Papers
Thu 28 Sep 2023
271 papers
- Stochastic Digital Twin for Copy Detection PatternsDiffusion models → Diffusion foundations and sampling
- Post-Training Overfitting Mitigation in DNN ClassifiersLLM safety and security → Backdoor and data poisoning attacks
- SatDM: Synthesizing Realistic Satellite Image with Semantic Layout Conditioning using Diffusion ModelsDiffusion models → Inverse problems and image restoration
- Promptbreeder: Self-Referential Self-Improvement Via Prompt EvolutionLLM reasoning → Prompting and chain-of-thought reasoning +1
- Memory in Plain Sight: Surveying the Uncanny Resemblances of Associative Memories and Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- ELIP: Efficient Discriminative Language-Image Pre-training with Fewer Vision TokensEfficient LLM inference and serving → Visual token pruning in multimodal models
- Robust Offline Reinforcement Learning -- Certify the Confidence IntervalOffline RL and imitation learning from data → Offline RL algorithms
- Stress Testing Chain-of-Thought Prompting for Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
- Semantic Scene Difference Detection in Daily Life Patroling by Mobile Robots using Pre-Trained Large-Scale Vision-Language ModelMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
- MotionLM: Multi-Agent Motion Forecasting as Language ModelingLLM agents and tool use → Multimodal and embodied agents
- CCEdit: Creative and Controllable Video Editing via Diffusion ModelsDiffusion models → Video generation
- Towards Poisoning Fair RepresentationsLLM safety and security → Backdoor and data poisoning attacks
- Neuro Symbolic Reasoning for Planning: Counterexample Guided Inductive Synthesis using Large Language Models and Satisfiability SolvingLLM reasoning → Reasoning benchmarks and evaluation
- QwenGrasp: A Usage of Large Vision-Language Model for Target-Oriented GraspingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
- Cyber Sentinel: Exploring Conversational Agents in Streamlining Security Tasks with GPT-4LLM agents and tool use → Agent threats, guardrails and governance
- Distilling ODE Solvers of Diffusion Models into Smaller StepsDiffusion models → Diffusion foundations and sampling
- AutoCLIP: Auto-tuning Zero-Shot Classifiers for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Uncertainty-Aware Decision Transformer for Stochastic Driving EnvironmentsEnd-to-end autonomous driving → Reinforcement learning for driving +1
- Human Feedback is not Gold StandardLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
- DeepPCR: Parallelizing Sequential Operations in Neural NetworksDiffusion models → Diffusion foundations and sampling
- CasIL: Cognizing and Imitating Skills via a Dual Cognition-Action ArchitectureOffline RL and imitation learning from data → Robot manipulation imitation learning
- At Which Training Stage Does Code Data Help LLMs Reasoning?LLM reasoning → Reasoning benchmarks and evaluation
- DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language ModelsEnd-to-end autonomous driving → Large language models for driving
- Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence ConstraintsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
- VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Generative AI Enables Structural Brain Network Construction from fMRI via Symmetric Diffusion LearningDiffusion models → Medical imaging and segmentation
- Stackelberg Batch Policy LearningOffline RL and imitation learning from data → Offline RL algorithms
- LAE-ST-MoE: Boosted Language-Aware Encoder Using Speech Translation Auxiliary Task for E2E Code-switching ASRMixture-of-experts → Multimodal MoE models
- Distill to Delete: Unlearning in Graph Networks with Knowledge DistillationLLM safety and security → Graph unlearning +1
- The Trickle-down Impact of Reward (In-)consistency on RLHFLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Compositional Sculpting of Iterative Generative ProcessesDiffusion models → Diffusion foundations and sampling
- TPE: Towards Better Compositional Reasoning over Conceptual Tools with Multi-persona CollaborationLLM reasoning → Reasoning benchmarks and evaluation
- Bayesian Cram'er-Rao Bound Estimation with Score-Based ModelsDiffusion models → Diffusion foundations and sampling
- Infer and Adapt: Bipedal Locomotion Reward Learning from Demonstrations via Inverse Reinforcement LearningOffline RL and imitation learning from data → Real-world robot offline RL
