Papers

New on arXiv

Sat 16 Mar 2024

144 papers

GazeFusion: Saliency-Guided Image GenerationDiffusion models → Video generation
Reward Guided Latent Consistency DistillationDiffusion models → Diffusion foundations and sampling +1
OMG: Occlusion-friendly Personalized Multi-concept Generation in Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
Dreaming of Many Worlds: Learning Contextual World Models Aids Zero-Shot GeneralizationWorld models → Latent dynamics models and model-based RL
Ctrl123: Consistent Novel View Synthesis via Closed-Loop TranscriptionDiffusion models → 3D, point cloud and scene generation
The Fallacy of Minimizing Cumulative Regret in the Sequential Task SettingDeep reinforcement learning methods → RL theory and sample complexity
ViSaRL: Visual Reinforcement Learning Guided by Human SaliencyDeep reinforcement learning methods → RL for robot locomotion and manipulation
Efficient Diffusion-Driven Corruption Editor for Test-Time AdaptationDiffusion models → Diffusion foundations and sampling
BEnQA: A Question Answering and Reasoning Benchmark for Bengali and EnglishLLM reasoning → Reasoning benchmarks and evaluation
A Watermark-Conditioned Diffusion Model for IP ProtectionDiffusion models → Robustness, privacy and adversarial aspects +1
Improving Adversarial Transferability of Vision-Language Pre-training Models through Collaborative Multimodal InteractionMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
Probabilistic World Modeling with Asymmetric Distance MeasureWorld models → Latent predictive world models
stMCDI: Masked Conditional Diffusion Model with Graph Neural Network for Spatial Transcriptomics Data ImputationDiffusion models → Medical imaging and segmentation
Neural-Kernel Conditional Mean EmbeddingsDeep reinforcement learning methods → RL theory and sample complexity
Reinforcement Learning with Options and State RepresentationDeep reinforcement learning methods → Deep RL algorithms and representations
A Comprehensive Study of Multimodal Large Language Models for Image Quality AssessmentMultimodal LLMs / vision-language models → Image editing and quality assessment
GAgent: An Adaptive Rigid-Soft Gripping Agent with Vision Language Models for Complex Lighting EnvironmentsLLM agents and tool use → Multimodal and embodied agents
Deep Reinforcement Learning-based Large-scale Robot ExplorationDeep reinforcement learning methods → RL for robot navigation and UAV control
MicroDiffusion: Implicit Representation-Guided Diffusion for 3D Reconstruction from Limited 2D Microscopy ProjectionsDiffusion models → Inverse problems and image restoration
Efficient Trajectory Forecasting and Generation with Conditional Flow MatchingDiffusion models → Diffusion and flow policies for robotics
FlyKD: Graph Knowledge Distillation on the Fly with Curriculum LearningKnowledge distillation → Graph neural network distillation
Object Retrieval for Visual Question Answering with Outside KnowledgeRetrieval-augmented generation → Multimodal RAG
ContourDiff: Unpaired Medical Image Translation with Structural ConsistencyDiffusion models → Medical imaging and segmentation
StableGarment: Garment-Centric Generation via Stable DiffusionDiffusion models → 3D, point cloud and scene generation
A Probabilistic Approach for Model Alignment with Human ComparisonsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Scheduling Drone and Mobile Charger via Hybrid-Action Deep Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
Feature Aggregation with Latent Generative Replay for Federated Continual Learning of Socially Appropriate Robot Behaviours
Exploring the Independent Cascade Model and Its Evolution in Social Network Information Diffusion
Early-stage detection of cognitive impairment by hybrid quantum-classical algorithm using resting-state functional MRI time-series
Empirical Studies of Parameter Efficient Methods for Large Language Models of Code and Knowledge Transfer to R
DG-RePlAce: A Dataflow-Driven GPU-Accelerated Analytical Global Placement Framework for Machine Learning Accelerators
Optimizing Performance on Trinity Utilizing Machine Learning, Proxy Applications and Scheduling Priorities
Linguistics from a topological viewpoint
Federated Learning based on Pruning and Recovery
Integrating Wearable Sensor Data and Self-reported Diaries for Personalized Affect Forecasting
Speedrunning and path integrals
Deep Generative Design for Mass Production
Advancing multivariate time series similarity assessment: an integrated computational approach
FAGH: Accelerating Federated Learning with Approximated Global Hessian
Texture Edge detection by Patch consensus (TEP)
Multiplane Quantitative Phase Imaging Using a Wavelength-Multiplexed Diffractive Optical Processor
