Papers
Thu 22 Jun 2023
174 papers
- Visual Adversarial Examples Jailbreak Aligned Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +2
- Directional diffusion models for graph representation learningDiffusion models → Flow matching, time series and science
- DiMSam: Diffusion Models as Samplers for Task and Motion Planning under Partial ObservabilityDiffusion models → Diffusion and flow policies for robotics
- Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory WeightingOffline RL and imitation learning from data → Offline RL algorithms
- Continuous Layout Editing of Single Images with Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
- Can Differentiable Decision Trees Enable Interpretable Reward Learning from Human Feedback?LLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Towards More Realistic Membership Inference Attacks on Large Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
- DiffWA: Diffusion Models for Watermark AttackDiffusion models → Robustness, privacy and adversarial aspects +1
- A prior regularized full waveform inversion using generative diffusion modelsDiffusion models → Flow matching, time series and science
- Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of ThoughtWorld models → World models for language agents +1
- Set-Membership Inference Attacks using Data Watermarking
- Noor-Ghateh: A Benchmark Dataset for Evaluating Arabic Word Segmenters in Hadith Domain
- Enhancing Reliability in Federated mmWave Networks: A Practical and Scalable Solution using Radar-Aided Dynamic Blockage Recognition
- The Role of Schwartz Measures in Human Tri-Color Vision
- Predictive Patentomics: Forecasting Innovation Success and Valuation with ChatGPT
- Inertial Navigation Meets Deep Learning: A Survey of Current Trends and Future Directions
- Realistic Synthetic Financial Transactions for Anti-Money Laundering Models
- Harnessing Data Augmentation to Quantify Uncertainty in the Early Estimation of Single-Photon Source Quality
- Molecular geometric deep learning
- Beyond Chemical Language: A Multimodal Approach to Enhance Molecular Property Prediction
- Prediction of Deep Ice Layer Thickness Using Adaptive Recurrent Graph Neural Networks
- Broadening the perspective for sustainable AI: Comprehensive sustainability criteria and indicators for AI systems
- Model Families for Multi-Criteria Decision Support: A COVID-19 Case Study
- Approximate Causal Effect Identification under Weak Confounding
- Continuous Online Extrinsic Calibration of Fisheye Camera and LiDAR
- The Inductive Bias of Flatness Regularization for Deep Matrix Factorization
- Pruning for Better Domain Generalizability
- Document Image Cleaning using Budget-Aware Black-Box Approximation
- On the Limitations and Possibilities of Nash Regret Minimization in Zero-Sum Matrix Games under Noisy Feedback
- DiversiGATE: A Comprehensive Framework for Reliable Large Language Models
- TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning
- Optimal Cost-Preference Trade-off Planning with Multiple Temporal Tasks
- Neural Network Pruning for Real-time Polyp Segmentation
- Improving Log-Cumulant Based Estimation of Roughness Information in SAR imagery
- Pre or Post-Softmax Scores in Gradient-based Attribution Methods, What is Best?
- Prompt to GPT-3: Step-by-Step Thinking Instructions for Humor Generation
- Uniform Convergence with Square-Root Lipschitz Loss
- An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression
- Prediction of Annual Snow Accumulation Using a Recurrent Graph Convolutional Approach
- Targeted Background Removal Creates Interpretable Feature Visualizations
- Amorphous Fortress: Observing Emergent Behavior in Multi-Agent FSMs
- A Sparse Graph Formulation for Efficient Spectral Image Segmentation
- Anticipatory Thinking Challenges in Open Worlds: Risk Management
- Rethinking the Physical Symbol Systems Hypothesis
- "Filling the Blanks'': Identifying Micro-activities that Compose Complex Human Activities of Daily Living
- Adversarial Resilience in Sequential Prediction via Abstention
- An overview on the evaluated video retrieval tasks at TRECVID 2022
- A Machine Learning Pressure Emulator for Hydrogen Embrittlement
- Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective
- Evading Forensic Classifiers with Attribute-Conditioned Adversarial Faces
- PromptIR: Prompting for All-in-One Blind Image Restoration
- A Comparison of Time-based Models for Multimodal Emotion Recognition
- Semi-automated extraction of research topics and trends from NCI funding in radiological sciences from 2000-2020
- Iterative Scale-Up ExpansionIoU and Deep Features Association for Multi-Object Tracking in Sports
- Auditing Predictive Models for Intersectional Biases
- Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs
- Named entity recognition in resumes
- SQ Lower Bounds for Learning Bounded Covariance GMMs
- Deep Metric Learning with Soft Orthogonal Proxies
- Quantum Pufferfish Privacy: A Flexible Privacy Framework for Quantum Systems
- Context-lumpable stochastic bandits
- Data augmentation and refinement for recommender system: A semi-supervised approach using maximum margin matrix factorization
- Analysis of the Cambridge Multiple-Choice Questions Reading Dataset with a Focus on Candidate Response Distribution
- Multi-Task Learning with Loop Specific Attention for CDR Structure Prediction
- Towards Explainable Evaluation Metrics for Machine Translation
- Impacts and Risk of Generative AI Technology on Cyber Defense
- Online Self-Supervised Deep Learning for Intrusion Detection Systems
- Decentralized Online Federated G-Network Learning for Lightweight Intrusion Detection
- Transferable Curricula through Difficulty Conditioned Generators
- AugDMC: Data Augmentation Guided Deep Multiple Clustering
- Toward Automated Detection of Microbleeds with Anatomical Scale Localization: A Complete Clinical Diagnosis Support Using Deep Learning
- Apolitical Intelligence? Auditing Delphi's responses on controversial political issues in the US
- Affine Correspondences between Multi-Camera Systems for Relative Pose Estimation
- Minimalist and High-Quality Panoramic Imaging with PSF-aware Transformers
- Speech Emotion Diarization: Which Emotion Appears When?