- EWasteNet: A Two-Stream Data Efficient Image Transformer Approach for E-Waste Classification
- Large Language Models in Finance: A Survey
- Simulation-based Safety Assurance for an AVP System incorporating Learning-Enabled Components
- AI Potentiality and Awareness: A Position Paper from the Perspective of Human-AI Teaming in Cybersecurity
- Automatic Identification of Stone-Handling Behaviour in Japanese Macaques Using LabGym Artificial Intelligence
- Deep Learning based Systems for Crater Detection: A Review
- Design of JiuTian Intelligent Network Simulation Platform
- Automated Chest X-Ray Report Generator Using Multi-Model Deep Learning Approach
- Optimizing Multicarrier Multiantenna Systems for LoS Channel Charting
- Context-Based Tweet Engagement Prediction
- Chatmap : Large Language Model Interaction with Cartographic Data
- Attention Sorting Combats Recency Bias In Long Context Language Models
- De-SaTE: Denoising Self-attention Transformer Encoders for Li-ion Battery Health Prognostics
- CtxMIM: Context-Enhanced Masked Image Modeling for Remote Sensing Image Understanding
- 3D-Mol: A Novel Contrastive Learning Framework for Molecular Property Prediction with 3D Information
- On the Contractivity of Plug-and-Play Operators
- A Sign Language Recognition System with Pepper, Lightweight-Transformer, and LLM
- Algorithmic Recourse in Abnormal Multivariate Time Series
- Superpixel Transformers for Efficient Semantic Segmentation
- Beyond Gut Feel: Using Time Series Transformers to Find Investment Gems
- The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing
- Message Propagation Through Time: An Algorithm for Sequence Dependency Retention in Time Series Modeling
- Investigating Human-Identifiable Features Hidden in Adversarial Perturbations
- LEF: Late-to-Early Temporal Fusion for LiDAR 3D Object Detection
- Preface: A Data-driven Volumetric Prior for Few-shot Ultra High-resolution Face Synthesis
- Improved Generalization Bounds for Transductive Learning by Transductive Local Complexity and Its Applications
- Applications of Federated Learning in IoT for Hyper Personalisation
- Sketch2CAD: 3D CAD Model Reconstruction from 2D Sketch using Visual Transformer
- Space-Time Attention with Shifted Non-Local Search
- Optimal Nonlinearities Improve Generalization Performance of Random Features
- DeBERTinha: A Multistep Approach to Adapt DebertaV3 XSmall for Brazilian Portuguese Natural Language Processing Task
- A Mean Field Approach to Empirical Bayes Estimation in High-dimensional Linear Regression
- Constant Approximation for Individual Preference Stable Clustering
- Propagation and Attribution of Uncertainty in Medical Imaging Pipelines
- An analysis of the derivative-free loss method for solving PDEs
- A Comprehensive View of Personalized Federated Learning on Heterogeneous Clinical Datasets
- Multi-Bellman operator for convergence of Q-learning with linear function approximation
- MEM: Multi-Modal Elevation Mapping for Robotics and Learning
- PROSE: Predicting Operators and Symbolic Expressions using Multimodal Transformers
- GraB-sampler: Optimal Permutation-based SGD Data Sampler for PyTorch
- Granularity at Scale: Estimating Neighborhood Socioeconomic Indicators from High-Resolution Orthographic Imagery and Hybrid Learning
- Curriculum-Driven Edubot: A Framework for Developing Language Learning Chatbots Through Synthesizing Conversational Data
- Ultra-low-power Image Classification on Neuromorphic Hardware
- Photonic Accelerators for Image Segmentation in Autonomous Driving and Defect Detection
- Surgical Tattoos in Infrared: A Dataset for Quantifying Tissue Tracking and Mapping
- Hallucination Reduction in Long Input Text Summarization
- Intriguing properties of generative classifiers
- How many words does ChatGPT know? The answer is ChatWords
- Neural scaling laws for phenotypic drug discovery
- XVO: Generalized Visual Odometry via Cross-Modal Self-Training
- Persona-Coded Poly-Encoder: Persona-Guided Multi-Stream Conversational Sentence Scoring
- Discovering environments with XRM
- Harnessing Diverse Data for Global Disaster Prediction: A Multimodal Framework
- Implicit Gaussian process representation of vector fields over arbitrary latent manifolds
- Efficient Training of One Class Classification-SVMs
- Predicting Long-term Renal Impairment in Post-COVID-19 Patients with Machine Learning Algorithms
