Papers
Fri 27 Oct 2023
204 papers
- DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial PurificationDiffusion models → Robustness, privacy and adversarial aspects
- Multi Time Scale World ModelsWorld models → World models for language agents
- Preventing Language Models From Hiding Their ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
- Publicly-Detectable Watermarking for Language ModelsLLM safety and security → Watermarking generated content and models
- Modeling Legal Reasoning: LM Annotation at the Edge of Human AgreementLLM reasoning → Reasoning for agents, planning and code
- Bridging Distributionally Robust Learning and Offline RL: An Approach to Mitigate Distribution Shift and Partial Data CoverageOffline RL and imitation learning from data → Offline RL algorithms
- MCRAGE: Synthetic Healthcare Data for FairnessDiffusion models → Medical imaging and segmentation
- Interactive Joint Planning for Autonomous VehiclesEnd-to-end autonomous driving → Imitation-learning end-to-end planners
- Guided Data Augmentation for Offline Reinforcement Learning and Imitation LearningOffline RL and imitation learning from data → Offline RL algorithms
- Fine-Tuning Language Models Using Formal Methods FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Ask more, know better: Reinforce-Learned Prompt Questions for Decision Making with Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
- Towards a Unified Conversational Recommendation System: Multi-task Learning via Contextualized Knowledge DistillationKnowledge distillation → Distillation for recommender systems
- DUMA: a Dual-Mind Conversational Agent with Fast and Slow ThinkingLLM reasoning → Reasoning for agents, planning and code +1
- ViCLEVR: A Visual Reasoning Dataset and Hybrid Multimodal Fusion Model for Visual Question Answering in VietnameseLLM reasoning → Multimodal reasoning
- ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single ImageDiffusion models → 3D, point cloud and scene generation
- Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Qilin-Med-VL: Towards Chinese Large Vision-Language Model for General HealthcareMultimodal LLMs / vision-language models → Medical vision-language models
- Mobile Application for Oral Disease Detection using Federated Learning
- Prioritising Interactive Flows in Data Center Networks With Central Control
- Determinants of renewable energy consumption in Madagascar: Evidence from feature selection algorithms
- Efficient Parallelization of a Ubiquitous Sequential Computation
- A Data-driven Deep Learning Approach for Bitcoin Price Forecasting
- Boosting Stock Price Prediction with Anticipated Macro Policy Changes
- MELEP: A Novel Predictive Measure of Transferability in Multi-Label ECG Diagnosis
- Edge AI Inference in Heterogeneous Constrained Computing: Feasibility and Opportunities
- Generative AI for Software Metadata: Overview of the Information Retrieval in Software Engineering Track at FIRE 2023
- Evaluating Cross-Domain Text-to-SQL Models and Benchmarks
- Contextual Stochastic Bilevel Optimization
- Feature Selection in the Contrastive Analysis Setting
- Sample based Explanations via Generalized Representers
- Using convolutional neural networks for stereological characterization of 3D hetero-aggregates based on synthetic STEM data
- Learning to recognize occluded and small objects with partial inputs
- Learning to design protein-protein interactions with enhanced generalization
- 3DCoMPaT++: An improved Large-scale 3D Vision Dataset for Compositional Recognition
- Deep Reinforcement Learning for Weapons to Targets Assignment in a Hypersonic strike
- Multi-fidelity Design of Porous Microstructures for Thermofluidic Applications
- On the Automatic Generation and Simplification of Children's Stories
- GPT-4 Vision on Medical Image Classification -- A Case Study on COVID-19 Dataset
- How Well Do Feature-Additive Explainers Explain Feature-Additive Predictors?
