time-Domain Brain-Assisted Speech Enhancement Network with Convolutional Cross Attention in Multi-talker Conditions
- A Fusion Model: Towards a Virtual, Physical and Cognitive Integration and its Principles
- Dual Semantic Knowledge Composed Multimodal Dialog Systems
- A robust multi-domain network for short-scanning amyloid PET reconstruction
- S3Track: Self-supervised Tracking with Soft Assignment Flow
- Stochastic Ratios Tracking Algorithm for Large Scale Machine Learning Problems
- Smart Word Suggestions for Writing Assistance
- River of No Return: Graph Percolation Embeddings for Efficient Knowledge Graph Reasoning
- Real-Time Flying Object Detection with YOLOv8
- Variable Length Embeddings
- SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation
- Quantum neural networks form Gaussian processes
- The Adversarial Consistency of Surrogate Risks for Binary Classification
- Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models
- HICO-DET-SG and V-COCO-SG: New Data Splits for Evaluating the Systematic Generalization Performance of Human-Object Interaction Detection Models
- Understanding the Initial Condensation of Convolutional Neural Networks
- AdaMSS: Adaptive Multi-Modality Segmentation-to-Survival Learning for Survival Outcome Prediction from PET/CT Images
- Pittsburgh Learning Classifier Systems for Explainable Reinforcement Learning: Comparing with XCS
- Demonstration-free Autonomous Reinforcement Learning via Implicit and Bidirectional Curriculum
- "I'm fully who I am": Towards Centering Transgender and Non-Binary Voices to Measure Biases in Open Language Generation
- Mastering Long-Tail Complexity on Graphs: Characterization, Learning, and Generalization
- Mitigating Group Bias in Federated Learning: Beyond Local Fairness
- Model-based Validation as Probabilistic Inference
- Tinto: Multisensor Benchmark for 3D Hyperspectral Point Cloud Segmentation in the Geosciences
- CageViT: Convolutional Activation Guided Efficient Vision Transformer
- A Genetic Fuzzy System for Interpretable and Parsimonious Reinforcement Learning Policies
- Assessing the Impact of Context Inference Error and Partial Observability on RL Methods for Just-In-Time Adaptive Interventions
- Incremental Outlier Detection Modelling Using Streaming Analytics in Finance & Health Care
- On the ISS Property of the Gradient Flow for Single Hidden-Layer Neural Networks with Linear Activations
- Privacy Loss of Noisy Stochastic Gradient Descent Might Converge Even for Non-Convex Losses
- Efficient Equivariant Transfer Learning from Pretrained Models
- Balancing Lexical and Semantic Quality in Abstractive Summarization
- Complementary Classifier Induced Partial Label Learning
- Convergence and Privacy of Decentralized Nonconvex Optimization with Gradient Clipping and Communication Compression
- Integrating Multiple Sources Knowledge for Class Asymmetry Domain Adaptation Segmentation of Remote Sensing Images
- Clustering-Aware Negative Sampling for Unsupervised Sentence Representation
- SS-BSN: Attentive Blind-Spot Network for Self-Supervised Denoising with Nonlocal Self-Similarity
- Simplifying Distributed Neural Network Training on Massive Graphs: Randomized Partitions Improve Model Aggregation
- A survey of the Vision Transformers and their CNN-Transformer based Variants
- Semantic Similarity Measure of Natural Language Text through Machine Learning and a Keyword-Aware Cross-Encoder-Ranking Summarizer -- A Case Study Using UCGIS GIS&T Body of Knowledge
- Generative Model-based Simulation of Driver Behavior when Using Control Input Interface for Teleoperated Driving in Unstructured Canyon Terrains
- A Signed Subgraph Encoding Approach via Linear Optimization for Link Sign Prediction
- The Principle of Uncertain Maximum Entropy
- The Jaseci Programming Paradigm and Runtime Stack: Building Scale-out Production Applications Easy and Fast
- Explaining black box text modules in natural language with language models
- Epsilon Sampling Rocks: Investigating Sampling Strategies for Minimum Bayes Risk Decoding for Machine Translation
- Smaller Language Models are Better Black-box Machine-Generated Text Detectors
- Knowledge Graph Completion Models are Few-shot Learners: An Empirical Study of Relation Labeling in E-commerce with LLMs
- CoEdIT: Text Editing by Task-Specific Instruction Tuning