- High Throughput Training of Deep Surrogates from Large Ensemble Runs
- Supervised Learning Models for Early Detection of Albuminuria Risk in Type-2 Diabetes Mellitus Patients
- Multi-Modal Financial Time-Series Retrieval Through Latent Space Projections
- Pushing Large Language Models to the 6G Edge: Vision, Challenges, and Opportunities
- Learning to Transform for Generalizable Instance-wise Invariance
- Demystifying CLIP Data
- Decaf: Monocular Deformation Capture for Face and Hand Interactions
- Training a Large Video Model on a Single Machine in a Day
- RealFill: Reference-Driven Generation for Authentic Image Completion
- HyperPPO: A scalable method for finding small policies for robotic control
All 271
- Geodesic Regression Characterizes 3D Shape Changes in the Female Brain During Menstruation
- SA2-Net: Scale-aware Attention Network for Microscopic Image Segmentation
- Visual In-Context Learning for Few-Shot Eczema Segmentation
- Novel Deep Learning Pipeline for Automatic Weapon Detection
- DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation
- ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning
- FLIP: Cross-domain Face Anti-spoofing with Language Guidance
- Improving Equivariance in State-of-the-Art Supervised Depth and Normal Predictors
- Reusability report: Prostate cancer stratification with diverse biologically-informed neural architectures
- Deep Geometrized Cartoon Line Inbetweening
- MindShift: Leveraging Large Language Models for Mental-States-Based Problematic Smartphone Use Intervention
- End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenon
- SupReMix: Supervised Contrastive Learning for Medical Imaging Regression with Mixup
- On Learning with LAD
- Class Activation Map-based Weakly supervised Hemorrhage Segmentation using Resnet-LSTM in Non-Contrast Computed Tomography images
- Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit
- Revisiting Neural Program Smoothing for Fuzzing
- Qwen Technical Report
- KV Inversion: KV Embeddings Learning for Text-Conditioned Real Image Action Editing
- "AI enhances our performance, I have no doubt this one will do the same": The Placebo effect is robust to negative descriptions of AI
- Exploiting Edge Features in Graphs with Fused Network Gromov-Wasserstein Distance
- Deep Learning Based Uplink Multi-User SIMO Beamforming Design
- Unlikelihood Tuning on Negative Samples Amazingly Improves Zero-Shot Translation
- Cross-Prediction-Powered Inference
- Transfer Learning for Bayesian Optimization on Heterogeneous Search Spaces
- Can LLMs Effectively Leverage Graph Structural Information through Prompts, and Why?
- Navigating Healthcare Insights: A Birds Eye View of Explainability with Knowledge Graphs
- Tensor Factorization for Leveraging Cross-Modal Knowledge in Data-Constrained Infrared Object Detection
- Vision Transformers Need Registers
- Text-to-3D using Gaussian Splatting
- Collaborative Distributed Machine Learning
- GPT-Fathom: Benchmarking Large Language Models to Decipher the Evolutionary Path towards GPT-4 and Beyond
- Overcoming the Barrier of Orbital-Free Density Functional Theory for Molecular Systems Using Deep Learning
- A Benchmark for Learning to Translate a New Language from One Grammar Book
- Language Models as a Service: Overview of a New Paradigm and its Challenges
- Review of Machine Learning Methods for Additive Manufacturing of Functionally Graded Materials
- Audio-Visual Speaker Verification via Joint Cross-Attention
- Augment to Interpret: Unsupervised and Inherently Interpretable Graph Embeddings
- CRIMED: Lower and Upper Bounds on Regret for Bandits with Unbounded Stochastic Corruption
- Voting Network for Contour Levee Farmland Segmentation and Classification
- MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyond
- Correcting for heterogeneity in real-time epidemiological indicators
- Unsupervised Pretraining for Fact Verification by Language Model Distillation
- Uncertainty Quantification for Eosinophil Segmentation
- KLoB: a Benchmark for Assessing Knowledge Locating Methods in Language Models
- HOI4ABOT: Human-Object Interaction Anticipation for Human Intention Reading Collaborative roBOTs
- Generating Personalized Insulin Treatments Strategies with Deep Conditional Generative Time Series Models
- AtomSurf : Surface Representation for Learning on Protein Structures