- Knowledge-based in silico models and dataset for the comparative evaluation of mammography AI for a range of breast characteristics, lesion conspicuities and doses
- MOSEL: Inference Serving Using Dynamic Modality Selection
- Weighted Sampled Split Learning (WSSL): Balancing Privacy, Robustness, and Fairness in Distributed Learning Environments
- Understanding and Improving Ensemble Adversarial Defense
- Parameter-Efficient Methods for Metastases Detection from Clinical Notes
- Causal disentanglement of multimodal data
- Semi-Synthetic Dataset Augmentation for Application-Specific Gaze Estimation
- Nearly Minimax Optimal Submodular Maximization with Bandit Feedback
- Benchingmaking Large Langage Models in Biomedical Triple Extraction
- Do Not Harm Protected Groups in Debiasing Language Representation Models
- LLMSTEP: LLM proofstep suggestions in Lean
- Approximate Heavy Tails in Offline (Multi-Pass) Stochastic Gradient Descent
- T5 meets Tybalt: Author Attribution in Early Modern English Drama Using Large Language Models
- MixRep: Hidden Representation Mixup for Low-Resource Speech Recognition
- Black-Box Optimization with Implicit Constraints for Public Policy
- A Novel Skip Orthogonal List for Dynamic Optimal Transport Problem
- M3C: A Framework towards Convergent, Flexible, and Unsupervised Learning of Mixture Graph Matching and Clustering
- Towards a fuller understanding of neurons with Clustered Compositional Explanations
- Exploring Shape Embedding for Cloth-Changing Person Re-Identification via 2D-3D Correspondences
- Expanding the Set of Pragmatic Considerations in Conversational AI
- SDOH-NLI: a Dataset for Inferring Social Determinants of Health from Clinical Notes
- The Bayesian Stability Zoo
- Fast Machine Learning Method with Vector Embedding on Orthonormal Basis and Spectral Transform
- Teacher Perception of Automatically Extracted Grammar Concepts for L2 Language Learning
- On the Fairness ROAD: Robust Optimization for Adversarial Debiasing
- A general learning scheme for classical and quantum Ising machines
- State-Action Similarity-Based Representations for Off-Policy Evaluation
- Entity Embeddings : Perspectives Towards an Omni-Modality Era for Large Language Models
- OffMix-3L: A Novel Code-Mixed Dataset in Bangla-English-Hindi for Offensive Language Identification
- Matching of Descriptive Labels to Glossary Descriptions
- MicroNAS: Memory and Latency Constrained Hardware-Aware Neural Architecture Search for Time Series Classification on Microcontrollers
- From Generative AI to Generative Internet of Things: Fundamentals, Framework, and Outlooks
- Unveil Sleep Spindles with Concentration of Frequency and Time
- Ontology Revision based on Pre-trained Language Models
- Large-scale Foundation Models and Generative AI for BigData Neuroscience
- SQLformer: Deep Auto-Regressive Query Graph Generation for Text-to-SQL Translation
- FP8-LM: Training FP8 Large Language Models
- Gen2Sim: Scaling up Robot Learning in Simulation with Generative Models
- Supervised and Penalized Baseline Correction
- A Stability Principle for Learning under Non-Stationarity
- Socially Cognizant Robotics for a Technology Enhanced Society
- Image Clustering Conditioned on Text Criteria
- Always Clear Days: Degradation Type and Severity Aware All-In-One Adverse Weather Removal
- Addressing GAN Training Instabilities via Tunable Classification Losses
- Riddle Generation using Learning Resources
- Sustainable Concrete via Bayesian Optimization
- Optimal Transport for Treatment Effect Estimation
- Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learning
- Universality for the global spectrum of random inner-product kernel matrices in the polynomial regime
- FOUND: Foot Optimization with Uncertain Normals for Surface Deformation Using Synthetic Data
- Navigating protein landscapes with a machine-learned transferable coarse-grained model
- LipSim: A Provably Robust Perceptual Similarity Metric
- Moments for Perceptive Narration Analysis Through the Emotional Attachment of Audience to Discourse and Story
- PlantPlotGAN: A Physics-Informed Generative Adversarial Network for Plant Disease Prediction
- Structured Semidefinite Programming for Recovering Structured Preconditioners
- Learning to Search Feasible and Infeasible Regions of Routing Problems with Flexible Neural k-Opt
- MalFake: A Multimodal Fake News Identification for Malayalam using Recurrent Neural Networks and VGG-16
- Label Shift Estimators for Non-Ignorable Missing Data
- A Self-Supervised Approach to Land Cover Segmentation
- A Review of the Evidence for Existential Risk from AI via Misaligned Power-Seeking
- α-Mutual Information: A Tunable Privacy Measure for Privacy Protection in Data Sharing
All 204
- Generative AI Model for Artistic Style Transfer Using Convolutional Neural Networks
- How Re-sampling Helps for Long-Tail Learning?
- Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation
- Edge AI-Based Vein Detector for Efficient Venipuncture in the Antecubital Fossa
- Deep Transformed Gaussian Processes
- Revising with a Backward Glance: Regressions and Skips during Reading as Cognitive Signals for Revision Policies in Incremental Processing
- TBDLNet: a network for classifying multidrug-resistant and drug-sensitive tuberculosis
- CROSS-Net: Region-Agnostic Taxi-Demand Prediction Using Feature Disentanglement
- Robustness of Algorithms for Causal Structure Learning to Hyperparameter Choice
- Understanding and Mitigating Hyperbolic Dimensional Collapse in Graph Contrastive Learning
- ArcheType: A Novel Framework for Open-Source Column Type Annotation using Large Language Models
- INA: An Integrative Approach for Enhancing Negotiation Strategies with Reward-Based Dialogue System
- Lost in Translation, Found in Spans: Identifying Claims in Multilingual Social Media
- Artifact-Robust Graph-Based Learning in Digital Pathology
- Is Scaling Learned Optimizers Worth It? Evaluating The Value of VeLO's 4000 TPU Months
- Model-free Posterior Sampling via Learning Rate Randomization
- Style Description based Text-to-Speech with Conditional Prosodic Layer Normalization based Diffusion GAN
- Personas as a Way to Model Truthfulness in Language Models
- MPrompt: Exploring Multi-level Prompt Tuning for Machine Reading Comprehension
- Enhancing Enterprise Network Security: Comparing Machine-Level and Process-Level Analysis for Dynamic Malware Detection
- Proportional Fairness in Clustering: A Social Choice Perspective
- Elevating Code-mixed Text Handling through Auditory Information of Words
- Disentangled Representation Learning with Large Language Models for Text-Attributed Graphs
- Improving Intrinsic Exploration by Creating Stationary Objectives
- Semi-Supervised Panoptic Narrative Grounding
- Unsupervised Representation Learning for Diverse Deformable Shape Collections
- End-to-end Video Gaze Estimation via Capturing Head-face-eye Spatial-temporal Interaction Context
- DELPHI: Data for Evaluating LLMs' Performance in Handling Controversial Issues
- Sample Complexity Bounds for Score-Matching: Causal Discovery and Generative Modeling
- OpinSummEval: Revisiting Automated Evaluation for Opinion Summarization
- A Global Multi-Unit Calibration as a Method for Large Scale IoT Particulate Matter Monitoring Systems Deployments
- Direct Unsupervised Denoising
- er.autopilot 1.0: The Full Autonomous Stack for Oval Racing at High Speeds
- Transductive conformal inference with adaptive scores
- Classifier-head Informed Feature Masking and Prototype-based Logit Smoothing for Out-of-Distribution Detection
- Mind the Gap: Automated Corpus Creation for Enthymeme Detection and Reconstruction in Learner Arguments
- Adversarial Anomaly Detection using Gaussian Priors and Nonlinear Anomaly Scores
- Lost in translation: using global fact-checks to measure multilingual misinformation prevalence, spread, and evolution
- A Chebyshev Confidence Guided Source-Free Domain Adaptation Framework for Medical Image Segmentation
- Unveiling the Potential of Probabilistic Embeddings in Self-Supervised Learning
- Lipschitz and H"older Continuity in Reproducing Kernel Hilbert Spaces
- Detrimental Contexts in Open-Domain Question Answering
- Knowledge Corpus Error in Question Answering
- On kernel-based statistical learning in the mean field limit
- A Scalable Framework for Table of Contents Extraction from Complex ESG Annual Reports
- Multi-grained Evidence Inference for Multi-choice Reading Comprehension
- "Honey, Tell Me What's Wrong", Global Explanation of Textual Discriminative Models through Cooperative Generation
- Text Augmented Spatial-aware Zero-shot Referring Image Segmentation
- Moral Responsibility for AI Systems
- On General Language Understanding
- Bayesian Prognostic Covariate Adjustment With Additive Mixture Priors
- Large language models for aspect-based sentiment analysis
