Papers
Fri 12 May 2023
183 papers
- ACCENT: An Automatic Event Commonsense Evaluation Metric for Open-Domain Dialogue SystemsLLM reasoning → Reasoning benchmarks and evaluation
- Learning to Reason over Scene Graphs: A Case Study of Finetuning GPT-2 into a Robot Language Model for Grounded Task PlanningLLM reasoning → Spatial and embodied reasoning
- Poisson-Gaussian Holographic Phase Retrieval with Score-based Image PriorDiffusion models → Inverse problems and image restoration
- Beware of diffusion models for synthesizing medical images -- A comparison with GANs in terms of memorizing brain MRI and chest x-ray imagesDiffusion models → Medical imaging and segmentation
- Scalable Coupling of Deep Learning with Logical ReasoningLLM reasoning → Reasoning benchmarks and evaluation
- Knowledge distillation with Segment Anything (SAM) model for Planetary Geological MappingKnowledge distillation → Detection and dense prediction distillation
- Towards Convergence Rates for Parameter Estimation in Gaussian-gated Mixture of ExpertsMixture-of-experts → MoE theory and gating functions
- WEDGE: A multi-weather autonomous driving dataset built from generative vision-language modelsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
- Learn to Unlearn: A Survey on Machine UnlearningLLM safety and security → Machine unlearning
- ArtGPT-4: Towards Artistic-understanding Large Vision-Language Models with Enhanced AdapterMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
- Identify, Estimate and Bound the Uncertainty of Reinforcement Learning for Autonomous DrivingEnd-to-end autonomous driving → Reinforcement learning for driving
- A Lightweight Domain Adversarial Neural Network Based on Knowledge Distillation for EEG-based Cross-subject Emotion RecognitionKnowledge distillation → Multimodal distillation
- Is ChatGPT a Good Causal Reasoner? A Comprehensive EvaluationLLM reasoning → Causal reasoning in LLMs
- CLIP-Count: Towards Text-Guided Zero-Shot Object CountingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Provably Convergent Schr"odinger Bridge with Applications to Probabilistic Time Series ImputationDiffusion models → Diffusion foundations and sampling
- Better speech synthesis through scalingDiffusion models → Audio, speech and music
- Towards Generalizable Reinforcement Learning for Trade Execution
- A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineering
- Machine Vision Using Cellphone Camera: A Comparison of deep networks for classifying three challenging denominations of Indian Coins
- High Accuracy and Low Regret for User-Cold-Start Using Latent Bandits
- Semantic-aware Digital Twin for Metaverse: A Comprehensive Review
- Multi-Agent Reinforcement Learning for Network Routing in Integrated Access Backhaul Networks
- A stable deep adversarial learning approach for geological facies generation
- Designing for Meaningful Human Control in Military Human-Machine Teams
- Unlocking the Use of Raw Multispectral Earth Observation Imagery for Onboard Artificial Intelligence
- An Automated Power Conservation System (APCS) using Particle Photon and Smartphone
- Milestones in Autonomous Driving and Intelligent Vehicles Part I: Control, Computing System Design, Communication, HD Map, Testing, and Human Behaviors
- An Intelligent SDWN Routing Algorithm Based on Network Situational Awareness and Deep Reinforcement Learning
- Intelligent multicast routing method based on multi-agent deep reinforcement learning in SDWN
- IMAGINATOR: Pre-Trained Image+Text Joint Embeddings using Word-Level Grounding of Images
- Subject-based Non-contrastive Self-Supervised Learning for ECG Signal Processing
- MM-Fi: Multi-Modal Non-Intrusive 4D Human Dataset for Versatile Wireless Sensing
- Neurosymbolic AI and its Taxonomy: a survey
- Online machine-learning forecast uncertainty estimation for sequential data assimilation
- AMULET: Adaptive Matrix-Multiplication-Like Tasks
- Improving Small Language Models on PubMedQA via Generative Data Augmentation
- Constructing Holistic Measures for Social Biases in Masked Language Models
- Using Deepfake Technologies for Word Emphasis Detection
- Automated Grain Boundary (GB) Segmentation and Microstructural Analysis in 347H Stainless Steel Using Deep Learning and Multimodal Microscopy
- HPE:Answering Complex Questions over Text by Hybrid Question Parsing and Execution
- ROI-based Deep Image Compression with Swin Transformers
- Revisiting Matching Pursuit: Beyond Approximate Submodularity
- Accelerator-Aware Training for Transducer-Based Speech Recognition
- PanFlowNet: A Flow-Based Deep Network for Pan-sharpening
- Monitoring and Adapting ML Models on Mobile Devices
- NL2TL: Transforming Natural Languages to Temporal Logics using Large Language Models
- Knowledge Authoring for Rules and Actions
- Unsupervised Melody-Guided Lyrics Generation
- TinyStories: How Small Can Language Models Be and Still Speak Coherent English?
