Papers
Mon 17 Apr 2023
207 papers
- Grounding Classical Task Planners via Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
- Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion ModelDiffusion models → 3D, point cloud and scene generation
- Delving into Shape-aware Zero-shot Semantic SegmentationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Hyper-Decision Transformer for Efficient Online Policy AdaptationOffline RL and imitation learning from data → Decision transformers and sequence modeling
- Towards Robust Prompts on Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Latent-Shift: Latent Diffusion with Temporal Shift for Efficient Text-to-Video GenerationDiffusion models → Video generation
- Synthetic Data from Diffusion Models Improves ImageNet ClassificationDiffusion models → Image generation, text-to-image and editing
- Tool Learning with Foundation ModelsLLM agents and tool use → Tool learning and function calling
- Refusion: Enabling Large-Size Realistic Image Restoration with Latent-Space Diffusion ModelsDiffusion models → Inverse problems and image restoration
- Integration of Reinforcement Learning Based Behavior Planning With Sampling Based Motion Planning for Automated DrivingEnd-to-end autonomous driving → Reinforcement learning for driving
- PaaS: Planning as a Service for reactive driving in CARLA LeaderboardEnd-to-end autonomous driving → End-to-end system architecture
- Learning to "Segment Anything" in Thermal Infrared Images through Knowledge Distillation with a Large Scale Dataset SATIRKnowledge distillation → Detection and dense prediction distillation
- Causal Decision Transformer for Recommender Systems via Offline Reinforcement LearningOffline RL and imitation learning from data → Decision transformers and sequence modeling
- Towards Unified AI Drug Discovery with Multiple Knowledge Modalities
- Learning-based Framework for US Signals Super-resolution
- SRCNet: Seminal Representation Collaborative Network for Marine Oil Spill Segmentation
- HandCT: hands-on computational dataset for X-Ray Computed Tomography and Machine-Learning
- SplitAMC: Split Learning for Robust Automatic Modulation Classification
- Effectiveness of Debiasing Techniques: An Indigenous Qualitative Analysis
- Development of Authenticated Clients and Applications for ICICLE CI Services -- Final Report for the REHS Program, June-August, 2022
- Testing the Reliability of ChatGPT for Text Annotation and Classification: A Cautionary Remark
- Training Automated Defense Strategies Using Graph-based Cyber Attack Simulations
- An Unbiased Transformer Source Code Learning with Semantic Vulnerability Graph
- Autoregressive models for biomedical signal processing
- SkillGPT: a RESTful API service for skill extraction and standardization using a Large Language Model
- Attention-based Part Assembly for 3D Volumetric Shape Modeling
- Quantifying the Benefit of Artificial Intelligence for Scientific Research
- Supporting Qualitative Analysis with Large Language Models: Combining Codebook with GPT-3 for Deductive Coding
- OOD-CV-v2: An extended Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images
- Optimum Output Long Short-Term Memory Cell for High-Frequency Trading Forecasting
- Leveraging Deep Reinforcement Learning for Metacognitive Interventions across Intelligent Tutoring Systems
- What Should Be Balanced in a "Balanced" Face Recognition Dataset?
