Papers
Thu 21 Sep 2023
238 papers
- LPML: LLM-Prompting Markup Language for Mathematical ReasoningLLM reasoning → Mathematical reasoning
- Trip Planning for Autonomous Vehicles with Wireless Data Transfer Needs Using Reinforcement LearningEnd-to-end autonomous driving → Cooperative and V2X driving
- RCMS: Risk-Aware Crash Mitigation System for Autonomous VehiclesEnd-to-end autonomous driving → Reinforcement learning for driving
- A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language GuidanceMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- A Diffusion-Model of Joint Interactive NavigationDiffusion models → Diffusion and flow policies for robotics
- License Plate Super-Resolution Using Diffusion ModelsDiffusion models → Inverse problems and image restoration
- Studying and improving reasoning in humans and machinesLLM reasoning → Reasoning benchmarks and evaluation
- LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an AgentLLM agents and tool use → Multimodal and embodied agents
- Real-Time Capable Decision Making for Autonomous Driving Using Reachable SetsEnd-to-end autonomous driving → Imitation-learning end-to-end planners
- MetaMath: Bootstrap Your Own Mathematical Questions for Large Language ModelsSynthetic data and self-improvement for LLMs → Synthetic reasoning data and bootstrapping
- AceGPT, Localizing Large Language Models in ArabicLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
- World Modeling for Autonomous Wheel LoadersWorld models → Embodied and robot world models
- Rethinking the Evaluating Framework for Natural Language Understanding in AI Systems: Language Acquisition as a Core for Future MetricsLLM reasoning → Reasoning benchmarks and evaluation
- InstructERC: Reforming Emotion Recognition in Conversation with Multi-task Retrieval-Augmented Large Language ModelsRetrieval-augmented generation → Conversational and speech RAG
- Goal-Oriented Prompt Attack and Safety Evaluation for LLMsLLM safety and security → Prompt injection and agent security
- How Robust is Google's Bard to Adversarial Image Attacks?Multimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
- Deshadow-Anything: When Segment Anything Model Meets Zero-shot shadow removalDiffusion models → 3D, point cloud and scene generation
- Class Relevance Learning For Out-of-distribution Detection
- Learning Noise-Robust Joint Representation for Multimodal Emotion Recognition under Incomplete Data Scenarios
- Personalization of Affective Models to Enable Neuropsychiatric Digital Precision Health Interventions: A Feasibility Study
- Deep Neuromorphic Networks with Superconducting Single Flux Quanta
- Extracting Physical Causality from Measurements to Detect and Localize False Data Injection Attacks
- Health diagnosis and recuperation of aged Li-ion batteries with data analytics and equivalent circuit modeling
- SCVCNet: Sliding cross-vector convolution network for cross-task and inter-individual-set EEG-based cognitive workload recognition
- Phase Synchrony Component Self-Organization in Brain Computer Interface
- A Knowledge-Driven Cross-view Contrastive Learning for EEG Representation
- How Prevalent is Gender Bias in ChatGPT? -- Exploring German and English ChatGPT Responses
- From Peptides to Nanostructures: A Euclidean Transformer for Fast and Stable Machine Learned Force Fields
- Limited Communications Distributed Optimization via Deep Unfolded Distributed ADMM
- Towards Lexical Analysis of Dog Vocalizations via Online Videos
- Does My Dog ''Speak'' Like Me? The Acoustic Correlation between Pet Dogs and Their Human Owners
- SPICED: News Similarity Detection Dataset with Multiple Topics and Complexity Levels
- MiChao-HuaFen 1.0: A Specialized Pre-trained Corpus Dataset for Domain-specific Large Models
- A Differentiable Framework for End-to-End Learning of Hybrid Structured Compression
- Curriculum Reinforcement Learning via Morphology-Environment Co-Evolution
- Confidence Calibration for Systems with Cascaded Predictive Modules
- Knowledge Graph Embedding: An Overview
- User-Level Differential Privacy With Few Examples Per User
- Evidential uncertainty sampling for active learning
- Exploring the Impact of Training Data Distribution and Subword Tokenization on Gender Bias in Machine Translation
- Sharpness-Aware Minimization and the Edge of Stability
- Robust Energy Consumption Prediction with a Missing Value-Resilient Metaheuristic-based Neural Network in Mobile App Development
- State2Explanation: Concept-Based Explanations to Benefit Agent Learning and User Understanding
- HANS, are you clever? Clever Hans Effect Analysis of Neural Systems
- SAVME: Efficient Safety Validation for Autonomous Systems Using Meta-Learning
- Impact of architecture on robustness and interpretability of multispectral deep neural networks
