Papers
Fri 28 Jul 2023
168 papers
- AbDiffuser: Full-Atom Generation of in vitro Functioning AntibodiesDiffusion models → Flow matching, time series and science
- An Overview Of Temporal Commonsense Reasoning and AcquisitionLLM reasoning → Knowledge- and tool-augmented reasoning
- Dialogue Shaping: Empowering Agents through NPC InteractionLLM agents and tool use → Reinforcement learning for LLM agents
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic ControlMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
- Understanding the Benefits and Challenges of Using Large Language Model-based Conversational Agents for Mental Well-being SupportLLM agents and tool use → Medical and scientific domain agents
- Primitive Skill-based Robot Learning from Human Evaluative FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Benchmarking Offline Reinforcement Learning on Real-Robot HardwareOffline RL and imitation learning from data → Real-world robot offline RL
- CLIP Brings Better Features to Visual Aesthetics LearnersKnowledge distillation → Multimodal distillation
- Robust Distortion-free Watermarks for Language ModelsLLM safety and security → Watermarking generated content and models
- A Dataflow Compiler for Efficient LLM Inference using Custom Microscaling FormatsEfficient LLM inference and serving → KV cache quantization
- Minimally-Supervised Speech Synthesis with Conditional Diffusion Model and Language Model: A Comparative Study of Semantic CodingDiffusion models → Audio, speech and music
- Cross-Modal Concept Learning and Inference for Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Skeleton-of-Thought: Prompting LLMs for Efficient Parallel GenerationLLM reasoning → Test-time compute and efficient thinking
- TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-ExpertsMixture-of-experts → Mixture of LoRA experts
- Does Unpredictability Influence Driving Behavior?End-to-end autonomous driving → Imitation-learning end-to-end planners
- RSGPT: A Remote Sensing Vision Language Model and BenchmarkMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
- Empirical Study of Straggler Problem in Parameter Server on Iterative Convergent Distributed Machine Learning
- Beyond Reality: The Pivotal Role of Generative AI in the Metaverse
- Goodness-of-Fit of Attributed Probabilistic Graph Generative Models
- RFID-Assisted Indoor Localization Using Hybrid Wireless Data Fusion
- Evaluating the structure of cognitive tasks with transfer learning
- SAP-sLDA: An Interpretable Interface for Exploring Unstructured Text
- DeepTSF: Codeless machine learning operations for time series forecasting
- VeriGen: A Large Language Model for Verilog Code Generation
- Task-Oriented Channel Attention for Fine-Grained Few-Shot Classification
- An unsupervised machine-learning-based shock sensor for high-order supersonic flow solvers
- Reasoning before Responding: Integrating Commonsense-based Causality Explanation for Empathetic Response Generation
- Rethinking Noisy Label Learning in Real-world Annotation Scenarios from the Noise-type Perspective
- Benchmarking Jetson Edge Devices with an End-to-end Video-based Anomaly Detection System
- Testing the Depth of ChatGPT's Comprehension via Cross-Modal Tasks Based on ASCII-Art: GPT3.5's Abilities in Regard to Recognizing and Generating ASCII-Art Are Not Totally Lacking
- VPP: Efficient Conditional 3D Generation via Voxel-Point Progressive Representation
- Quantum Kernel Estimation With Neutral Atoms For Supervised Classification: A Gate-Based Approach
- Holistic Survey of Privacy and Fairness in Machine Learning
- Mean Estimation with User-level Privacy under Data Heterogeneity
- Non-parametric Hypothesis Tests for Distributional Group Symmetry
- A Distance Correlation-Based Approach to Characterize the Effectiveness of Recurrent Neural Networks for Time Series Forecasting
- Seeing Behind Dynamic Occlusions with Event Cameras
- Multi-growth stage plant recognition: a case study of Palmer amaranth (Amaranthus palmeri) in cotton (Gossypium hirsutum)
- Anomaly Detection in Industrial Machinery using IoT Devices and Machine Learning: a Systematic Mapping
- On Single Index Models beyond Gaussian Data
- Summaries, Highlights, and Action items: Design, implementation and evaluation of an LLM-powered meeting recap system
- SAFE: Saliency-Aware Counterfactual Explanations for DNN-based Automated Driving Systems
- Spherical and Hyperbolic Toric Topology-Based Codes On Graph Embedding for Ising MRF Models: Classical and Quantum Topology Machine Learning
- Select and Augment: Enhanced Dense Retrieval Knowledge Graph Augmentation
- Seeking the Yield Barrier: High-Dimensional SRAM Evaluation Through Optimal Manifold
- Weighted variation spaces and approximation by shallow ReLU networks
- The Hydra Effect: Emergent Self-repair in Language Model Computations
- CHATREPORT: Democratizing Sustainability Disclosure Analysis through LLM-based Tools
- Lessons in Reproducibility: Insights from NLP Studies in Materials Science
- Resume Evaluation through Latent Dirichlet Allocation and Natural Language Processing for Effective Candidate Selection
- Context-VQA: Towards Context-Aware and Purposeful Visual Question Answering
- How regularization affects the geometry of loss functions
- AI for Anticipatory Action: Moving Beyond Climate Forecasting
- Curiosity-Driven Reinforcement Learning based Low-Level Flight Control
