Papers
Tue 11 Jul 2023
210 papers
- Scale Alone Does not Improve Mechanistic Interpretability in Vision ModelsMechanistic interpretability → Circuits and mechanistic analysis
- Metropolis Sampling for Constrained Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Geometric Neural Diffusion ProcessesDiffusion models → Diffusion foundations and sampling
- Boosting Feedback Efficiency of Interactive Reinforcement Learning by Adaptive Learning from ScoresLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- On the Vulnerability of DeepFake Detectors to Attacks Generated by Denoising Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
- Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-CollaborationLLM agents and tool use → General LLM agent frameworks and benchmarks
- Navigating Uncertainty: The Role of Short-Term Trajectory Prediction in Autonomous Vehicle SafetyEnd-to-end autonomous driving → End-to-end system architecture
- The Staged Knowledge Distillation in Video Classification: Harmonizing Student Progress by a Complementary Weakly Supervised FrameworkKnowledge distillation → General knowledge distillation methods
- Membership Inference Attacks on DNNs using Adversarial PerturbationsLLM safety and security → Membership inference attacks
- Retrieval-augmented GPT-3.5-based Text-to-SQL Framework with Sample-aware Prompting and Dynamic Revision ChainRetrieval-augmented generation → RAG robustness and adaptive retrieval
- Neural-Symbolic Recommendation with Graph-Enhanced InformationLLM reasoning → LLM reasoning for recommendation
- Selective Sampling and Imitation Learning via Online RegressionOffline RL and imitation learning from data → Imitation learning methods
- Epidemic Modeling with Generative AgentsLLM agents and tool use → Social simulation and multi-agent debate
- Diffusion idea exploration for art generationDiffusion models → Image generation, text-to-image and editing
- Secrets of RLHF in Large Language Models Part I: PPOLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Non-Hierarchical Transformers for Pedestrian Segmentation
- A Heavy-Load-Enhanced and Changeable-Periodicity-Perceived Workload Prediction Network
- Writer adaptation for offline text recognition: An exploration of neural network-based methods
- Sports Betting: an application of neural networks and modern portfolio theory to the English Premier League
- Unsupervised Learning in Complex Systems
- Has China caught up to the US in AI research? An exploration of mimetic isomorphism as a model for late industrializers
- Exploring the Emotional and Mental Well-Being of Individuals with Long COVID Through Twitter Analysis
- Can I say, now machines can think?
- HistoColAi: An Open-Source Web Platform for Collaborative Digital Histology Image Annotation with AI-Driven Predictive Integration
- Reducing Causality to Functions with Structural Models
- Depth-bounded Epistemic Logic
- Named entity recognition using GPT for identifying comparable companies
- RoPDA: Robust Prompt-based Data Augmentation for Low-Resource Named Entity Recognition
- AnuraSet: A dataset for benchmarking Neotropical anuran calls identification in passive acoustic monitoring
- Lightweight reranking for language model generations
- PIGEON: Predicting Image Geolocations
- Influential Simplices Mining via Simplicial Convolutional Network
- Scaling Distributed Multi-task Reinforcement Learning with Experience Sharing
- Bag of Views: An Appearance-based Approach to Next-Best-View Planning for 3D Reconstruction
- Memorization Through the Lens of Curvature of Loss Function Around Samples
- Relational Extraction on Wikipedia Tables using Convolutional and Memory Networks
- Bayesian taut splines for estimating the number of modes
- Safe Reinforcement Learning for Strategic Bidding of Virtual Power Plants in Day-Ahead Markets
- Improving Segmentation and Detection of Lesions in CT Scans Using Intensity Distribution Supervision
- Differentiable Forward Projector for X-ray Computed Tomography
- A Hierarchical Transformer Encoder to Improve Entire Neoplasm Segmentation on Whole Slide Image of Hepatocellular Carcinoma
- 3D Medical Image Segmentation based on multi-scale MPU-Net
- Improved POS tagging for spontaneous, clinical speech using data augmentation
- Machine Learning Study of the Extended Drug-target Interaction Network informed by Pain Related Voltage-Gated Sodium Channels