- Multimodal Deep Learning for Scientific Imaging Interpretation
- A Theory of Multimodal Learning
- LongDocFACTScore: Evaluating the Factuality of Long Document Abstractive Summarisation
- A Convex Framework for Confounding Robust Inference
- Ensemble Neural Networks for Remaining Useful Life (RUL) Prediction
- Foundation Metrics for Evaluating Effectiveness of Healthcare Conversations Powered by Generative AI
- Active Learning for Multilingual Fingerspelling Corpora
- DIOR: Dataset for Indoor-Outdoor Reidentification -- Long Range 3D/2D Skeleton Gait Collection Pipeline, Semi-Automated Gait Keypoint Labeling and Baseline Evaluation Methods
- Synthetic Image Detection: Highlights from the IEEE Video and Image Processing Cup 2022 Student Competition
- Can LLMs Augment Low-Resource Reading Comprehension Datasets? Opportunities and Challenges
- DualToken-ViT: Position-aware Efficient Vision Transformer with Dual Token Fusion
- Event Prediction using Case-Based Reasoning over Knowledge Graphs
- Change Management using Generative Modeling on Digital Twins
- Constraints First: A New MDD-based Model to Generate Sentences Under Constraints
- Speeding up Resnet Architecture with Layers Targeted Low Rank Decomposition
- POLAR-Sim: Augmenting NASA's POLAR Dataset for Data-Driven Lunar Perception and Rover Simulation
- SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap
- Memory Efficient Mixed-Precision Optimizers
- Methods for generating and evaluating synthetic longitudinal patient data: a systematic review
- Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling
- Shedding Light on the Ageing of Extra Virgin Olive Oil: Probing the Impact of Temperature with Fluorescence Spectroscopy and Machine Learning Techniques
- Active Stereo Without Pattern Projector
- TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance
- ForceSight: Text-Guided Mobile Manipulation with Visual-Force Goals
- Rehearsal: Simulating Conflict to Teach Conflict Resolution
- LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
- TalkNCE: Improving Active Speaker Detection with Talk-Aware Contrastive Learning
- SlowFast Network for Continuous Sign Language Recognition
- PanoVOS: Bridging Non-panoramic and Panoramic Views with Transformer for Video Segmentation
- Text-Guided Vector Graphics Customization
- Environment-biased Feature Ranking for Novelty Detection Robustness
- See to Touch: Learning Tactile Dexterity through Visual Incentives
- Learning to Drive Anywhere
- Reranking for Natural Language Generation from Logical Forms: A Study based on Large Language Models
- The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"
- Performance Conditioning for Diffusion-Based Multi-Instrument Music Synthesis
- The Broad Impact of Feature Imitation: Neural Enhancements Across Financial, Speech, and Physiological Domains
- Inspire the Large Language Model by External Knowledge on BioMedical Named Entity Recognition
- LLMR: Real-time Prompting of Interactive Worlds using Large Language Models
- Improving VTE Identification through Adaptive NLP Model Selection and Clinical Expert Rule-based Classifier from Radiology Reports
- The Cambridge Law Corpus: A Dataset for Legal AI Research
- Enabling Quartile-based Estimated-Mean Gradient Aggregation As Baseline for Federated Image Classifications
- On the Relationship between Skill Neurons and Robustness in Prompt Tuning
- Soft Merging: A Flexible and Robust Soft Model Merging Approach for Enhanced Neural Network Performance
- SALSA-CLRS: A Sparse and Scalable Benchmark for Algorithmic Reasoning
- Parallelizing non-linear sequential models over the sequence length
- SQUARE: Automatic Question Answering Evaluation using Multiple Positive and Negative References
- Bad Actor, Good Advisor: Exploring the Role of Large Language Models in Fake News Detection
- Adaptive Input-image Normalization for Solving the Mode Collapse Problem in GAN-based X-ray Images
- ChaCha: Leveraging Large Language Models to Prompt Children to Share Their Emotions about Personal Events
- Weakly-supervised Automated Audio Captioning via text only training
- Clustering risk in Non-parametric Hidden Markov and I.I.D. Models
- t-EER: Parameter-Free Tandem Evaluation of Countermeasures and Biometric Comparators
- Smooth ECE: Principled Reliability Diagrams via Kernel Smoothing
All 238
- Bridging the Gaps of Both Modality and Language: Synchronous Bilingual CTC for Speech Translation and Speech Recognition
- Smooth Nash Equilibria: Algorithms and Complexity
- Towards Answering Health-related Questions from Medical Videos: Datasets and Approaches
- Regionally Additive Models: Explainable-by-design models minimizing feature interactions
- Can We Reliably Improve the Robustness to Image Acquisition of Remote Sensing of PV Systems?
