Papers
Tue 20 Jun 2023
232 papers
- Knowledge Distillation via Token-level Relationship GraphKnowledge distillation → General knowledge distillation methods
- LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph MatchingMultimodal LLMs / vision-language models → Medical vision-language models
- Exploring the Effectiveness of Dataset Synthesis: An application of Apple Detection in OrchardsDiffusion models → Image generation, text-to-image and editing
- Learning Profitable NFT Image Diffusions via Multiple Visual-Policy Guided Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics
- Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct SupervisionDiffusion models → Diffusion foundations and sampling
- RoboCat: A Self-Improving Generalist Agent for Robotic ManipulationLLM agents and tool use → Multimodal and embodied agents +1
- Harnessing the Power of Adversarial Prompting and Large Language Models for Robust Hypothesis Generation in AstronomyLLM safety and security → Safety alignment, refusal and guardrails
- Improving visual image reconstruction from human brain activity using latent diffusion models via multiple decoded inputsDiffusion models → Medical imaging and segmentation
- Align, Adapt and Inject: Sound-guided Unified Image GenerationDiffusion models → Audio, speech and music
- EMoG: Synthesizing Emotive Co-speech 3D Gesture with Diffusion ModelDiffusion models → Audio, speech and music
- Informed POMDP: Leveraging Additional Information in Model-Based RLWorld models → Latent dynamics models and model-based RL
- Comprehensive Training and Evaluation on Deep Reinforcement Learning for Automated Driving in Various Simulated Driving ManeuversEnd-to-end autonomous driving → Reinforcement learning for driving
- Safe, Efficient, Comfort, and Energy-saving Automated Driving through Roundabout Based on Deep Reinforcement LearningEnd-to-end autonomous driving → Reinforcement learning for driving
- MuDPT: Multi-modal Deep-symphysis Prompt Tuning for Large Pre-trained Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- CrossKD: Cross-Head Knowledge Distillation for Object DetectionKnowledge distillation → Detection and dense prediction distillation
- Masked Diffusion Models Are Fast Distribution LearnersDiffusion models → Diffusion foundations and sampling
- Surfer: Progressive Reasoning with World Models for Robotic ManipulationWorld models → Embodied and robot world models
- RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote SensingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
- Lipschitz Singularities in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Autonomous Driving with Deep Reinforcement Learning in CARLA SimulationEnd-to-end autonomous driving → Reinforcement learning for driving
- An empirical study of using radiology reports and images to improve ICU mortality prediction
- Towards Environmentally Equitable AI via Geographical Load Balancing
- Food Recognition and Nutritional Apps
- Guideline for Trustworthy Artificial Intelligence -- AI Assessment Catalog
- HIDFlowNet: A Flow-Based Deep Network for Hyperspectral Image Denoising
- State space models can express n-gram languages
- Clustering-based Identification of Precursors of Extreme Events in Chaotic Systems
- Uncertainty Estimation for Molecules: Desiderata and Methods
- A GPT-4 Reticular Chemist for Guiding MOF Discovery
- Modern Constraint Programming Education: Lessons for the Future
- Intersectionality and Testimonial Injustice in Medical Records
- Diverse Community Data for Benchmarking Data Privacy Algorithms
- EEG Decoding for Datasets with Heterogenous Electrode Configurations using Transfer Learning Graph Neural Networks
- Comparing Deep Learning Models for the Task of Volatility Prediction Using Multivariate Data
- Factors Affecting the Performance of Automated Speaker Verification in Alzheimer's Disease Clinical Trials
- DEPAC: a Corpus for Depression and Anxiety Detection from Speech
- Winter Wheat Crop Yield Prediction on Multiple Heterogeneous Datasets using Machine Learning
- Towards Understanding What Code Language Models Learned
- A Deep Learning Model for Heterogeneous Dataset Analysis -- Application to Winter Wheat Crop Yield Prediction
- Efficient Dynamics Modeling in Interactive Environments with Koopman Theory
- Opportunities and Risks of LLMs for Scalable Deliberation with Polis
- Open Problem: Learning with Variational Objectives on Measures