- Grid Cell-Inspired Fragmentation and Recall for Efficient Map Building
- Implicit regularisation in stochastic gradient descent: from single-objective to two-player games
- Merging multiple input descriptors and supervisors in a deep neural network for tractogram filtering
- Making the Nystr"om method highly accurate for low-rank approximations
- EgoAdapt: A multi-stream evaluation study of adaptation to real-world egocentric user video
- Large Language Models
- Automated Artifact Detection in Ultra-widefield Fundus Photography of Patients with Sickle Cell Disease
- Neural Machine Translation Data Generation and Augmentation using ChatGPT
- Weisfeiler and Leman Go Measurement Modeling: Probing the Validity of the WL Test
- Random-Set Neural Networks (RS-NN)
- Rad-ReStruct: A Novel VQA Benchmark and Method for Structured Radiology Reporting
- Realtime Spectrum Monitoring via Reinforcement Learning -- A Comparison Between Q-Learning and Heuristic Methods
- Line Art Colorization of Fakemon using Generative Adversarial Neural Networks
- Towards Robust and Efficient Continual Language Learning
- Effective Latent Differential Equation Models via Attention and Multiple Shooting
- Towards A Scalable Solution for Improving Multi-Group Fairness in Compositional Classification
- An Open-Source Knowledge Graph Ecosystem for the Life Sciences
- MoP-CLIP: A Mixture of Prompt-Tuned CLIP Models for Domain Incremental Learning
- Measure transfer via stochastic slicing and matching
- A Causal Ordering Prior for Unsupervised Representation Learning
- SepHRNet: Generating High-Resolution Crop Maps from Remote Sensing imagery using HRNet with Separable Convolution
- ReLoRA: High-Rank Training Through Low-Rank Updates
- Objaverse-XL: A Universe of 10M+ 3D Objects
- Evidence-based Hand Hygiene. Can You Trust the Fluorescent-based Assessment Methods?
- Better Handling Coreference Resolution in Aspect Level Sentiment Classification by Fine-Tuning Language Models
- Multiobjective Hydropower Reservoir Operation Optimization with Transformer-Based Deep Reinforcement Learning
- ConFL: Constraint-guided Fuzzing for Machine Learning Framework
- Learning Active Subspaces and Discovering Important Features with Gaussian Radial Basis Functions Neural Networks
- A Comprehensive Survey of Deep Transfer Learning for Anomaly Detection in Industrial Time Series: Methods, Applications, and Directions
- Speech Diarization and ASR with GMM
- Fundamental limits of overparametrized shallow neural networks for supervised learning
- Hyperspherical Embedding for Point Cloud Completion
- Transaction Fraud Detection via an Adaptive Graph Neural Network
- Belief Revision from Probability
- Causal Kripke Models
- Characterization of AGM Belief Contraction in Terms of Conditionals
- DNAGPT: A Generalized Pre-trained Tool for Versatile DNA Sequence Analysis Tasks
- Separate-and-Aggregate: A Transformer-based Patch Refinement Model for Knowledge Graph Completion
- CILF:Causality Inspired Learning Framework for Out-of-Distribution Vehicle Trajectory Prediction
- A DeepLearning Framework for Dynamic Estimation of Origin-Destination Sequence
- Latent Space Perspicacity and Interpretation Enhancement (LS-PIE) Framework
- mathrmSAMMed: A medical image annotation framework based on large vision model
- Image Reconstruction using Enhanced Vision Transformer
- Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives
- My3DGen: A Scalable Personalized 3D Generative Model
- EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone
- Efficient 3D Articulated Human Generation with Layered Surface Volumes
- Empowering Cross-lingual Behavioral Testing of NLP Models with Typological Features
- Bio-Inspired Night Image Enhancement Based on Contrast Enhancement and Denoising
- ISLTranslate: Dataset for Translating Indian Sign Language
- Improving the Security of Smartwatch Payment with Deep Learning
- One-Versus-Others Attention: Scalable Multimodal Integration for Biomedical Data
- Self-Supervised Learning with Lie Symmetries for Partial Differential Equations
- Differential Analysis of Triggers and Benign Features for Black-Box DNN Backdoor Detection
- Duncode Characters Shorter
- BLUEX: A benchmark based on Brazilian Leading Universities Entrance eXams
All 210
- 3D detection of roof sections from a single satellite image and application to LOD2-building reconstruction
