Papers
Sun 10 Dec 2023
156 papers
- Separate-and-Enhance: Compositional Finetuning for Text2Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
- Class-Prototype Conditional Diffusion Model with Gradient Projection for Continual LearningDiffusion models → Robustness, privacy and adversarial aspects
- Neutral Editing Framework for Diffusion-based Video EditingDiffusion models → Video generation
- Correcting Diffusion Generation through ResamplingDiffusion models → Diffusion foundations and sampling
- Thinking Assistants: LLM-Based Conversational Assistants that Help Users Think By Asking rather than AnsweringLLM reasoning → Reasoning benchmarks and evaluation
- A Note on the Convergence of Denoising Diffusion Probabilistic ModelsDiffusion models → Diffusion foundations and sampling
- NovaCOMET: Open Commonsense Foundation Models with Symbolic Knowledge DistillationKnowledge distillation → Knowledge distillation for LLMs
- Language-Conditioned Semantic Search-Based Policy for Robotic Manipulation TasksOffline RL and imitation learning from data → Language-conditioned policies and VLAs
- A Video is Worth 256 Bases: Spatial-Temporal Expectation-Maximization Inversion for Zero-Shot Video EditingDiffusion models → Video generation
- InteractDiffusion: Interaction Control in Text-to-Image Diffusion ModelsDiffusion models → Video generation
- ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language ModelsEfficient LLM inference and serving → Early exit and edge inference
- Layered 3D Human Generation via Semantic-Aware Diffusion ModelDiffusion models → 3D, point cloud and scene generation
- Large Multimodal Model Compression via Efficient Pruning and Distillation at AntGroupMultimodal LLMs / vision-language models → Visual token pruning and efficiency
- Graph-based Prediction and Planning Policy Network (GP3Net) for scalable self-driving in dynamic environments using Deep Reinforcement LearningEnd-to-end autonomous driving → Imitation-learning end-to-end planners
- AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion ModelDiffusion models → Flow matching, time series and science
- The Generalization Gap in Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Micro-Macro Consistency in Multiscale Modeling: Score-Based Model Assisted Sampling of Fast/Slow Dynamical SystemsDiffusion models → Diffusion foundations and sampling
- Synergizing Quality-Diversity with Descriptor-Conditioned Reinforcement Learning
- Consciousness as a logically consistent and prognostic model of reality
- Informational non-reductionist theory of consciousness that providing maximum accuracy of reality prediction
- The performance of multiple language models in identifying offensive language on social media
- Speech and Text-Based Emotion Recognizer
- No prejudice! Fair Federated Graph Neural Networks for Personalized Recommendation
- Music Recommendation on Spotify using Deep Learning
- Early ChatGPT User Portrait through the Lens of Data
- I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions
- Singular Value Penalization and Semantic Data Augmentation for Fully Test-Time Adaptation
- COVID-19 Detection Using Slices Processing Techniques and a Modified Xception Classifier from Computed Tomography Images
- Cross Fertilizing Empathy from Brain to Machine as a Value Alignment Strategy
- Benchmarking Distribution Shift in Tabular Data with TableShift
- Arabic Handwritten Text Line Dataset
- Investigating YOLO Models Towards Outdoor Obstacle Detection For Visually Impaired People
- TeTriRF: Temporal Tri-Plane Radiance Fields for Efficient Free-Viewpoint Video
- Physics Informed Neural Network for Option Pricing
- AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One
- UNeR3D: Versatile and Scalable 3D RGB Point Cloud Generation from 2D Images in Unsupervised Reconstruction
- Perceiving University Student's Opinions from Google App Reviews
- SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction
- OpenSD: Unified Open-Vocabulary Segmentation and Detection
- Dynamic Adversarial Attacks on Autonomous Driving Systems
- Leveraging Generative Language Models for Weakly Supervised Sentence Component Analysis in Video-Language Joint Learning
- Multimodality of AI for Education: Towards Artificial General Intelligence
- Towards impactful challenges: post-challenge paper, benchmarks and other dissemination actions
- Modeling Uncertainty in Personalized Emotion Prediction with Normalizing Flows
- Evaluating the Utility of Model Explanations for Model Development