- Private and Communication-Efficient Algorithms for Entropy Estimation
- To transfer or not transfer: Unified transferability metric and analysis
- Measuring Surprise in the Wild
- Predicting COVID-19 pandemic by spatio-temporal graph neural networks: A New Zealand's study
- Learning in Inverse Optimization: Incenter Cost, Augmented Suboptimality Loss, and Algorithms
- In Search of Verifiability: Explanations Rarely Enable Complementary Performance in AI-Advised Decision Making
- Designing Optimal Behavioral Experiments Using Machine Learning
- Intercomparison of Brown Dwarf Model Grids and Atmospheric Retrieval Using Machine Learning
- Parallel Tree Kernel Computation
- Field theory for optimal signal propagation in ResNets
- Multi-Modal 3D Object Detection by Box Matching
- Zero-shot racially balanced dataset generation using an existing biased StyleGAN2
- Using Language Models to Detect Alarming Student Responses
- ELSA -- Enhanced latent spaces for improved collider simulations
- Mastering Percolation-like Games with Deep Learning
- Synthetic data generation for a longitudinal cohort study -- Evaluation, method extension and reproduction of published data analysis results
- ML-Based Teaching Systems: A Conceptual Framework
- Exploring the Rate-Distortion-Complexity Optimization in Neural Image Compression
- A Critical View of Vision-Based Long-Term Dynamics Prediction Under Environment Misalignment
- The ASNR-MICCAI Brain Tumor Segmentation (BraTS) Challenge 2023: Intracranial Meningioma
- Efficient Neural Network based Classification and Outlier Detection for Image Moderation using Compressed Sensing and Group Testing
- On the Partial Convexification for Low-Rank Spectral Optimization: Rank Bounds and Algorithms
- Text2Cohort: Facilitating Intuitive Access to Biomedical Data with Natural Language Cohort Discovery
- Zero-shot Item-based Recommendation via Multi-task Product Knowledge Graph Pre-Training
- Design, Development, and Evaluation of an Interactive Personalized Social Robot to Monitor and Coach Post-Stroke Rehabilitation Exercises
- Meta Omnium: A Benchmark for General-Purpose Learning-to-Learn
- Agile gesture recognition for capacitive sensing devices: adapting on-the-job
- PALR: Personalization Aware LLMs for Recommendation
- Uncertainty Estimation and Out-of-Distribution Detection for Deep Learning-Based Image Reconstruction using the Local Lipschitz
- What are the Desired Characteristics of Calibration Sets? Identifying Correlates on Long Form Scientific Summarization
- NevIR: Negation in Neural Information Retrieval
- Spider GAN: Leveraging Friendly Neighbors to Accelerate GAN Training
- Lower Bounds and Accelerated Algorithms in Distributed Stochastic Optimization with Communication Compression
- Multimodal Sentiment Analysis: A Survey
- Is ChatGPT Fair for Recommendation? Evaluating Fairness in Large Language Model Recommendation
- Generative AI: Implications and Applications for Education
- ViT Unified: Joint Fingerprint Recognition and Presentation Attack Detection
- Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformer
- Opti Code Pro: A Heuristic Search-based Approach to Code Refactoring
- MoMo: Momentum Models for Adaptive Learning Rates
- Fisher Information Embedding for Node and Graph Learning
- A Memory Model for Question Answering from Streaming Data Supported by Rehearsal and Anticipation of Coreference Information
- Measuring Progress in Fine-grained Vision-and-Language Understanding
- Dish detection in food platters: A framework for automated diet logging and nutrition management