- Domain-Agnostic Neural Architecture for Class Incremental Continual Learning in Document Processing Platform
- Handwritten Text Recognition Using Convolutional Neural Network
- Stochastic Nested Compositional Bi-level Optimization for Robust Feature Learning
- Combating Data Imbalances in Federated Semi-supervised Learning with Dual Regulators
- GujiBERT and GujiGPT: Construction of Intelligent Information Processing Foundation Language Models for Ancient Texts
- Leveraging Variational Autoencoders for Parameterized MMSE Estimation
- Tracking Most Significant Shifts in Nonparametric Contextual Bandits
- Explaining Competitive-Level Programming Solutions using LLMs
- ProgGP: From GuitarPro Tablature Neural Generation To Progressive Metal Production
- Self-supervised adversarial masking for 3D point cloud representation learning
- Class Instance Balanced Learning for Long-Tailed Classification
- Predicting small molecules solubilities on endpoint devices using deep ensemble neural networks
- Automatic Generation of Semantic Parts for Face Image Synthesis
- Masked Vision and Language Pre-training with Unimodal and Multimodal Contrastive Losses for Medical Visual Question Answering
- Discovering Symbolic Laws Directly from Trajectories with Hamiltonian Graph Neural Networks
- Rethinking Distribution Shifts: Empirical Analysis and Modeling for Tabular Data
- Unbiased Scene Graph Generation via Two-stage Causal Modeling
- CareFall: Automatic Fall Detection through Wearable Devices and AI Methods
- APRF: Anti-Aliasing Projection Representation Field for Inverse Problem in Imaging
- U-CREAT: Unsupervised Case Retrieval using Events extrAcTion
- Integrated Planning in Hospitals: A Review
- OpenAL: An Efficient Deep Active Learning Framework for Open-Set Pathology Image Classification
- MAP- and MLE-Based Teaching
- Minimizing robust density power-based divergences for general parametric density models
- DRMC: A Generalist Model with Dynamic Routing for Multi-Center PET Image Synthesis
- Does pre-training on brain-related tasks results in better deep-learning-based brain age biomarkers?
- A Survey From Distributed Machine Learning to Distributed Deep Learning
- Attribute Controlled Dialogue Prompting
- Emu: Generative Pretraining in Multimodality
- Supervised Attention Using Homophily in Graph Neural Networks
- Score Function Gradient Estimation to Widen the Applicability of Decision-Focused Learning
- Contextual Pre-planning on Reward Machine Abstractions for Enhanced Transfer in Deep Reinforcement Learning
- Reject option models comprising out-of-distribution detection
- Differentially Private Statistical Inference through β-Divergence One Posterior Sampling
- Using Linear Regression for Iteratively Training Neural Networks
- Decorrelation using Optimal Transport
- CAT-ViL: Co-Attention Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery
- ResMatch: Residual Attention Learning for Local Feature Matching
- Mao-Zedong At SemEval-2023 Task 4: Label Represention Multi-Head Attention Model With Contrastive Learning-Enhanced Nearest Neighbor Mechanism For Multi-Label Text Classification
- Enriching Verbal Feedback from Usability Testing: Automatic Linking of Thinking-Aloud Recordings and Stimulus using Eye Tracking and Mouse Data
- Neural Quantile Optimization for Edge-Cloud Networking
- A Mapping Study of Machine Learning Methods for Remaining Useful Life Estimation of Lead-Acid Batteries
- SuryaKiran at MEDIQA-Sum 2023: Leveraging LoRA for Clinical Dialogue Summarization
- On the Effectiveness of Speech Self-supervised Learning for Music
- A Modular Multimodal Architecture for Gaze Target Prediction: Application to Privacy-Sensitive Settings
- Stable Normative Explanations: From Argumentation to Deontic Logic
- Fast Neural Network Inference on FPGAs for Triggering on Long-Lived Particles at Colliders
- ExFaceGAN: Exploring Identity Directions in GAN's Learned Latent Space for Synthetic Identity Generation
- A Modal Logic for Explaining some Graph Neural Networks
- Deep Probabilistic Movement Primitives with a Bayesian Aggregator
- Unveiling the Invisible: Enhanced Detection and Analysis of Deteriorated Areas in Solar PV Modules Using Unsupervised Sensing Algorithms and 3D Augmented Reality
- TIAM -- A Metric for Evaluating Alignment in Text-to-Image Generation