- K-means Clustering Based Feature Consistency Alignment for Label-free Model Evaluation
- Attributing Image Generative Models using Latent Fingerprints
- Pretrained Language Models as Visual Planners for Human Assistance
- Alzheimers Disease Diagnosis using Machine Learning: A Review
- Enhancing Personalized Ranking With Differentiable Group AUC Optimization
- Memento: Facilitating Effortless, Efficient, and Reliable ML Experiments
- Exploring 360-Degree View of Customers for Lookalike Modeling
- LaSNN: Layer-wise ANN-to-SNN Distillation for Effective and Efficient Training in Deep Spiking Neural Networks
- MDDL: A Framework for Reinforcement Learning-based Position Allocation in Multi-Channel Feed
- Balancing Unobserved Confounding with a Few Unbiased Ratings in Debiased Recommendations
- DRIFT: A Federated Recommender System with Implicit Feedback on the Items
- Always Strengthen Your Strengths: A Drift-Aware Incremental Learning Framework for CTR Prediction
- Insta(nt) Pet Therapy: GAN-generated Images for Therapeutic Social Media Content
- Continuous Versatile Jumping Using Learned Action Residuals
- (LC)2: LiDAR-Camera Loop Constraints For Cross-Modal Place Recognition
- In-situ surface porosity prediction in DED (directed energy deposition) printed SS316L parts using multimodal sensor fusion
- On Uncertainty Calibration and Selective Generation in Probabilistic Neural Summarization: A Benchmark Study
- Classification of US Supreme Court Cases using BERT-Based Techniques
- ProPanDL: A Modular Architecture for Uncertainty-Aware Panoptic Segmentation
- TAP: A Comprehensive Data Repository for Traffic Accident Prediction in Road Networks
- pgmpy: A Python Toolkit for Bayesian Networks
- An Evaluation on Large Language Model Outputs: Discourse and Memorization
- Signal Processing Grand Challenge 2023 -- e-Prevention: Sleep Behavior as an Indicator of Relapses in Psychotic Patients
- Bridging Discrete and Backpropagation: Straight-Through and Beyond
- Crossing Roads of Federated Learning and Smart Grids: Overview, Challenges, and Perspectives
- RS2G: Data-Driven Scene-Graph Extraction and Embedding for Robust Autonomous Perception and Scenario Understanding
- eTOP: Early Termination of Pipelines for Faster Training of AutoML Systems
- AdaMTL: Adaptive Input-dependent Inference for Efficient Multi-Task Learning
- Forecasting with Sparse but Informative Variables: A Case Study in Predicting Blood Glucose
- Fast and Straggler-Tolerant Distributed SGD with Reduced Computation Load
- Researchers eye-view of sarcasm detection in social media textual content
- U2RLE: Uncertainty-Guided 2-Stage Room Layout Estimation
- GrOVe: Ownership Verification of Graph Neural Networks using Embeddings
- CAM2: Conformity-Aware Multi-Task Ranking Model for Large-Scale Recommender Systems
- Stochastic Subgraph Neighborhood Pooling for Subgraph Classification
- Generative Disco: Text-to-Video Generation for Music Visualization
- When SAM Meets Medical Images: An Investigation of Segment Anything Model (SAM) on Multi-phase Liver Tumor Segmentation
- A Scalable Test Problem Generator for Sequential Transfer Optimization
- CyFormer: Accurate State-of-Health Prediction of Lithium-Ion Batteries via Cyclic Attention
- STRAP: Structured Object Affordance Segmentation with Point Supervision
- Conditional Generation of Audio from Video via Foley Analogies
- Affordances from Human Videos as a Versatile Representation for Robotics
- BenchMD: A Benchmark for Unified Learning on Medical Images and Sensors
- Visual Instruction Tuning
- Text2Performer: Text-Driven Human Video Generation
- Neural Map Prior for Autonomous Driving
- DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP Training
- Learning to Compress Prompts with Gist Tokens
- MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing
- Learning to Render Novel Views from Wide-Baseline Stereo Pairs
- LongForm: Effective Instruction Tuning with Reverse Instructions
- Improving Autoregressive NLP Tasks via Modular Linearized Attention
- Efficient Video Action Detection with Token Dropout and Context Refinement
- An Iterative Optimizing Framework for Radiology Report Summarization with ChatGPT
- RadarFormer: Lightweight and Accurate Real-Time Radar Object Detection Model
- SCANet: Self-Paced Semi-Curricular Attention Network for Non-Homogeneous Image Dehazing
- The MiniPile Challenge for Data-Efficient Language Models
- Morph-SSL: Self-Supervision with Longitudinal Morphing to Predict AMD Progression from OCT
- CAViaR: Context Aware Video Recommendations
- Can a virtual conductor create its own interpretation of a music orchestra?
- Prak: An automatic phonetic alignment tool for Czech
- Long-term Forecasting with TiDE: Time-series Dense Encoder
- Evil from Within: Machine Learning Backdoors through Hardware Trojans
- OVTrack: Open-Vocabulary Multiple Object Tracking
- Multimodal Short Video Rumor Detection System Based on Contrastive Learning
- ATHEENA: A Toolflow for Hardware Early-Exit Network Automation
- Beyond first-order methods for non-convex non-concave min-max optimization
- Progressive Visual Prompt Learning with Contrastive Feature Re-formation
All 207
- Unsupervised Image Denoising with Score Function
- MELT: Mutual Enhancement of Long-Tailed User and Item for Sequential Recommendation
- A study on a Q-Learning algorithm application to a manufacturing assembly problem
- New Product Development (NPD) through Social Media-based Analysis by Comparing Word2Vec and BERT Word Embeddings
- Human Gesture and Gait Analysis for Autism Detection
- Why is AI not a Panacea for Data Workers? An Interview Study on Human-AI Collaboration in Data Storytelling
- Transformer with Selective Shuffled Position Embedding and Key-Patch Exchange Strategy for Early Detection of Knee Osteoarthritis
- Energy Efficiency Considerations for Popular AI Benchmarks
- What Makes a Good Dataset for Symbol Description Reading?