- Can a single image processing algorithm work equally well across all phases of DCE-MRI?
- Inferring the finest pattern of mutual independence from data
- Conversation Derailment Forecasting with Graph Convolutional Networks
- Achieving Sample and Computational Efficient Reinforcement Learning by Action Space Reduction via Grouping
- Sum-Rate Maximization of RSMA-based Aerial Communications with Energy Harvesting: A Reinforcement Learning Approach
- Adaptive Bernstein Change Detector for High-Dimensional Data Streams
- PyKoopman: A Python Package for Data-Driven Approximation of the Koopman Operator
- Siamese SIREN: Audio Compression with Implicit Neural Representations
- Triggering Dark Showers with Conditional Dual Auto-Encoders
- Public Attitudes Toward ChatGPT on Twitter: Sentiments, Topics, and Occupations
- On the use of the Gram matrix for multivariate functional principal components analysis
- Evolving Computation Graphs
- Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models
- Feature Mixing for Writer Retrieval and Identification on Papyri Fragments
- Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing
- Decentralized Multi-Agent Reinforcement Learning with Global State Prediction
- AudioPaLM: A Large Language Model That Can Speak and Listen
- An Interactive Interface for Novel Class Discovery in Tabular Data
- Cross-lingual Cross-temporal Summarization: Dataset, Models, Evaluation
- Multi-Objective Hull Form Optimization with CAD Engine-based Deep Learning Physics for 3D Flow Prediction
- Implicit spoken language diarization
- Mitigating Discrimination in Insurance with Wasserstein Barycenters
- xSIM++: An Improved Proxy to Bitext Mining Performance for Low-Resource Languages
- In Situ Framework for Coupling Simulation and Machine Learning with Application to CFD
All 174
- Machine-Learning-Assisted and Real-Time-Feedback-Controlled Growth of InAs/GaAs Quantum Dots
- Unveiling Global Narratives: A Multilingual Twitter Dataset of News Media on the Russo-Ukrainian Conflict
- Data-Free Backbone Fine-Tuning for Pruned Neural Networks
- FuXi: A cascade machine learning forecasting system for 15-day global weather forecast
- Wind Noise Reduction with a Diffusion-based Stochastic Regeneration Model
- Learning from Visual Observation via Offline Pretrained State-to-Go Transformer
- Reinforcement Federated Learning Method Based on Adaptive OPTICS Clustering
- Efficient Partitioning Method of Large-Scale Public Safety Spatio-Temporal Data based on Information Loss Constraints
- Don't Treat the Symptom, Find the Cause! Efficient Artificial-Intelligence Methods for (Interactive) Debugging
- Natural Language Processing in Electronic Health Records in Relation to Healthcare Decision-making: A Systematic Review
- MultiTASC: A Multi-Tenancy-Aware Scheduler for Cascaded DNN Inference at the Consumer Edge
- StrainTensorNet: Predicting crystal structure elastic properties using SE(3)-equivariant graph neural networks
- XAI-TRIS: Non-linear image benchmarks to quantify false positive post-hoc attribution of feature importance
- Conditional Generators for Limit Order Book Environments: Explainability, Challenges, and Robustness
- Robust Statistical Comparison of Random Variables with Locally Varying Scale of Measurement
- Otter-Knowledge: benchmarks of multimodal knowledge graph representation learning from different sources for drug discovery
- HypeRS: Building a Hypergraph-driven ensemble Recommender System
- Super-Resolution of BVOC Emission Maps Via Domain Adaptation
- Learning Unseen Modality Interaction
- Overview of Robust and Multilingual Automatic Evaluation Metrics for Open-Domain Dialogue Systems at DSTC 11 Track 4
- MFCCGAN: A Novel MFCC-Based Speech Synthesizer Using Adversarial Learning
- Pure Exploration in Bandits with Linear Constraints
- 3D Reconstruction of Spherical Images based on Incremental Structure from Motion
- Concept-aware clustering for decentralized deep learning under temporal shift