- On the Use of Self-Supervised Speech Representations in Spontaneous Speech Synthesis
- Overview of BioASQ 2023: The eleventh BioASQ challenge on Large-Scale Biomedical Semantic Indexing and Question Answering
- DFR: Depth from Rotation by Uncalibrated Image Rectification with Latitudinal Motion Assumption
- One-Shot Learning for Periocular Recognition: Exploring the Effect of Domain Adaptation and Data Bias on Deep Representations
- Enhancing Continuous Time Series Modelling with a Latent ODE-LSTM Approach
- Transaction Fraud Detection via Spatial-Temporal-Aware Graph Transformer
- ℓp-Regression in the Arbitrary Partition Model of Communication
- Piecing Together Clues: A Benchmark for Evaluating the Detective Skills of Large Language Models
- Conformalization of Sparse Generalized Linear Models
- A Deep Dive into Perturbations as Evaluation Technique for Time Series XAI
- ATWM: Defense against adversarial malware based on adversarial training
- Offline and Online Optical Flow Enhancement for Deep Video Compression
- SAR-NeRF: Neural Radiance Fields for Synthetic Aperture Radar Multi-View Representation
- Vacaspati: A Diverse Corpus of Bangla Literature
- OntoChatGPT Information System: Ontology-Driven Structured Prompts for ChatGPT Meta-Learning
- Argumentative Segmentation Enhancement for Legal Summarization
- Estimating label quality and errors in semantic segmentation data via any model
- Uni-Removal: A Semi-Supervised Framework for Simultaneously Addressing Multiple Degradations in Real-World Images
- Aggregating Credences into Beliefs: Agenda Conditions for Impossibility Results
- Mining for Unknown Unknowns
- Cognitive Bias and Belief Revision
- A Theory of Bounded Inductive Rationality
- Exploiting Asymmetry in Logic Puzzles: Using ZDDs for Symbolic Model Checking Dynamic Epistemic Logic
- Tableaux for the Logic of Strategically Knowing How
- System of Spheres-based Two Level Credibility-limited Revisions
- On Imperfect Recall in Multi-Agent Influence Diagrams
- Strengthening Consistency Results in Modal Logic
- Towards Understanding In-Context Learning with Contrastive Demonstrations and Saliency Maps
- Portfolio Optimization: A Comparative Study
- Epistemic Syllogistic: First Steps
- Disentangled Contrastive Image Translation for Nighttime Surveillance
- Number Systems for Deep Neural Network Architectures: A Survey
- Synthetic Dataset for Evaluating Complex Compositional Knowledge for Natural Language Inference
- Towards Anytime Optical Flow Estimation with Event Cameras
- FairLay-ML: Intuitive Remedies for Unfairness in Data-Driven Social-Critical Algorithms
- Unleashing the Potential of Regularization Strategies in Learning with Noisy Labels
- Feature Activation Map: Visual Explanation of Deep Learning Models for Image Classification
- TRansPose: Large-Scale Multispectral Dataset for Transparent Object
- Test-Time Training on Video Streams
- Improving RNN-Transducers with Acoustic LookAhead
- Control as Probabilistic Inference as an Emergent Communication Mechanism in Multi-Agent Reinforcement Learning
- Neural Point-based Volumetric Avatar: Surface-guided Neural Points for Efficient and Photorealistic Volumetric Head Avatar
- Empowering recommender systems using automatically generated Knowledge Graphs and Reinforcement Learning
- PowerFusion: A Tensor Compiler with Explicit Data Movement Description and Instruction-level Graph IR
- Uncertainty Quantification of the Virial Black Hole Mass with Conformal Prediction
- Monotone deep Boltzmann machines
- Benchmarking Bayesian Causal Discovery Methods for Downstream Treatment Effect Estimation
- A Multi-view Impartial Decision Network for Frontotemporal Dementia Diagnosis
- SAM-U: Multi-box prompts triggered uncertainty estimation for reliable SAM in medical image
- DyCL: Dynamic Neural Network Compilation Via Program Rewriting and Graph Optimization
- Intrinsically motivated graph exploration using network theories of human curiosity
- Reinforcement Learning with Non-Cumulative Objective
- PKU-GoodsAD: A Supermarket Goods Dataset for Unsupervised Anomaly Detection and Segmentation
- Hybrid hidden Markov LSTM for short-term traffic flow prediction
- Compact Twice Fusion Network for Edge Detection
- DDGM: Solving inverse problems by Diffusive Denoising of Gradient-based Minimization
- Benchmarking Algorithms for Federated Domain Generalization