- Deep Explainable Relational Reinforcement Learning: A Neuro-Symbolic Approach
- VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset
- NF-ULA: Langevin Monte Carlo with Normalizing Flow Prior for Imaging Inverse Problems
- Use of social media and Natural Language Processing (NLP) in natural hazard research
- Convolutional neural network for earthquake detection
- LED: A Dataset for Life Event Extraction from Dialogs
- Goal-oriented Uncertainty Quantification for Inverse Problems via Variational Encoder-Decoder Networks
- Decentralized Learning Made Easy with DecentralizePy
- Towards Computational Performance Engineering for Unsupervised Concept Drift Detection -- Complexities, Benchmarking, Performance Analysis
- Subduction zone fault slip from seismic noise and GPS data
- Thorny Roses: Investigating the Dual Use Dilemma in Natural Language Processing
- TreeC: a method to generate interpretable energy management systems using a metaheuristic algorithm
- Promises and Pitfalls of the Linearized Laplace in Bayesian Optimization
- Predicting dynamic, motion-related changes in B0 field in the brain at a 7 T MRI using a subject-specific fine-tuned U-net
- SDVRF: Sparse-to-Dense Voxel Region Fusion for Multi-modal 3D Object Detection
- Implicit Bayes Adaptation: A Collaborative Transport Approach
- Interactive and Explainable Region-guided Radiology Report Generation
- 'That Darned Sandstorm': A Study of Procedural Generation through Archaeological Storytelling
- Toward Auto-evaluation with Confidence-based Category Relation-aware Regression
- Deep-Learning-based Vasculature Extraction for Single-Scan Optical Coherence Tomography Angiography
- MoDA: Modeling Deformable 3D Objects from Casual Videos
- Compositional Probabilistic and Causal Inference using Tractable Circuit Models
- Implementing Responsible AI: Tensions and Trade-Offs Between Ethics Aspects
- About latent roles in forecasting players in team sports
- Open-World Weakly-Supervised Object Localization
- Cross or Wait? Predicting Pedestrian Interaction Outcomes at Unsignalized Crossings
- Graph Embedding Augmented Skill Rating System
- Base Placement Optimization for Coverage Mobile Manipulation Tasks
- Uncovering the Background-Induced bias in RGB based 6-DoF Object Pose Estimation
- Intra-Batch Supervision for Panoptic Segmentation on High-Resolution Images
- Context-Dependent Embedding Utterance Representations for Emotion Recognition in Conversations
- Dynamically Reconfigurable Variable-precision Sparse-Dense Matrix Acceleration in Tensorflow Lite
- ATTACH Dataset: Annotated Two-Handed Assembly Actions for Human Action Understanding
- VECO 2.0: Cross-lingual Language Model Pre-training with Multi-granularity Contrastive Learning
- Learning Geometry-aware Representations by Sketching
- Applications of Deep Learning for Top-View Omnidirectional Imaging: A Survey
- Human Pose Estimation in Monocular Omnidirectional Top-View Images
- Normalizing Flow-based Neural Process for Few-Shot Knowledge Graph Completion
- Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca
- Pointwise convergence of Fourier series and deep neural network for the indicator function of d-dimensional ball
- Attention Mixtures for Time-Aware Sequential Recommendation
- Prediction-Oriented Bayesian Active Learning
- Political corpus creation through automatic speech recognition on EU debates
- Detection of Dense Subhypergraphs by Low-Degree Polynomials
- Tackling Face Verification Edge Cases: In-Depth Analysis and Human-Machine Fusion Approach
- A Survey on Few-Shot Class-Incremental Learning
- DAS-N2N: Machine learning Distributed Acoustic Sensing (DAS) signal denoising without clean data
- An Empirical Study of Multitask Learning to Improve Open Domain Dialogue Systems
- ViPLO: Vision Transformer based Pose-Conditioned Self-Loop Graph for Human-Object Interaction Detection
- Analysis of Interpolating Regression Models and the Double Descent Phenomenon