- Agent-Based Model: Simulating a Virus Expansion Based on the Acceptance of Containment Measures
- Quantum-limited stochastic optical neural networks operating at a few quanta per activation
- Generalized Open-World Semi-Supervised Object Detection
- Uncertainty in Natural Language Generation: From Theory to Applications
- MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking
- Aligned Unsupervised Pretraining of Object Detectors with Self-training
- Universal Recurrent Event Memories for Streaming Data
- PatchMixer: Rethinking network design to boost generalization for 3D point cloud understanding
- ODTlearn: A Package for Learning Optimal Decision Trees for Prediction and Prescription
- A supervised hybrid quantum machine learning solution to the emergency escape routing problem
- Dynamic Analysis and an Eigen Initializer for Recurrent Neural Networks
- Case Studies of Causal Discovery from IT Monitoring Time Series
- Adversarial training for tabular data with attack propagation
- Bayesian Time-Series Classifier for Decoding Simple Visual Stimuli from Intracranial Neural Activity
- TrackAgent: 6D Object Tracking via Reinforcement Learning
- CoRe Optimizer: An All-in-One Solution for Machine Learning
- Multi-layer Aggregation as a key to feature-based OOD detection
- Scale-aware Test-time Click Adaptation for Pulmonary Nodule and Mass Segmentation
- Scaling Data Generation in Vision-and-Language Navigation
- TriadNet: Sampling-free predictive intervals for lesional volume in 3D brain MR images
- A Comparative Analysis of Machine Learning Methods for Lane Change Intention Recognition Using Vehicle Trajectory Data
- Shrink-Perturb Improves Architecture Mixing during Population Based Training for Neural Architecture Search
- A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and beyond
- Integrated Digital Reconstruction of Welded Components: Supporting Improved Fatigue Life Prediction
- OAFuser: Towards Omni-Aperture Fusion for Light Field Semantic Segmentation
- When to generate hedges in peer-tutoring interactions
- Point Clouds Are Specialized Images: A Knowledge Transfer Approach for 3D Understanding
- We are all Individuals: The Role of Robot Personality and Human Traits in Trustworthy Interaction
- Panoptic Scene Graph Generation with Semantics-Prototype Learning
- Dynamic algorithms for k-center on graphs
- All-for-One and One-For-All: Deep learning-based feature fusion for Synthetic Speech Detection
- 'What are you referring to?' Evaluating the Ability of Multi-Modal Dialogue Models to Process Clarificational Exchanges
- On the Trade-off Between Efficiency and Precision of Neural Abstraction
- Oracle Computability and Turing Reducibility in the Calculus of Inductive Constructions
- Beating Backdoor Attack at Its Own Game
- Few-shot Image Classification based on Gradual Machine Learning
- YOLOv8 for Defect Inspection of Hexagonal Directed Self-Assembly Patterns: A Data-Centric Approach
- Revisiting Fully Convolutional Geometric Features for Object 6D Pose Estimation
- The Road to Quality is Paved with Good Revisions: A Detailed Evaluation Methodology for Revision Policies in Incremental Sequence Labelling
- Improving image quality of sparse-view lung tumor CT images with U-Net
- Exploring Format Consistency for Instruction Tuning
- The Applicability of Federated Learning to Official Statistics
- From continuous-time formulations to discretization schemes: tensor trains and robust regression for BSDEs and parabolic PDEs
- ETHER: Aligning Emergent Communication for Hindsight Experience Replay
- The timing bottleneck: Why timing and overlap are mission-critical for conversational user interfaces, speech recognition and dialogue systems
- A Semantic Approach to Decidability in Epistemic Planning (Extended Version)
All 168
- Non-invasive Diabetes Detection using Gabor Filter: A Comparative Analysis of Different Cameras
- Local and Global Information in Obstacle Detection on Railway Tracks
- FeedbackLogs: Recording and Incorporating Stakeholder Feedback into Machine Learning Pipelines
- LUCID-GAN: Conditional Generative Models to Locate Unfairness
- Defocus Blur Synthesis and Deblurring via Interpolation and Extrapolation in Latent Space
- Worrisome Properties of Neural Network Controllers and Their Symbolic Representations
- Trie-NLG: Trie Context Augmentation to Improve Personalized Query Auto-Completion for Short and Unseen Prefixes
- From Probabilistic Programming to Complexity-based Programming
- DELPHIC: Practical DEL Planning via Possibilities (Extended Version)
- ERCPMP: An Endoscopic Image and Video Dataset for Colorectal Polyps Morphology and Pathology
- Optimal Alignment of Temporal Knowledge Bases
- Autonomous Payload Thermal Control
- Automated Visual Monitoring of Nocturnal Insects with Light-based Camera Traps
- CFN-ESA: A Cross-Modal Fusion Network with Emotion-Shift Awareness for Dialogue Emotion Recognition
- Improvable Gap Balancing for Multi-Task Learning
- Implicit neural representation for change detection
- Deep Learning Pipeline for Automated Visual Moth Monitoring: Insect Localization and Species Classification
- A Critical Review of Large Language Models: Sensitivity, Bias, and the Path Toward Specialized AI
- Deep Generative Models, Synthetic Tabular Data, and Differential Privacy: An Overview and Synthesis
- Is One Epoch All You Need For Multi-Fidelity Hyperparameter Optimization?