- No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths
- NILUT: Conditional Neural Implicit 3D Lookup Tables for Image Enhancement
- Adaptive Ensemble Q-learning: Minimizing Estimation Bias via Error Feedback
- Structure-Aware Robustness Certificates for Graph Classification
- Randomized Quantization is All You Need for Differential Privacy in Federated Learning
- Copula-Based Deep Survival Models for Dependent Censoring
- LNL+K: Enhancing Learning with Noisy Labels Through Noise Source Knowledge Integration
- Generalized Random Forests using Fixed-Point Trees
- Deep Fusion: Efficient Network Training via Pre-trained Initializations
- Evaluation of Chinese-English Machine Translation of Emotion-Loaded Microblog Texts: A Human Annotated Dataset for the Quality Assessment of Emotion Translation
- Closing the loop: Autonomous experiments enabled by machine-learning-based online data analysis in synchrotron beamline environments
- Relating tSNE and UMAP to Classical Dimensionality Reduction
- Reinforcement Learning-based Virtual Fixtures for Teleoperation of Hydraulic Construction Machine
- Learning Elastic Costs to Shape Monge Displacements
- Exploring New Frontiers in Agricultural NLP: Investigating the Potential of Large Language Models for Food Applications
- SPRINT: Scalable Policy Pre-Training via Language Instruction Relabeling
- Reward Shaping via Diffusion Process in Reinforcement Learning
- Open-Domain Text Evaluation via Contrastive Distribution Methods
- BMAD: Benchmarks for Medical Anomaly Detection
- Multiverse Transformer: 1st Place Solution for Waymo Open Sim Agents Challenge 2023
- Personalized Federated Learning with Feature Alignment and Classifier Collaboration
- Unsupervised Deep Unfolded PGD for Transmit Power Allocation in Wireless Systems
- Proactive Human-Robot Co-Assembly: Leveraging Human Intention Prediction and Robust Safe Control
- A Model-free Closeness-of-influence Test for Features in Supervised Learning
- Generalization Across Experimental Parameters in Machine Learning Analysis of High Resolution Transmission Electron Microscopy Datasets
- Using super-resolution for enhancing visual perception and segmentation performance in veterinary cytology
- Decoding Urban-health Nexus: Interpretable Machine Learning Illuminates Cancer Prevalence based on Intertwined City Features
- Discovering Causality for Efficient Cooperation in Multi-Agent Environments
- Retrieval-Based Transformer for Table Augmentation
- Should I Stop or Should I Go: Early Stopping with Heterogeneous Populations
- Efficient Machine Translation Corpus Generation
- Brain Anatomy Prior Modeling to Forecast Clinical Progression of Cognitive Impairment with Structural MRI
- Topological Parallax: A Geometric Specification for Deep Perception Models
- QuOTeS: Query-Oriented Technical Summarization
- UMM: Unsupervised Mean-difference Maximization
- Any Deep ReLU Network is Shallow
- DiNADO: Norm-Disentangled Neurally-Decomposed Oracles for Controlling Language Models
- EvolveMT: an Ensemble MT Engine Improving Itself with Usage Only
- Self-supervised Multi-task Learning Framework for Safety and Health-Oriented Connected Driving Environment Perception using Onboard Camera
- Learning to Generate Better Than Your LLM
- Inshrinkerator: Compressing Deep Learning Training Checkpoints via Dynamic Quantization
- Towards a robust and reliable deep learning approach for detection of compact binary mergers in gravitational wave data
- Time-Varying Transition Matrices with Multi-task Gaussian Processes
- Designing Explainable Predictive Machine Learning Artifacts: Methodology and Practical Demonstration
- Geometric Deep Learning for Structure-Based Drug Design: A Survey
- A Graphical Modeling Language for Artificial Intelligence Applications in Automation Systems
- About some compression algorithms
- On Frequency-Wise Normalizations for Better Recording Device Generalization in Audio Spectrogram Transformers
- MultiEarth 2023 Deforestation Challenge -- Team FOREVER
- Learning and evolution: factors influencing an effective combination
- Deep Learning Accelerator in Loop Reliability Evaluation for Autonomous Driving
- MRFI: An Open Source Multi-Resolution Fault Injection Framework for Neural Network Processing
- Segment Anything Model (SAM) for Radiation Oncology
- Dense Video Object Captioning from Disjoint Supervision
- How can objects help action recognition?