- Understanding Automatic Differentiation Pitfalls
- Content-based jewellery item retrieval using the local region-based histograms
- Saturated Non-Monotonic Activation Functions
- Joint MR sequence optimization beats pure neural network approaches for spin-echo MRI super-resolution
- SPADE: Sparse Pillar-based 3D Object Detection Accelerator for Autonomous Driving
- AGFormer: Efficient Graph Representation with Anchor-Graph Transformer
- HFLIC: Human Friendly Perceptual Learned Image Compression with Reinforced Transform
All 183
- BlendFields: Few-Shot Example-Driven Facial Modeling
- eXplainable Artificial Intelligence on Medical Images: A Survey
- LeXFiles and LegalLAMA: Facilitating English Multinational Legal Language Model Development
- Calibration-Aware Bayesian Learning
- Learning representations that are closed-form Monge mapping optimal with application to domain adaptation
- Device-Robust Acoustic Scene Classification via Impulse Response Augmentation
- Visual Information Extraction in the Wild: Practical Dataset and End-to-end Solution
- Dynamically Conservative Self-Driving Planner for Long-Tail Cases
- Gallery Sampling for Robust and Fast Face Identification
- Temporal Network Creation Games
- A Comprehensive Analysis of Adapter Efficiency
- Benchmarks and leaderboards for sound demixing tasks
- Reduced Label Complexity For Tight ℓ2 Regression
- Online Learning Under A Separable Stochastic Approximation Framework
- Comprehensive Solution Program Centric Pretraining for Table-and-Text Hybrid Numerical Reasoning
- Perturbation-based QE: An Explainable, Unsupervised Word-level Quality Estimation Method for Blackbox Machine Translation
- Improving Cascaded Unsupervised Speech Translation with Denoising Back-translation
- Deep Deterministic Policy Gradient for End-to-End Communication Systems without Prior Channel Knowledge
- Expertise-based Weighting for Regression Models with Noisy Labels
- Unlocking the Potential of Medical Imaging with ChatGPT's Intelligent Diagnostics
- Instance Smoothed Contrastive Learning for Unsupervised Sentence Embedding
- Selective imitation on the basis of reward function similarity
- A Multidimensional Graph Fourier Transformation Neural Network for Vehicle Trajectory Prediction
- Comparison of machine learning models applied on anonymized data with different techniques
- Distributed Gradient Descent for Functional Learning
- Two-in-One: A Model Hijacking Attack Against Text Generation Models
- Color Deconvolution applied to Domain Adaptation in HER2 histopathological images
- Synergistic Interplay between Search and Large Language Models for Information Retrieval
- Learning Monocular Depth in Dynamic Environment via Context-aware Temporal Attention
- Prompt Learning to Mitigate Catastrophic Forgetting in Cross-lingual Transfer for Open-domain Dialogue Generation
- The Ethics of AI in Games
- Investigating the Sensitivity of Automatic Speech Recognition Systems to Phonetic Variation in L2 Englishes
- One-step Bipartite Graph Cut: A Normalized Formulation and Its Application to Scalable Subspace Clustering
- Surfacing Biases in Large Language Models using Contrastive Input Decoding
- DAISM: Digital Approximate In-SRAM Multiplier-based Accelerator for DNN Training and Inference
- Implications of Deep Circuits in Improving Quality of Quantum Question Answering
- Interactive Text-to-SQL Generation via Editable Step-by-Step Explanations
- Decentralized Learning over Wireless Networks: The Effect of Broadcast with Random Access
- S-REINFORCE: A Neuro-Symbolic Policy Gradient Approach for Interpretable Reinforcement Learning