- Fast Classification of Large Time Series Datasets
- Stress Management Using Virtual Reality-Based Attention Training
- Exploiting Representation Bias for Data Distillation in Abstractive Text Summarization
- GenDepth: Generalizing Monocular Depth Estimation for Arbitrary Camera Parameters via Ground Plane Embedding
- Speeding up astrochemical reaction networks with autoencoders and neural ODEs
- Guardians of Trust: Navigating Data Security in AIOps through Vendor Partnerships
- Large Language Models on Lexical Semantic Change Detection: An Evaluation
- From Correspondences to Pose: Non-minimal Certifiably Optimal Relative Pose without Disambiguation
- FastPart: Over-Parameterized Stochastic Gradient Descent for Sparse optimisation on Measures
- Modifying RL Policies with Imagined Actions: How Predictable Policies Can Enable Users to Perform Novel Tasks
- Constructing Vec-tionaries to Extract Message Features from Texts: A Case Study of Moral Appeals
- Reconstruction of Cortical Surfaces with Spherical Topology from Infant Brain MRI via Recurrent Deformation Learning
- Fused Extended Two-Way Fixed Effects for Difference-in-Differences With Staggered Adoptions
- Accurate Differential Operators for Hybrid Neural Fields
- Maximum flow-based formulation for the optimal location of electric vehicle charging stations
- Neural Architecture Codesign for Fast Bragg Peak Analysis
- A Representative Study on Human Detection of Artificially Generated Media Across Countries
- FM-G-CAM: A Holistic Approach for Explainable AI in Computer Vision
- Learning the Causal Structure of Networked Dynamical Systems under Latent Nodes and Structured Noise
- Activating Frequency and ViT for 3D Point Cloud Quality Assessment without Reference
- Jumpstarting Surgical Computer Vision
- Fake It Till Make It: Federated Learning with Consensus-Oriented Generation
- ConSequence: Synthesizing Logically Constrained Sequences for Electronic Health Record Generation
- Aikyam: A Video Conferencing Utility for Deaf and Dumb
- TransGlow: Attention-augmented Transduction model based on Graph Neural Networks for Water Flow Forecasting
- VAE-IF: Deep feature extraction with averaging for fully unsupervised artifact detection in routinely acquired ICU time-series
- Learning Differentiable Particle Filter on the Fly
- RadImageGAN -- A Multi-modal Dataset-Scale Generative AI for Medical Imaging
- Uncertainty Propagation through Trained Deep Neural Networks Using Factor Graphs
- ASH: Animatable Gaussian Splats for Efficient and Photoreal Human Rendering
- Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs
- Temporal Supervised Contrastive Learning for Modeling Patient Risk Progression
- A Comprehensive Dataset and Automated Pipeline for Nailfold Capillary Analysis
- AesFA: An Aesthetic Feature-Aware Arbitrary Neural Style Transfer
- Data-Free Hard-Label Robustness Stealing Attack
- Weakly Supervised Video Individual CountingWeakly Supervised Video Individual Counting
- Dig-CSI: A Distributed and Generative Model Assisted CSI Feedback Training Framework
- Diffusion for Natural Image Matting
- Ensemble Kalman Filtering Meets Gaussian Process SSM for Non-Mean-Field and Online Inference
- Multi-Energy Guided Image Translation with Stochastic Differential Equations for Near-Infrared Facial Expression Recognition
- Hypergraph-Guided Disentangled Spectrum Transformer Networks for Near-Infrared Facial Expression Recognition
- Improving Subgraph-GNNs via Edge-Level Ego-Network Encodings
- Deep-Learning-Assisted Analysis of Cataract Surgery Videos
- PSCR: Patches Sampling-based Contrastive Regression for AIGC Image Quality Assessment
- A conservative hybrid physics-informed neural network method for Maxwell-Amp`ere-Nernst-Planck equations
- Scaling #DNN-Verification Tools with Efficient Bound Propagation and Parallel Computing
- SuperPrimitive: Scene Reconstruction at a Primitive Level
- Three-dimensional numerical schemes for the segmentation of the psoas muscle in X-ray computed tomography images
- Adaptive Parameter Selection for Kernel Ridge Regression
- Using deep neural networks to improve the precision of fast-sampled particle timing detectors
- Data-driven optimal stopping: A pure exploration analysis
- Wild Motion Unleashed: Markerless 3D Kinematics and Force Estimation in Cheetahs
- Skew-Probabilistic Neural Networks for Learning from Imbalanced Data
- Proceedings of the 2023 XCSP3 Competition
- Class-Aware Pruning for Efficient Neural Networks
All 156