- Leveraging Multi-view Data for Improved Detection Performance: An Industrial Use Case
- A Comparative Study between Full-Parameter and LoRA-based Fine-Tuning on Chinese Instruction Data for Instruction Following Large Language Model
- DETR-based Layered Clothing Segmentation and Fine-Grained Attribute Recognition
- Towards Tumour Graph Learning for Survival Prediction in Head & Neck Cancer Patients
- Low-code LLM: Graphical User Interface over Large Language Models
- LLA-FLOW: A Lightweight Local Aggregation on Cost Volume for Optical Flow Estimation
- Transformer-based Graph Neural Networks for Outfit Generation
- Wireless Channel Charting: Theory, Practice, and Applications
- Trust and Transparency in Recommender Systems
- Automatic Textual Explanations of Concept Lattices
- InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction
- VCD: Visual Causality Discovery for Cross-Modal Question Reasoning
- Collaborative Feature Learning for Fine-grained Facial Forgery Detection and Segmentation
- Two-stage MR Image Segmentation Method for Brain Tumors based on Attention Mechanism
- DETRs Beat YOLOs on Real-time Object Detection
- One-Class SVM on siamese neural network latent space for Unsupervised Anomaly Detection on brain MRI White Matter Hyperintensities
- DeepSim-Nets: Deep Similarity Networks for Stereo Image Matching
- Fed-MIWAE: Federated Imputation of Incomplete Data via Deep Generative Models
- Accelerated Distributed Aggregative Optimization
- ERTIM@MC2: Diversified Argumentative Tweets Retrieval
- MMANet: Margin-aware Distillation and Modality-aware Regularization for Incomplete Multimodal Learning
- DeePLT: Personalized Lighting Facilitates by Trajectory Prediction of Recognized Residents in the Smart Home
- Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping
- Learning How To Robustly Estimate Camera Pose in Endoscopic Videos
- Self-Supervised Learning from Non-Object Centric Images with a Geometric Transformation Sensitive Architecture
- CLIP-Lung: Textual Knowledge-Guided Lung Nodule Malignancy Prediction
- Everyone Can Be Picasso? A Computational Framework into the Myth of Human versus AI Painting
- From Zero to Hero: Examining the Power of Symbolic Tasks in Instruction Tuning
- In-Context Operator Learning with Data Prompts for Differential Equation Problems
- One-shot and Partially-Supervised Cell Image Segmentation Using Small Visual Prompt
- Chinese Open Instruction Generalist: A Preliminary Release
- Snacks: a fast large-scale kernel SVM solver
- Incentive Mechanism Design for Unbiased Federated Learning with Randomized Client Participation
- RNN-Guard: Certified Robustness Against Multi-frame Attacks for Recurrent Neural Networks
- NeRF-Loc: Visual Localization with Conditional Neural Radiance Field
- Improving Weakly Supervised Temporal Action Localization by Bridging Train-Test Gap in Pseudo Labels
- Frequency Regularization: Restricting Information Redundancy of Convolutional Neural Networks
- 360^circ High-Resolution Depth Estimation via Uncertainty-aware Structural Knowledge Transfer
- Recursive Joint Attention for Audio-Visual Fusion in Regression based Emotion Recognition
- A Question-Answering Approach to Key Value Pair Extraction from Form-like Document Images
- Heterogeneous Domain Adaptation with Positive and Unlabeled Data
- Metrics for Bayesian Optimal Experiment Design under Model Misspecification
- Sustainable AIGC Workload Scheduling of Geo-Distributed Data Centers: A Multi-Agent Reinforcement Learning Approach
- Learning To Rank Resources with GNN
- Reclaimer: A Reinforcement Learning Approach to Dynamic Resource Allocation for Cloud Microservices
- Leveraging sparse and shared feature activations for disentangled representation learning
- A Randomized Approach for Tight Privacy Accounting
- Causal Disentangled Variational Auto-Encoder for Preference Understanding in Recommendation