FH-TabNet: Multi-Class Familial Hypercholesterolemia Detection via a Multi-Stage Tabular Deep Learning
EfficientMorph: Parameter-Efficient Transformer-Based Architecture for 3D Image Registration
Pre-Trained Language Models Represent Some Geographic Populations Better Than Others
Fast Sparse View Guided NeRF Update for Object Reconfigurations
Towards Neuro-Symbolic Video Understanding
Accelerating prototype selection with spatial abstraction
Identifying the Attractors of Gene Regulatory Networks from Expression Data under Uncertainty: An Interpretable Approach
Improved Algorithm and Bounds for Successive Projection
DIALECTBENCH: A NLP Benchmark for Dialects, Varieties, and Closely-Related Languages
MASSM: An End-to-End Deep Learning Framework for Multi-Anatomy Statistical Shape Modeling Directly From Images
Forward Learning of Graph Neural Networks
Topologically Faithful Multi-class Segmentation in Medical Images
N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields
Mixed-Reality Digital Twins: Leveraging the Physical and Virtual Worlds for Hybrid Sim2Real Transition of Multi-Agent Reinforcement Learning Policies
Edge Private Graph Neural Networks with Singular Value Perturbation
Boosting Flow-based Generative Super-Resolution Models via Learned Prior
IoTCO2: Assessing the End-To-End Carbon Footprint of Internet-of-Things-Enabled Deep Learning
Automatic Spatial Calibration of Near-Field MIMO Radar With Respect to Optical Depth Sensors
Lambda: Learning Matchable Prior For Entity Alignment with Unlabeled Dangling Cases
Task-Aware Low-Rank Adaptation of Segment Anything Model
Enhancing IoT Security Against DDoS Attacks through Federated Learning
Pointer-Generator Networks for Low-Resource Machine Translation: Don't Copy That!
Exploiting Topological Priors for Boosting Point Cloud Generation
Energy-Based Models with Applications to Speech and Language Processing
SelfIE: Self-Interpretation of Large Language Model Embeddings
Human Centered AI for Indian Legal Text Analytics
MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations
ScanTalk: 3D Talking Heads from Unregistered Scans
Initial Decoding with Minimally Augmented Language Model for Improved Lattice Rescoring in Low Resource ASR
Channel-wise Feature Decorrelation for Enhanced Learned Image Compression
Understanding Robustness of Visual State Space Models for Image Classification
Towards Collective Intelligence: Uncertainty-aware SAM Adaptation for Ambiguous Medical Image Segmentation
Inducing Individual Students' Learning Strategies through Homomorphic POMDPs
Function-space Parameterization of Neural Networks for Sequential Learning
Distributed Multi-Objective Dynamic Offloading Scheduling for Air-Ground Cooperative MEC
Learning Dual-Level Deformable Implicit Representation for Real-World Scale Arbitrary Super-Resolution
Interpretable Machine Learning for TabPFN
FishNet: Deep Neural Networks for Low-Cost Fish Stock Estimation
Automatic location detection based on deep learning
Graph Regularized NMF with L20-norm for Unsupervised Feature Learning
ARC-NeRF: Area Ray Casting for Broader Unseen View Coverage in Few-shot Object Rendering
Urban Sound Propagation: a Benchmark for 1-Step Generative Modeling of Complex Physical Systems
DTOR: Decision Tree Outlier Regressor to explain anomalies
Rethinking Multi-view Representation Learning via Distilled Disentangling
Towards Robustness and Diversity: Continual Learning in Dialog Generation with Text-Mixup and Batch Nuclear-Norm Maximization
List Sample Compression and Uniform Convergence
LuoJiaHOG: A Hierarchy Oriented Geo-aware Image Caption Dataset for Remote Sensing Image-Text Retrival
Could We Generate Cytology Images from Histopathology Images? An Empirical Study
Fuzzy Rank-based Late Fusion Technique for Cytology image Segmentation
Optimizing Language Augmentation for Multilingual Large Language Models: A Case Study on Korean
Regularizing CNNs using Confusion Penalty Based Label Smoothing for Histopathology Images
COVID-CT-H-UNet: a novel COVID-19 CT segmentation network based on attention mechanism and Bi-category Hybrid loss
FedQNN: Federated Learning using Quantum Neural Networks
Sim2Real within 5 Minutes: Efficient Domain Transfer with Stylized Gaussian Splatting for Endoscopic Images
RetMIL: Retentive Multiple Instance Learning for Histopathological Whole Slide Image Classification
Zero-shot Generative Linguistic Steganography
GenOL: Generating Diverse Examples for Name-only Online Learning
RetinaQA: A Robust Knowledge Base Question Answering Model for both Answerable and Unanswerable Questions
Twin Transformer using Gated Dynamic Learnable Attention mechanism for Fault Detection and Diagnosis in the Tennessee Eastman Process

All 144