- Learning for CasADi: Data-driven Models in Numerical Optimization
- TaBIIC: Taxonomy Building through Iterative and Interactive Clustering
- Finding Concept Representations in Neural Networks with Self-Organizing Maps
- NeVRF: Neural Video-based Radiance Fields for Long-duration Sequences
- Composite Survival Analysis: Learning with Auxiliary Aggregated Baselines and Survival Scores
- Mutual Enhancement of Large and Small Language Models with Cross-Silo Knowledge Transfer
- Topological Data Analysis for Neural Network Analysis: A Comprehensive Survey
- Evidence-based Interpretable Open-domain Fact-checking with Large Language Models
- Spatial-wise Dynamic Distillation for MLP-like Efficient Visual Fault Detection of Freight Trains
- Physics-Aware Multifidelity Bayesian Optimization: a Generalized Formulation
- A Decoupled Spatio-Temporal Framework for Skeleton-based Action Segmentation
- Sparse Multitask Learning for Efficient Neural Representation of Motor Imagery and Execution
- Detecting Toxic Flow
- R2Human: Real-Time 3D Human Appearance Rendering from a Single Image
- Toward Open-ended Embodied Tasks Solving
- ICTSurF: Implicit Continuous-Time Survival Functions with Neural Networks
- Neural Speech Embeddings for Speech Synthesis Based on Deep Generative Networks
- Federated Learning Empowered by Generative Content
- Transformer-based Selective Super-Resolution for Efficient Image Refinement
- SGNet: Structure Guided Network via Gradient-Frequency Awareness for Depth Map Super-Resolution
- Disentangled Representation Learning for Controllable Person Image Generation
- Multimodality in Online Education: A Comparative Study
- Spectral Statistics of the Sample Covariance Matrix for High Dimensional Linear Gaussians
- Statistical Spatially Inhomogeneous Diffusion Inference
- Take an Irregular Route: Enhance the Decoder of Time-Series Forecasting Transformer
- SimPSI: A Simple Strategy to Preserve Spectral Information in Time Series Data Augmentation
- Efficient Sparse-Reward Goal-Conditioned Reinforcement Learning with a High Replay Ratio and Regularization
- DCIR: Dynamic Consistency Intrinsic Reward for Multi-Agent Reinforcement Learning
- PULSAR: Graph based Positive Unlabeled Learning with Multi Stream Adaptive Convolutions for Parkinson's Disease Recognition
- Negative Pre-aware for Noisy Cross-modal Matching
- Hacking Task Confounder in Meta-Learning
- Multi-Defendant Legal Judgment Prediction via Hierarchical Reasoning
- QMGeo: Differentially Private Federated Learning via Stochastic Quantization with Mixed Truncated Geometric Distribution
- RepViT-SAM: Towards Real-Time Segmenting Anything
- Beyond One Model Fits All: Ensemble Deep Learning for Autonomous Vehicles
- CLeaRForecast: Contrastive Learning of High-Purity Representations for Time Series Forecasting
- Towards Human-like Perception: Learning Structural Causal Model in Heterogeneous Graph
- A quantitative fusion strategy of stock picking and timing based on Particle Swarm Optimized-Back Propagation Neural Network and Multivariate Gaussian-Hidden Markov Model
- Camera-based 3D Semantic Scene Completion with Sparse Guidance Network
- Benchmarking of Query Strategies: Towards Future Deep Active Learning
- IL-NeRF: Incremental Learning for Neural Radiance Fields with Camera Pose Alignment
- Difference of Probability and Information Entropy for Skills Classification and Prediction in Student Learning
- Open World Object Detection in the Era of Foundation Models
- Building Variable-sized Models via Learngene Pool
- MISCA: A Joint Model for Multiple Intent Detection and Slot Filling with Intent-Slot Co-Attention
- GAMC: An Unsupervised Method for Fake News Detection using Graph Autoencoder with Masking
- FedReverse: Multiparty Reversible Deep Neural Network Watermarking
- ASWT-SGNN: Adaptive Spectral Wavelet Transform-based Self-Supervised Graph Neural Network
- A Comprehensive Survey on Multi-modal Conversational Emotion Recognition with Deep Learning
- DevBots can co-design APIs
- FP8-BERT: Post-Training Quantization for Transformer
- Learning Spatially-Continuous Fiber Orientation Functions
- Beyond Gradient and Priors in Privacy Attacks: Leveraging Pooler Layer Inputs of Language Models in Federated Learning
- DVANet: Disentangling View and Action Features for Multi-View Action Recognition
- Forecasting Lithium-Ion Battery Longevity with Limited Data Availability: Benchmarking Different Machine Learning Algorithms
- Initialization Matters for Adversarial Transfer Learning