- Latent Noise Segmentation: How Neural Noise Leads to the Emergence of Segmentation and Grouping
- From Complexity to Clarity: Analytical Expressions of Deep Neural Network Weights via Clifford's Geometric Algebra and Convexity
- Toloka Visual Question Answering Benchmark
- Deep Single Models vs. Ensembles: Insights for a Fast Deployment of Parking Monitoring Systems
- Accurate and lightweight dehazing via multi-receptive-field non-local network and novel contrastive regularization
- Asset Bundling for Wind Power Forecasting
- HTC-DC Net: Monocular Height Estimation from Single Remote Sensing Images
- Rethinking Domain Generalization: Discriminability and Generalizability
- High-dimensional robust regression under heavy-tailed data: Asymptotics and Universality
- Compositional Program Generation for Few-Shot Systematic Generalization
- A Metaheuristic for Amortized Search in High-Dimensional Parameter Spaces
- Diverse Target and Contribution Scheduling for Domain Generalization
- Augmenting LLMs with Knowledge: A survey on hallucination prevention
- SI-SD: Sleep Interpreter through awake-guided cross-subject Semantic Decoding
- Resisting Backdoor Attacks in Federated Learning via Bidirectional Elections and Individual Perspective
- On the Trade-offs between Adversarial Robustness and Actionable Explanations
- Towards Novel Class Discovery: A Study in Novel Skin Lesions Clustering
- A parsimonious, computationally efficient machine learning method for spatial regression
- Radar Instance Transformer: Reliable Moving Instance Segmentation in Sparse Radar Point Clouds
- Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation
- Nonlinear MPC design for incrementally ISS systems with application to GRU networks
- Prompt-and-Align: Prompt-Based Social Alignment for Few-Shot Fake News Detection
- Genetic Engineering Algorithm (GEA): An Efficient Metaheuristic Algorithm for Solving Combinatorial Optimization Problems
- Selective Nonparametric Regression via Testing
- Constructing Synthetic Treatment Groups without the Mean Exchangeability Assumption
- VAE-based latent-space classification of RNO-G data
- Physics-Preserving AI-Accelerated Simulations of Plasma Turbulence
- Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey
- A Comprehensive Survey of Document-level Relation Extraction (2016-2023)
- HIC-YOLOv5: Improved YOLOv5 For Small Object Detection
- 2-Cats: 2D Copula Approximating Transforms
- An Enhanced Low-Resolution Image Recognition Method for Traffic Environments
- Exposing Image Splicing Traces in Scientific Publications via Uncertainty-guided Refinement
- Multi-Swap k-Means++
- RLLTE: Long-Term Evolution Project of Reinforcement Learning
- Conditional normalizing flows for IceCube event reconstruction
- A Comprehensive Review on Tree Detection Methods Using Point Cloud and Aerial Imagery from Unmanned Aerial Vehicles
- MHG-GNN: Combination of Molecular Hypergraph Grammar with Graph Neural Network
- Bringing the Discussion of Minima Sharpness to the Audio Domain: a Filter-Normalised Evaluation for Acoustic Scene Classification
- FG-NeRF: Flow-GAN based Probabilistic Neural Radiance Field for Independence-Assumption-Free Uncertainty Estimation
- Leveraging Pre-trained Language Models for Time Interval Prediction in Text-Enhanced Temporal Knowledge Graphs
- Transformer-VQ: Linear-Time Transformers via Vector Quantization
- ShapeDBA: Generating Effective Time Series Prototypes using ShapeDTW Barycenter Averaging
- Dark Side Augmentation: Generating Diverse Night Examples for Metric Learning
- Intrinsic Language-Guided Exploration for Complex Long-Horizon Robotic Manipulation Tasks
- Epistemic Logic Programs: a study of some properties
- LagrangeBench: A Lagrangian Fluid Mechanics Benchmarking Suite
- Anti-Matthew FL: Bridging the Performance Gap in Federated Learning to Counteract the Matthew Effect
- Logarithm-transform aided Gaussian Sampling for Few-Shot Learning
- End-to-end Risk Prediction of Atrial Fibrillation from the 12-Lead ECG by Deep Neural Networks
- Augmenting Transformers with Recursively Composed Multi-grained Representations
- Astroconformer: The Prospects of Analyzing Stellar Light Curves with Transformer-Based Deep Learning Models
- A Primer on Bayesian Neural Networks: Review and Debates
- Weakly-Supervised Video Anomaly Detection with Snippet Anomalous Attention
- Can the Query-based Object Detector Be Designed with Fewer Stages?