- SupeRBNN: Randomized Binary Neural Network Using Adiabatic Superconductor Josephson Devices
- Physics-informed State-space Neural Networks for Transport Phenomena
- Boolformer: Symbolic Regression of Logic Functions with Transformers
- Brain Tumor Detection Using Deep Learning Approaches
- SG-Bot: Object Rearrangement via Coarse-to-Fine Robotic Imagination on Scene Graphs
- ORTexME: Occlusion-Robust Human Shape and Pose via Temporal Average Texture and Mesh Encoding
- Autoregressive Sign Language Production: A Gloss-Free Approach with Discrete Representations
- Explainable Artificial Intelligence for Drug Discovery and Development -- A Comprehensive Survey
- SANPO: A Scene Understanding, Accessibility and Human Navigation Dataset
- Optimal Conditional Inference in Adaptive Experiments
- Code Soliloquies for Accurate Calculations in Large Language Models
- Information Forensics and Security: A quarter-century-long journey
- Towards Robust and Truly Large-Scale Audio-Sheet Music Retrieval
- Unsupervised Domain Adaptation for Self-Driving from Past Traversal Features
- On the relationship between Benchmarking, Standards and Certification in Robotics and AI
- OSN-MDAD: Machine Translation Dataset for Arabic Multi-Dialectal Conversations on Online Social Media
- Self-Supervised Contrastive Learning for Robust Audio-Sheet Music Retrieval Systems
- Automating construction contract review using knowledge graph-enhanced large language models
- Convergence and Recovery Guarantees of Unsupervised Neural Networks for Inverse Problems
- Vulnerability of 3D Face Recognition Systems to Morphing Attacks
- How-to Guides for Specific Audiences: A Corpus and Initial Findings
- AutoPET Challenge 2023: Sliding Window-based Optimization of U-Net
- Incentivizing Massive Unknown Workers for Budget-Limited Crowdsensing: From Off-Line and On-Line Perspectives
- Passage Summarization with Recurrent Models for Audio-Sheet Music Retrieval
- Exploiting CLIP-based Multi-modal Approach for Artwork Classification and Retrieval
- PEFTT: Parameter-Efficient Fine-Tuning for low-resource Tibetan pre-trained language models
- A Computational Analysis of Vagueness in Revisions of Instructional Texts
- FourierLoss: Shape-Aware Loss Function with Fourier Descriptors
- SemEval-2022 Task 7: Identifying Plausible Clarifications of Implicit and Underspecified Phrases in Instructional Texts
- Bayesian sparsification for deep neural networks with Bayesian model reduction
- Multi-Task Cooperative Learning via Searching for Flat Minima
- Clustering-based Domain-Incremental Learning
- Prompt Tuned Embedding Classification for Multi-Label Industry Sector Allocation
- Benchmarking quantized LLaMa-based models on the Brazilian Secondary School Exam
- Survey of Action Recognition, Spotting and Spatio-Temporal Localization in Soccer -- Current Trends and Research Perspectives
- An Efficient Consolidation of Word Embedding and Deep Learning Techniques for Classifying Anticancer Peptides: FastText+BiLSTM
- BELT:Bootstrapping Electroencephalography-to-Language Decoding and Zero-Shot Sentiment Classification by Natural Language Supervision
- Self-Calibrating, Fully Differentiable NLOS Inverse Rendering
- Beyond Image Borders: Learning Feature Extrapolation for Unbounded Image Composition
- S-BDT: Distributed Differentially Private Boosted Decision Trees
- Uncertainty-driven Exploration Strategies for Online Grasp Learning
- Uplift vs. predictive modeling: a theoretical analysis
- BASE: Probably a Better Approach to Multi-Object Tracking
