Papers
Tue 8 Aug 2023
214 papers
- Accelerating LLM Inference with Staged Speculative DecodingEfficient LLM inference and serving → Speculative decoding
- Improved Activation Clipping for Universal Backdoor Mitigation and Test-Time DetectionLLM safety and security → Backdoor and data poisoning attacks
- Shepherd: A Critic for Language Model GenerationLLM reasoning → Test-time compute and efficient thinking
- Bootstrapping Developmental AIs: From Simple Competences to Intelligent Human-Compatible AIsSynthetic data and self-improvement for LLMs → Self-evolving LLM agents
- Semi-Supervised Semantic Segmentation of Cell Nuclei via Diffusion-based Large-Scale Pre-Training and Collaborative LearningDiffusion models → Medical imaging and segmentation
- Weakly Semi-Supervised Detection in Lung Ultrasound VideosKnowledge distillation → Distillation for medical imaging
- DiffCR: A Fast Conditional Diffusion Framework for Cloud Removal from Optical Satellite ImagesDiffusion models → Inverse problems and image restoration
- Cumulative Reasoning with Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
- RLHF-Blender: A Configurable Interactive Interface for Learning from Diverse Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Teacher-Student Architecture for Knowledge Distillation: A SurveyKnowledge distillation → General knowledge distillation methods
- FLIRT: Feedback Loop In-context Red TeamingLLM safety and security → Vision-language and text-to-image safety
- AICSD: Adaptive Inter-Class Similarity Distillation for Semantic SegmentationKnowledge distillation → Detection and dense prediction distillation
- Hybrid-RACA: Hybrid Retrieval-Augmented Composition Assistance for Real-time Text PredictionRetrieval-augmented generation → Generation and context integration
- Breaking Speaker Recognition with PaddingBackLLM safety and security → Audio jailbreaks and speech backdoors
- Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative InstructionsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
- Enhancing Adversarial Robustness in Low-Label Regime via Adaptively Weighted Regularization and Knowledge DistillationKnowledge distillation → Federated, robust and private distillation
- Gentopia: A Collaborative Platform for Tool-Augmented LLMsLLM agents and tool use → General LLM agent frameworks and benchmarks
- Few-shot medical image classification with simple shape and texture text descriptors using vision-language modelsMultimodal LLMs / vision-language models → Medical vision-language models
- Understanding CNN Hidden Neuron Activations Using Structured Background Knowledge and Deductive ReasoningLLM reasoning → Reasoning benchmarks and evaluation
- Target Speech Extraction with Conditional Diffusion ModelDiffusion models → Audio, speech and music
- Automated machine vision control system for technological nodes assembly process
- Non-Intrusive Electric Load Monitoring Approach Based on Current Feature Visualization for Smart Energy Management
- Applications of Nature-Inspired Metaheuristic Algorithms for Tackling Optimization Problems Across Disciplines
- TranSTYLer: Multimodal Behavioral Style Transfer for Facial and Body Gestures Generation
- AdaptEx: A Self-Service Contextual Bandit Platform
- PokerKit: A Comprehensive Python Library for Fine-Grained Multi-Variant Poker Game Simulations
- Towards Automatic Scoring of Spinal X-ray for Ankylosing Spondylitis
- Copy Number Variation Informs fMRI-based Prediction of Autism Spectrum Disorder
- Dynamic Model Agnostic Reliability Evaluation of Machine-Learning Methods Integrated in Instrumentation & Control Systems
- Vector Embeddings by Sequence Similarity and Context for Improved Compression, Similarity Search, Clustering, Organization, and Manipulation of cDNA Libraries
- PTransIPs: Identification of phosphorylation sites enhanced by protein PLM embeddings
- Why Data Science Projects Fail
- A Comparative Study of Sentence Embedding Models for Assessing Semantic Variation
- Benchmarking LLM powered Chatbots: Methods and Metrics
- Rendering Humans from Object-Occluded Monocular Videos
- Multiclass Online Learnability under Bandit Feedback
- Machine Learning, Deep Learning and Data Preprocessing Techniques for Detection, Prediction, and Monitoring of Stress and Stress-related Mental Disorders: A Scoping Review
- Sparse Array Design for Direction Finding using Deep Learning
- Deep Learning Driven Detection of Tsunami Related Internal GravityWaves: a path towards open-ocean natural hazards detection
- PSRFlow: Probabilistic Super Resolution with Flow-Based Models for Scientific Data
- A Survey on Decentralized Federated Learning
- A Brief Yet In-Depth Survey of Deep Learning-Based Image Watermarking
- Model of models -- Part 1
- 1st Place Solution for CVPR2023 BURST Long Tail and Open World Challenges
- Quantization Aware Factorization for Deep Neural Network Compression
- Temporal DINO: A Self-supervised Video Strategy to Enhance Action Prediction
- ScatterUQ: Interactive Uncertainty Visualizations for Multiclass Deep Learning Problems
- Kernel Single Proxy Control for Deterministic Confounding
- LATR: 3D Lane Detection from Monocular Images with Transformer
- RECipe: Does a Multi-Modal Recipe Knowledge Graph Fit a Multi-Purpose Recommendation System?