- Multi-Value Alignment in Normative Multi-Agent System: Evolutionary Optimisation Approach
- Towards Transliteration between Sindhi Scripts from Devanagari to Perso-Arabic
- Improving the Quality of Neural Machine Translation Through Proper Translation of Name Entities
- Towards Versatile and Efficient Visual Knowledge Integration into Pre-trained Language Models with Cross-Modal Adapters
- ZARA: Improving Few-Shot Self-Rationalization for Small Language Models
- A Survey on Deep Learning-Based Monocular Spacecraft Pose Estimation: Current State, Limitations and Prospects
- BundleRecon: Ray Bundle-Based 3D Neural Reconstruction
- Model-based Programming: Redefining the Atomic Unit of Programming for the Deep Learning Era
- MedGPTEval: A Dataset and Benchmark to Evaluate Responses of Large Language Models in Medicine
- MotionBEV: Attention-Aware Online LiDAR Moving Object Segmentation with Bird's Eye View based Appearance and Motion Features
- Locking and Quacking: Stacking Bayesian model predictions by log-pooling and superposition
- Enhance Multi-Scale Spatial-Temporal Coherence for Configurable Video Anomaly Detection
- ActUp: Analyzing and Consolidating tSNE and UMAP
- Parameterized Approximation for Robust Clustering in Discrete Geometric Spaces
- partialmathbbB nets: learning discrete functions by gradient descent
- Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularization
- Efficient Search of Comprehensively Robust Neural Architectures via Multi-fidelity Evaluation
- Self-Learning Symmetric Multi-view Probabilistic Clustering
- Multi-Relational Hyperbolic Word Embeddings from Natural Language Definitions
- An Object SLAM Framework for Association, Mapping, and High-Level Tasks
- The 3rd Anti-UAV Workshop & Challenge: Methods and Results
- RepCL: Exploring Effective Representation for Continual Text Classification
- Open-WikiTable: Dataset for Open Domain Question Answering with Complex Reasoning over Table
- Quaternion-valued Correlation Learning for Few-Shot Semantic Segmentation
- Harvesting Event Schemas from Large Language Models
- SSD-MonoDETR: Supervised Scale-aware Deformable Transformer for Monocular 3D Object Detection
- Meta-Optimization for Higher Model Generalizability in Single-Image Depth Prediction
- Gaussian Prior Reinforcement Learning for Nested Named Entity Recognition
- A Central Asian Food Dataset for Personalized Dietary Interventions, Extended Abstract
- Machine-learning-accelerated simulations to enable automatic surface reconstruction
- Quantile-Based Deep Reinforcement Learning using Two-Timescale Policy Gradient Algorithms
- On the Optimality of Misspecified Kernel Ridge Regression
- T-former: An Efficient Transformer for Image Inpainting
- Dual Forgetting Operators in the Context of Weakest Sufficient and Strongest Necessary Conditions
- When Giant Language Brains Just Aren't Enough! Domain Pizzazz with Knowledge Sparkle Dust
- Asymmetric feature interaction for interpreting model predictions
- Transavs: End-To-End Audio-Visual Segmentation With Transformer
- Versatile audio-visual learning for emotion recognition
- MMG-Ego4D: Multi-Modal Generalization in Egocentric Action Recognition
- Rethinking k-means from manifold learning perspective
- Mem-Rec: Memory Efficient Recommendation System using Alternative Representation
- MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers
- Boosting Value Decomposition via Unit-Wise Attentive State Representation for Cooperative Multi-Agent Reinforcement Learning
- Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual Recognition