- Low-complexity Multidimensional DCT Approximations
- Multi-Fidelity Active Learning with GFlowNets
- Meta-Analysis of Transfer Learning for Segmentation of Brain Lesions
All 232
- Data-Driven but Privacy-Conscious: Pedestrian Dataset De-identification via Full-Body Person Synthesis
- Lingua Manga: A Generic Large Language Model Centric System for Data Curation
- Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs
- GenPlot: Increasing the Scale and Diversity of Chart Derendering Data
- DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
- Treatment Effects in Extreme Regimes
- RoTaR: Efficient Row-Based Table Representation Learning via Teacher-Student Training
- A Simple and Effective Pruning Approach for Large Language Models
- Statistical Tests for Replacing Human Decision Makers with Algorithms
- SkyGPT: Probabilistic Short-term Solar Forecasting Using Synthetic Sky Videos from Physics-constrained VideoGPT
- MoleCLUEs: Molecular Conformers Maximally In-Distribution for Predictive Models
- The Implicit Bias of Batch Normalization in Linear Models and Two-layer Linear Convolutional Neural Networks
- GIO: Gradient Information Optimization for Training Dataset Selection
- Principles for Initialization and Architecture Selection in Graph Neural Networks with ReLU Activations
- G-NM: A Group of Numerical Time Series Prediction Models
- Neural Astrophysical Wind Models
- FedNoisy: Federated Noisy Label Learning Benchmark
- Recent Advances in Direct Speech-to-text Translation
- Textbooks Are All You Need
- Collision Avoidance Detour for Multi-Agent Trajectory Forecasting
- SeFNet: Bridging Tabular Datasets with Semantic Feature Nets
- Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity
- Mean-field Analysis of Generalization Errors
- Annotation Cost Efficient Active Learning for Content Based Image Retrieval
- BEVScope: Enhancing Self-Supervised Depth Estimation Leveraging Bird's-Eye-View in Dynamic Scenarios
- Improving Image Captioning Descriptiveness by Ranking and LLM-based Fusion
- Deep Double Self-Expressive Subspace Clustering
- Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent
- Provably Powerful Graph Neural Networks for Directed Multigraphs
- FAIR: A Causal Framework for Accurately Inferring Judgments Reversals
- Computing a human-like reaction time metric from stable recurrent vision models
- Deep Learning Methods for Retinal Blood Vessel Segmentation: Evaluation on Images with Retinopathy of Prematurity
- HomeRobot: Open-Vocabulary Mobile Manipulation
- MILD: Modeling the Instance Learning Dynamics for Learning with Noisy Labels
- The Ecological Fallacy in Annotation: Modelling Human Label Variation goes beyond Sociodemographics
- NeRF synthesis with shading guidance
- Inter-Cell Network Slicing With Transfer Learning Empowered Multi-Agent Deep Reinforcement Learning
- IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL
- Event Stream GPT: A Data Pre-processing and Modeling Library for Generative, Pre-trained Transformers over Continuous-time Sequences of Complex Events
- Bullying10K: A Large-Scale Neuromorphic Dataset towards Privacy-Preserving Bullying Recognition
- Audio-Driven 3D Facial Animation from In-the-Wild Videos
- Evolutionary Strategy Guided Reinforcement Learning via MultiBuffer Communication
- 3D Keypoint Estimation Using Implicit Representation Learning
- TransRef: Multi-Scale Reference Embedding Transformer for Reference-Guided Image Inpainting
- Understanding Contrastive Learning Through the Lens of Margins
- Hallucination is the last thing you need
- One model to rule them all: ranking Slovene summarizers
- Pushing the Limits of 3D Shape Generation at Scale
- Implicit neural representation with physics-informed neural networks for the reconstruction of the early part of room impulse responses
- TrustGPT: A Benchmark for Trustworthy and Responsible Large Language Models
- Conditional Independence Testing with Heteroskedastic Data and Applications to Causal Discovery
- Convergence and concentration properties of constant step-size SGD through Markov chains
- UM-CAM: Uncertainty-weighted Multi-resolution Class Activation Maps for Weakly-supervised Fetal Brain Segmentation
- Give Us the Facts: Enhancing Large Language Models with Knowledge Graphs for Fact-aware Language Modeling
- Efficient Large-scale Nonstationary Spatial Covariance Function Estimation Using Convolutional Neural Networks
- Explicit Syntactic Guidance for Neural Text Generation
- Int-HRL: Towards Intention-based Hierarchical Reinforcement Learning
- Learning Locally Interpretable Rule Ensemble
- CATS: A Pragmatic Chinese Answer-to-Sequence Dataset with Large Scale and High Quality
- Delegated Classification
- A Passivity-Based Method for Accelerated Convex Optimisation
- Timestamped Embedding-Matching Acoustic-to-Word CTC ASR
- Spatio-temporal DeepKriging for Interpolation and Probabilistic Forecasting
- Provably Robust Temporal Difference Learning for Heavy-Tailed Rewards
- Blackbird language matrices (BLM), a new task for rule-like generalization in neural networks: Motivations and Formal Specifications
- UUKG: Unified Urban Knowledge Graph Dataset for Urban Spatiotemporal Prediction