- SentMix-3L: A Bangla-English-Hindi Code-Mixed Dataset for Sentiment Analysis
- FormalGeo: An Extensible Formalized Framework for Olympiad Geometric Problem Solving
- NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark
- DP-SGD with weight clipping
- Closing the Gap Between the Upper Bound and the Lower Bound of Adam's Iteration Complexity
- Deep Learning Enables Large Depth-of-Field Images for Sub-Diffraction-Limit Scanning Superlens Microscopy
- Autonomous 3D Exploration in Large-Scale Environments with Dynamic Obstacles
- InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews
- FaultSeg Swin-UNETR: Transformer-Based Self-Supervised Pretraining Model for Fault Recognition
- EcoLearn: Optimizing the Carbon Footprint of Federated Learning
- Multivessel Coronary Artery Segmentation and Stenosis Localisation using Ensemble Learning
- Developing a Multilingual Dataset and Evaluation Metrics for Code-Switching: A Focus on Hong Kong's Polylingual Dynamics
- Shape-centered Representation Learning for Visible-Infrared Person Re-identification
- Understanding Parameter Saliency via Extreme Value Theory
- Instance Segmentation under Occlusions via Location-aware Copy-Paste Data Augmentation
- A Comprehensive and Reliable Feature Attribution Method: Double-sided Remove and Reconstruct (DoRaR)
- A Survey on Trustworthy Edge Intelligence: From Security and Reliability To Transparency and Sustainability
- Diversifying Spatial-Temporal Perception for Video Domain Generalization
- Unified Segment-to-Segment Framework for Simultaneous Sequence Generation
- Transformers as Graph-to-Graph Models
- SOUL: Towards Sentiment and Opinion Understanding of Language
- Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method
- Lifting the Veil: Unlocking the Power of Depth in Q-learning
- 3D-Aware Visual Question Answering about Parts, Poses and Occlusions
- DocStormer: Revitalizing Multi-Degraded Colored Document Images to Pristine PDF
- The Innovation-to-Occupations Ontology: Linking Business Transformation Initiatives to Occupations and Skills
- Pitfalls in Language Models for Code Intelligence: A Taxonomy and Survey
- Improving the Knowledge Gradient Algorithm
- Natural Language Interfaces for Tabular Data Querying and Visualization: A Survey
- Federated Learning over Hierarchical Wireless Networks: Training Latency Minimization via Submodel Partitioning
- Impressions: Understanding Visual Semiotics and Aesthetic Impact
- Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
- LOOP-MAC: Learning-Based Multi-Agent Coordination with Guaranteed Local Feasibility in a Virtual Power Plant
- Reconstructive Latent-Space Neural Radiance Fields for Efficient 3D Scene Representations
- A Sublinear-Time Spectral Clustering Oracle with Improved Preprocessing Time
- ASPIRO: Any-shot Structured Parsing-error-Induced ReprOmpting for Consistent Data-to-Text Generation
- TarGEN: Targeted Data Generation with Large Language Models
- Siamese-DETR for Generic Multi-Object Tracking
- SmooSeg: Smoothness Prior for Unsupervised Semantic Segmentation
- Ranking with Slot Constraints
- Grid Jigsaw Representation with CLIP: A New Perspective on Image Clustering
- Reproducibility in Multiple Instance Learning: A Case For Algorithmic Unit Tests
- From Values to Opinions: Predicting Human Behaviors and Stances Using Value-Injected Large Language Models
- Function Space Bayesian Pseudocoreset for Bayesian Neural Networks
- Boosting Data Analytics With Synthetic Volume Expansion
- Adaptive operator learning for infinite-dimensional Bayesian inverse problems
- Optimal Pricing for Data-Augmented AutoML Marketplaces
- What You See Is What You Detect: Towards better Object Densification in 3D detection
- Real-time Animation Generation and Control on Rigged Models via Large Language Models
- Positional Encoding-based Resident Identification in Multi-resident Smart Homes
- One Style is All you Need to Generate a Video
- Hybrid Optical Turbulence Models Using Machine Learning and Local Measurements