- Face Identity-Aware Disentanglement in StyleGAN
- Expert-Aided Causal Discovery of Ancestral Graphs
- Striking Gold in Advertising: Standardization and Exploration of Ad Text Generation
- Exploring Self-supervised Skeleton-based Action Recognition in Occluded Environments
- Dynamic Hypergraph Structure Learning for Traffic Flow Forecasting
- Precision in Building Extraction: Comparing Shallow and Deep Models using LiDAR Data
- Robust Approximation Algorithms for Non-monotone k-Submodular Maximization under a Knapsack Constraint
- Demystifying Visual Features of Movie Posters for Multi-Label Genre Identification
- Convolution and Attention Mixer for Synthetic Aperture Radar Image Change Detection
- Elevating Skeleton-Based Action Recognition with Efficient Multi-Modality Self-Supervision
- Safe Hierarchical Reinforcement Learning for CubeSat Task Scheduling Based on Energy Consumption
- LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset
- Identification of pneumonia on chest x-ray images through machine learning
- Enhancing SAEAs with Unevaluated Solutions: A Case Study of Relation Model for Expensive Optimization
- Neural Stochastic Screened Poisson Reconstruction
- A Vision-Based Navigation System for Arable Fields
- Predictability and Comprehensibility in Post-Hoc XAI Methods: A User-Centered Analysis
- ZS6D: Zero-shot 6D Object Pose Estimation using Vision Transformers
- State Representations as Incentives for Reinforcement Learning Agents: A Sim2Real Analysis on Robotic Grasping
- Variational Connectionist Temporal Classification for Order-Preserving Sequence Modeling
- Stock Market Sentiment Classification and Backtesting via Fine-tuned BERT
- Inferring Capabilities from Task Performance with Bayesian Triangulation
- NeuralLabeling: A versatile toolset for labeling vision datasets using Neural Radiance Fields
- Generating Hierarchical Structures for Improved Time Series Classification Using Stochastic Splitting Functions
- Ego3DPose: Capturing 3D Cues from Binocular Egocentric Views
- A Comprehensive Review on Financial Explainable AI
- A Study of Forward-Forward Algorithm for Self-Supervised Learning
- On the Probability of Immunity
- On the Definition of Appropriate Trust and the Tools that Come with it
- Fully Transformer-Equipped Architecture for End-to-End Referring Video Object Segmentation
- A Machine Learning-oriented Survey on Tiny Machine Learning
- Bridging the Gap: Learning Pace Synchronization for Open-World Semi-Supervised Learning
- Video Scene Location Recognition with Neural Networks
- Scaling up COMETKIWI: Unbabel-IST 2023 Submission for the Quality Estimation Shared Task
- TextCLIP: Text-Guided Face Image Generation And Manipulation Without Adversarial Training
- Spatial-Temporal Transformer based Video Compression Framework
- Learning to Recover for Safe Reinforcement Learning
- Unlocking the Heart Using Adaptive Locked Agnostic Networks
- Focal Inferential Infusion Coupled with Tractable Density Discrimination for Implicit Hate Detection
- Audio Contrastive-based Fine-tuning: Decoupling Representation Learning and Classification
- Heart Rate Detection Using an Event Camera
- High-order Joint Constituency and Dependency Parsing
- On-the-Fly SfM: What you capture is What you get
- Using Saliency and Cropping to Improve Video Memorability
- Multi-level Asymmetric Contrastive Learning for Volumetric Medical Image Segmentation Pre-training
- Stochastic stiffness identification and response estimation of Timoshenko beams via physics-informed Gaussian processes