- Graph Neural Stochastic Differential Equations for Learning Brownian Dynamics
- Plausibility-Based Heuristics for Latent Space Classical Planning
- Towards Theory-based Moral AI: Moral AI with Aggregating Models Based on Normative Ethical Theory
- Exploring the Performance and Efficiency of Transformer Models for NLP on Mobile Devices
- On Evaluating Multilingual Compositional Generalization with Translated Datasets
- Computing large deviation prefactors of stochastic dynamical systems based on machine learning
- PyRCA: A Library for Metric-based Root Cause Analysis
- Multi-Scale Occ: 4th Place Solution for CVPR 2023 3D Occupancy Prediction Challenge
- Size Matters: Large Graph Generation with HiGGs
- Stable and Consistent Prediction of 3D Characteristic Orientation via Invariant Residual Learning
- The Cultivated Practices of Text-to-Image Generation
- Did the Models Understand Documents? Benchmarking Models for Language Understanding in Document-Level Relation Extraction
- A Bayesian Take on Gaussian Process Networks
- Multi-task Collaborative Pre-training and Individual-adaptive-tokens Fine-tuning: A Unified Framework for Brain Representation Learning
- HabiCrowd: A High Performance Simulator for Crowd-Aware Visual Navigation
- Top-down machine learning of coarse-grained protein force-fields
- Democratizing LLMs for Low-Resource Languages by Leveraging their English Dominant Abilities with Linguistically-Diverse Prompts
- Visually grounded few-shot word learning in low-resource settings
- RoMe: Towards Large Scale Road Surface Reconstruction via Mesh Representation
- End-to-end 2D-3D Registration between Image and LiDAR Point Cloud for Vehicle Localization
- KiUT: Knowledge-injected U-Transformer for Radiology Report Generation
- Contrastive Disentangled Learning on Graph for Node Classification
- A Universal Unbiased Method for Classification from Aggregate Observations
- Exploring Antitrust and Platform Power in Generative AI
- MSVD-Indonesian: A Benchmark for Multimodal Video-Text Tasks in Indonesian
- Masking meets Supervision: A Strong Learning Alliance
- FDINet: Protecting against DNN Model Extraction via Feature Distortion Index
- Cooperative Multi-Agent Learning for Navigation via Structured State Abstraction
- Depth and DOF Cues Make A Better Defocus Blur Detector
- Low Latency Edge Classification GNN for Particle Trajectory Tracking on FPGAs
- Meerkat Behaviour Recognition Dataset
- Unfolding Framework with Prior of Convolution-Transformer Mixture and Uncertainty Estimation for Video Snapshot Compressive Imaging
- Variational Disentangled Graph Auto-Encoders for Link Prediction
- Deep graph kernel point processes over networks
- Data Structures for Density Estimation
- Multi-pass Training and Cross-information Fusion for Low-resource End-to-end Accented Speech Recognition
- Learning Variable Impedance Skills from Demonstrations with Passivity Guarantee
- Transforming Graphs for Enhanced Attribute Clustering: An Innovative Graph Transformer-Based Method
- Progressive Fourier Neural Representation for Sequential Video Compilation
- Traversing Between Modes in Function Space for Fast Ensembling
- Adversarial Search and Tracking with Multiagent Reinforcement Learning in Sparsely Observable Environment
- Decentralized Quantum Federated Learning for Metaverse: Analysis, Design and Implementation
- ChatGPT Chemistry Assistant for Text Mining and Prediction of MOF Synthesis
- Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigation
- Spatiotemporal Pyramidal CNN with Depth-Wise Separable Convolution for Eye Blinking Detection in the Wild
- Towards Characterizing Domain Counterfactuals For Invertible Latent Causal Models
- Less Can Be More: Exploring Population Rating Dispositions with Partitioned Models in Recommender Systems
- Warm-Start Actor-Critic: From Approximation Error to Sub-optimality Gap
- Evaluating the Zero-shot Robustness of Instruction-tuned Language Models
- GraphGLOW: Universal and Generalizable Structure Learning for Graph Neural Networks
- Comparative Evaluation of Recent Universal Adversarial Perturbations in Image Classification
- A Novel Counterfactual Data Augmentation Method for Aspect-Based Sentiment Analysis
- Deep Learning of Dynamical System Parameters from Return Maps as Images
- GUMSum: Multi-Genre Data and Evaluation for English Abstractive Summarization
- HK-LegiCoST: Leveraging Non-Verbatim Transcripts for Speech Translation
- InRank: Incremental Low-Rank Learning
- OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning
- Dynamic Perceiver for Efficient Visual Recognition
- Deep Reinforcement Learning for Inventory Networks: Toward Reliable Policy Optimization
- CAMP-Net: Consistency-Aware Multi-Prior Network for Accelerated MRI Reconstruction
- Eight challenges in developing theory of intelligence
- Reasoning over the Air: A Reasoning-based Implicit Semantic-Aware Communication Framework
- LoSparse: Structured Compression of Large Language Models based on Low-Rank and Sparse Approximation
- CF-GODE: Continuous-Time Causal Inference for Multi-Agent Dynamical Systems
- The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning
- Quilt-1M: One Million Image-Text Pairs for Histopathology