- Mapping and Cleaning Open Commonsense Knowledge Bases with Generative Translation
- Blended-NeRF: Zero-Shot Object Generation and Blending in Existing Neural Radiance Fields
- Restoration of the JPEG Maximum Lossy Compressed Face Images with Hourglass Block based on Early Stopping Discriminator
- On the Robustness of Generative Retrieval Models: An Out-of-Distribution Perspective
- Don't be so Monotone: Relaxing Stochastic Line Search in Over-Parameterized Models
- To Spike or Not to Spike? A Quantitative Comparison of SNN and CNN FPGA Implementations
- Ladder Fine-tuning approach for SAM integrating complementary network
- MP3: Movement Primitive-Based (Re-)Planning Policy
- On Exploring Node-feature and Graph-structure Diversities for Node Drop Graph Pooling
- Generative Multimodal Entity Linking
- Natural Language Generation for Advertising: A Survey
- Toward Leveraging Pre-Trained Self-Supervised Frontends for Automatic Singing Voice Understanding Tasks: Three Case Studies
- OptIForest: Optimal Isolation Forest for Anomaly Detection
- Accelerated Training via Incrementally Growing Neural Networks using Variance Transfer and Learning Rate Adaptation
- Multilingual Neural Machine Translation System for Indic to Indic Languages
- Slimmable Encoders for Flexible Split DNNs in Bandwidth and Resource Constrained IoT Systems
- Vec2Vec: A Compact Neural Network Approach for Transforming Text Embeddings with High Fidelity
- Towards quantum enhanced adversarial robustness in machine learning
- Explainable Representations for Relation Prediction in Knowledge Graphs
- FlowFace++: Explicit Semantic Flow-supervised End-to-End Face Swapping
- Rethinking the Backward Propagation for Adversarial Transferability
- One at a Time: Progressive Multi-step Volumetric Probability Learning for Reliable 3D Scene Perception
- Recent Developments in Recommender Systems: A Survey
- Constructing Colloquial Dataset for Persian Sentiment Analysis of Social Microblogs
- Outlier-robust Estimation of a Sparse Linear Model Using Invexity
- SoftGPT: Learn Goal-oriented Soft Object Manipulation Skills by Generative Pre-trained Heterogeneous Graph Transformer
- Memristive Reservoirs Learn to Learn
- Identifying and Disentangling Spurious Features in Pretrained Image Representations
- Generalized Low-Rank Update: Model Parameter Bounds for Low-Rank Training Data Modifications
- Instruct-FinGPT: Financial Sentiment Analysis by Instruction Tuning of General-Purpose Large Language Models
- Fitted value iteration methods for bicausal optimal transport
- Identifying and Extracting Rare Disease Phenotypes with Large Language Models
- Novelty Accommodating Multi-Agent Planning in High Fidelity Simulated Open World
- UltraGlove: Hand Pose Estimation with Mems-Ultrasonic Sensors
- Curriculum Knowledge Switching for Pancreas Segmentation
- Learnability and Algorithm for Continual Learning
- FLAG: Finding Line Anomalies (in code) with Generative AI
- TaCA: Upgrading Your Visual Foundation Model with Task-agnostic Compatible Adapter
- On Addressing the Limitations of Graph Neural Networks
- Efficient quantum image representation and compression circuit using zero-discarded state preparation approach
- Targeted collapse regularized autoencoder for anomaly detection: black hole at the center
- 1st Place Solution to MultiEarth 2023 Challenge on Multimodal SAR-to-EO Image Translation
- Adaptive Compression in Federated Learning via Side Information
- DreamEdit: Subject-driven Image Editing
- SEAL: Simultaneous Exploration and Localization in Multi-Robot Systems
- RXFOOD: Plug-in RGB-X Fusion for Object of Interest Detection
- Class-Incremental Learning based on Label Generation
- RobustNeuralNetworks.jl: a Package for Machine Learning and Data-Driven Control with Certified Robustness
- Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial Patches
- Towards Regulatable AI Systems: Technical Gaps and Policy Opportunities