- MLIC++: Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compression
- Improving Social Media Popularity Prediction with Multiple Post Dependencies
- Investigating the Learning Behaviour of In-context Learning: A Comparison with Supervised Learning
- Towards a Fully Unsupervised Framework for Intent Induction in Customer Support Dialogues
- Uncertainty-aware Unsupervised Multi-Object Tracking
- Stochastic automatic differentiation for Monte Carlo processes
- The Initial Screening Order Problem
- Noisy Interpolation Learning with Shallow Univariate ReLU Networks
- An Empirical Study of Large-Scale Data-Driven Full Waveform Inversion
- AffineGlue: Joint Matching and Robust Estimation
- Co-attention Graph Pooling for Efficient Pairwise Graph Interaction Learning
- Multilingual Tourist Assistance using ChatGPT: Comparing Capabilities in Hindi, Telugu, and Kannada
- Conflict-free joint decision by lag and zero-lag synchronization in laser network
- Toward Transparent Sequence Models with Model-Based Tree Markov Model
- Prompt Guided Transformer for Multi-Task Dense Prediction
- Confident Feature Ranking
- Supervised Homography Learning with Realistic Dataset Generation
- Med-HALT: Medical Domain Hallucination Test for Large Language Models
- Teach Me How to Improve My Argumentation Skills: A Survey on Feedback in Argumentation
- The Radon Signed Cumulative Distribution Transform and its applications in classification of Signed Images
- BARTPhoBEiT: Pre-trained Sequence-to-Sequence and Image Transformers Models for Vietnamese Visual Question Answering
- Dynamic PlenOctree for Adaptive Sampling Refinement in Explicit NeRF
- Tutorials on Stance Detection using Pre-trained Language Models: Fine-tuning BERT and Prompting Large Language Models
- Staging E-Commerce Products for Online Advertising using Retrieval Assisted Image Generation
- Equivariance and partial observations in Koopman operator theory for partial differential equations
- Robust Visual Sim-to-Real Transfer for Robotic Manipulation
- DocDeshadower: Frequency-Aware Transformer for Document Shadow Removal
- DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation
- Efficient Multiuser AI Downloading via Reusable Knowledge Broadcasting
- TrafficSafetyGPT: Tuning a Pre-trained Large Language Model to a Domain-Specific Expert in Transportation Safety
- Attentive Multimodal Fusion for Optical and Scene Flow
- Differential Evolution Algorithm based Hyper-Parameters Selection of Transformer Neural Network Model for Load Forecasting
- WC-SBERT: Zero-Shot Text Classification via SBERT with Self-Training for Wikipedia Categories
- ChatHome: Development and Evaluation of a Domain-Specific Language Model for Home Renovation
- Learning Nonlinear Projections for Reduced-Order Modeling of Dynamical Systems using Constrained Autoencoders
- Multilingual Lexical Simplification via Paraphrase Generation
- Optimal Approximation of Zonoids and Uniform Approximation by Shallow Neural Networks
- AC-Norm: Effective Tuning for Medical Image Analysis via Affine Collaborative Normalization
- Recovering high-quality FODs from a reduced number of diffusion-weighted images using a model-driven deep learning architecture
- Anatomy-Aware Lymph Node Detection in Chest CT using Implicit Station Stratification
- Learning with Constraint Learning: New Perspective, Solution Strategy and Various Applications
- Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classification
- A Solution to Co-occurrence Bias: Attributes Disentanglement via Mutual Information Minimization for Pedestrian Attribute Recognition
- D2S: Representing sparse descriptors and 3D coordinates for camera relocalization
- Is this model reliable for everyone? Testing for strong calibration
- A Practical Recipe for Federated Learning Under Statistical Heterogeneity Experimental Design
- BOURNE: Bootstrapped Self-supervised Learning Framework for Unified Graph Anomaly Detection
- TROPHY: A Topologically Robust Physics-Informed Tracking Framework for Tropical Cyclones