- Gated Cross-Attention Network for Depth Completion
- Efficiency Separation between RL Methods: Model-Free, Model-Based and Goal-Conditioned
- LawBench: Benchmarking Legal Knowledge of Large Language Models
- Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learning
- Self-supervised Cross-view Representation Reconstruction for Change Captioning
- UPB @ ACTI: Detecting Conspiracies using fine tuned Sentence Transformers
- A framework for paired-sample hypothesis testing for high-dimensional data
- Social Media Fashion Knowledge Extraction as Captioning
- Hierarchical Network Data Analytics Framework for B5G Network Automation: Design and Implementation
- GAMMA: Generalizable Articulation Modeling and Manipulation for Articulated Objects
- Cooperation Dynamics in Multi-Agent Systems: Exploring Game-Theoretic Scenarios with Mean-Field Equilibria
- QonFusion -- Quantum Approaches to Gaussian Random Variables: Applications in Stable Diffusion and Brownian Motion
- Nondestructive chicken egg fertility detection using CNN-transfer learning algorithms
- On the Challenges of Fully Incremental Neural Dependency Parsing
- FORB: A Flat Object Retrieval Benchmark for Universal Image Embedding
- Spider4SPARQL: A Complex Benchmark for Evaluating Knowledge Graph Question Answering Systems
- Object Motion Guided Human Motion Synthesis
- Language models in molecular discovery
- Analyzing Political Figures in Real-Time: Leveraging YouTube Metadata for Sentiment Analysis
- Controllable Text Generation with Residual Memory Transformer
- Brand Network Booster: A new system for improving brand connectivity
- GInX-Eval: Towards In-Distribution Evaluation of Graph Neural Network Explanations
- Off-the-shelf bin picking workcell with visual pose estimation: A case study on the world robot summit 2018 kitting task
- Unmasking the Chameleons: A Benchmark for Out-of-Distribution Detection in Medical Tabular Data
- GAFlow: Incorporating Gaussian Attention into Optical Flow
- Abdominal multi-organ segmentation in CT using Swinunter
- Low-rank tensor completion via tensor joint rank with logarithmic composite norm
- Parameter-Saving Adversarial Training: Reinforcing Multi-Perturbation Robustness via Hypernetworks
- Alzheimer's Disease Prediction via Brain Structural-Functional Deep Fusing Network
- Marathi-English Code-mixed Text Generation
- Max-Sliced Mutual Information
- Cloth2Body: Generating 3D Human Body Mesh from 2D Clothing
- A More General Theory of Diagnosis from First Principles
- BEVHeight++: Toward Robust Visual Centric 3D Object Detection
- Navigating the Noise: Bringing Clarity to ML Parameterization Design with O(100) Ensembles
- Using Weak Supervision and Data Augmentation in Question Answering
- Large Language Model Soft Ideologization via AI-Self-Consciousness
- CoinRun: Solving Goal Misgeneralisation
- Learning to Terminate in Object Navigation
- Leveraging Untrustworthy Commands for Multi-Robot Coordination in Unpredictable Environments: A Bandit Submodular Maximization Approach
- AE-GPT: Using Large Language Models to Extract Adverse Events from Surveillance Reports-A Use Case with Influenza Vaccine Adverse Events
- OSM-Net: One-to-Many One-shot Talking Head Generation with Spontaneous Head Motions
- T-COL: Generating Counterfactual Explanations for General User Preferences on Variable Machine Learning Systems
- The Confidence-Competence Gap in Large Language Models: A Cognitive Study
- Generative Semi-supervised Learning with Meta-Optimized Synthetic Samples
- Align before Search: Aligning Ads Image to Text for Accurate Cross-Modal Sponsored Search
- CLIP-Hand3D: Exploiting 3D Hand Pose Estimation via Context-Aware Prompting
- Two-Step Active Learning for Instance Segmentation with Uncertainty and Diversity Sampling
- Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval
- A dual-branch model with inter- and intra-branch contrastive loss for long-tailed recognition
- Mask4Former: Mask Transformer for 4D Panoptic Segmentation
- A Spectral Approach for Learning Spatiotemporal Neural Differential Equations
- Joint Correcting and Refinement for Balanced Low-Light Image Enhancement
- Open Compound Domain Adaptation with Object Style Compensation for Semantic Segmentation
- UVL2: A Unified Framework for Video Tampering Localization
- ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers
- D3Fields: Dynamic 3D Descriptor Fields for Zero-Shot Generalizable Rearrangement
- Low-redundancy Distillation for Continual Learning
- Comparing Active Learning Performance Driven by Gaussian Processes or Bayesian Neural Networks for Constrained Trajectory Exploration
- Learning Effective NeRFs and SDFs Representations with 3D Generative Adversarial Networks for 3D Object Generation
- Feature Normalization Prevents Collapse of Non-contrastive Learning Dynamics
- Channel Vision Transformers: An Image Is Worth 1 x 16 x 16 Words
- Differentially Private Secure Multiplication: Hiding Information in the Rubble of Noise
- Discovering Utility-driven Interval Rules
- Nonparametric estimation of a covariate-adjusted counterfactual treatment regimen response curve
- Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial Robustness
- Forgetting Private Textual Sequences in Language Models via Leave-One-Out Ensemble
- Task-Oriented Koopman-Based Control with Contrastive Encoder