- Syntactic Variation Across the Grammar: Modelling a Complex Adaptive System
- OSNet & MNetO: Two Types of General Reconstruction Architectures for Linear Computed Tomography in Multi-Scenarios
- TCOVIS: Temporally Consistent Online Video Instance Segmentation
- Activation Compression of Graph Neural Networks using Block-wise Quantization with Improved Variance Minimization
- BitCoin: Bidirectional Tagging and Supervised Contrastive Learning based Joint Relational Triple Extraction Framework
- Knowledge Sanitization of Large Language Models
- DEYOv3: DETR with YOLO for Real-time Object Detection
- A Discourse-level Multi-scale Prosodic Model for Fine-grained Emotion Analysis
- MEFLUT: Unsupervised 1D Lookup Tables for Multi-exposure Image Fusion
- TMac: Temporal Multi-Modal Graph Learning for Acoustic Event Classification
- MoPA: Multi-Modal Prior Aided Domain Adaptation for 3D Semantic Segmentation
- Evaluating Large Language Models for Document-grounded Response Generation in Information-Seeking Dialogues
- Word Embedding with Neural Probabilistic Prior
- Automatic Endoscopic Ultrasound Station Recognition with Limited Data
- Multimodal Transformers for Wireless Communications: A Case Study in Beam Prediction
- JobRecoGPT -- Explainable job recommendations using LLMs
- FGFusion: Fine-Grained Lidar-Camera Fusion for 3D Object Detection
- A Comprehensive Review of Community Detection in Graphs
- SLHCat: Mapping Wikipedia Categories and Lists to DBpedia by Leveraging Semantic, Lexical, and Hierarchical Features
- DimCL: Dimensional Contrastive Learning For Improving Self-Supervised Learning
- A Real-Time Multi-Task Learning System for Joint Detection of Face, Facial Landmark and Head Pose
- Fast Satellite Tensorial Radiance Field for Multi-date Satellite Imagery of Large Size
- Dictionary Attack on IMU-based Gait Authentication
- Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
- SAM-OCTA: A Fine-Tuning Strategy for Applying Foundation Model to OCTA Image Segmentation Tasks
- 2DDATA: 2D Detection Annotations Transmittable Aggregation for Semantic Segmentation on Point Cloud
- A Vision-Centric Approach for Static Map Element Annotation
- Improve the efficiency of deep reinforcement learning through semantic exploration guided by natural language
- PIE: Simulating Disease Progression via Progressive Image Editing
- Unveiling Optimal SDG Pathways: An Innovative Approach Leveraging Graph Pruning and Intent Graph for Effective Recommendations
- Choice-75: A Dataset on Decision Branching in Script Learning
- Turaco: Complexity-Guided Data Sampling for Training Neural Surrogates of Programs
- FluentEditor: Text-based Speech Editing by Considering Acoustic and Prosody Consistency
- Emotion-Aware Prosodic Phrasing for Expressive Text-to-Speech
- Efficient Core-selecting Incentive Mechanism for Data Sharing in Federated Learning
- CPR-Coach: Recognizing Composite Error Actions based on Single-class Training
- A Dynamic Domain Adaptation Deep Learning Network for EEG-based Motor Imagery Classification
- Quasi-Monte Carlo for 3D Sliced Wasserstein
- MoDA: Leveraging Motion Priors from Videos for Advancing Unsupervised Domain Adaptation in Semantic Segmentation
- ContextRef: Evaluating Referenceless Metrics For Image Description Generation
- Efficient Long-Short Temporal Attention Network for Unsupervised Video Object Segmentation
- Meta OOD Learning for Continuously Adaptive OOD Detection
- Incentivized Communication for Federated Bandits
- LLM-based Medical Assistant Personalization with Short- and Long-Term Memory Coordination