- Optimizing Algorithms From Pairwise User Preferences
- Single-Sentence Reader: A Novel Approach for Addressing Answer Position Bias
- Spectral Regularized Kernel Goodness-of-Fit Tests
- FocalFormer3D : Focusing on Hard Instance for 3D Object Detection
- From Fake to Real: Pretraining on Balanced Synthetic Images to Prevent Spurious Correlations in Image Recognition
- Improving Medical Image Classification in Noisy Labels Using Only Self-supervised Pretraining
- Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation
- YUDO: YOLO for Uniform Directed Object Detection
- Improving Performance in Continual Learning Tasks using Bio-Inspired Architectures
- Facial Prior Based First Order Motion Model for Micro-expression Generation
- Estimation of Human Condition at Disaster Site Using Aerial Drone Images
- Ahead of the Text: Leveraging Entity Preposition for Financial Relation Extraction
- Generating Modern Persian Carpet Map by Style-transfer
- Unsupervised Camouflaged Object Segmentation as Domain Adaptation
- Large-Scale Multi-Hypotheses Cell Tracking Using Ultrametric Contours Maps
- Deep Learning for Steganalysis of Diverse Data Types: A review of methods, taxonomy, challenges and future directions
- DisCoCat for Donkey Sentences
- Toward unlabeled multi-view 3D pedestrian detection by generalizable AI: techniques and performance analysis
- MT-IceNet -- A Spatial and Multi-Temporal Deep Learning Model for Arctic Sea Ice Forecasting
- Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognition
- DialogRE^C+: An Extension of DialogRE to Investigate How Much Coreference Helps Relation Extraction in Dialogs
- Efficient option pricing with unary-based photonic computing chip and generative adversarial learning
- ChatGPT for Arabic Grammatical Error Correction
- A Comparative Study of Code Generation using ChatGPT 3.5 across 10 Programming Languages
- D-Score: A Synapse-Inspired Approach for Filter Pruning
- Correlating Medi-Claim Service by Deep Learning Neural Networks
- 3D Scene Diffusion Guidance using Scene Graphs
- Backdoor Federated Learning by Poisoning Backdoor-Critical Layers
- Characterization of Human Balance through a Reinforcement Learning-based Muscle Controller
- When More is Less: Incorporating Additional Datasets Can Hurt Performance By Introducing Spurious Correlations
- SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore
- Sample-Efficient Linear Representation Learning from Non-IID Non-Isotropic Data
- A Deep-Learning Method Using Auto-encoder and Generative Adversarial Network for Anomaly Detection on Ancient Stone Stele Surfaces
- A Bi-directional Multi-hop Inference Model for Joint Dialog Sentiment Classification and Act Recognition
- Digging into Depth Priors for Outdoor Neural Radiance Fields
- Probabilistic Invariant Learning with Randomized Linear Classifiers
- V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection
- XGBD: Explanation-Guided Graph Backdoor Detection
- Person Re-Identification without Identification via Event Anonymization
- Fine-Tuning Games: Bargaining and Adaptation for General-Purpose Models
- Character-level NMT and language similarity
- LEFormer: A Hybrid CNN-Transformer Architecture for Accurate Lake Extraction from Remote Sensing Imagery
- Event Abstraction for Enterprise Collaboration Systems to Support Social Process Mining
- Data Augmentation-Based Unsupervised Domain Adaptation In Medical Imaging
- Learning Evaluation Models from Large Language Models for Sequence Generation
- DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Clouds
- Your Negative May not Be True Negative: Boosting Image-Text Matching with False Negative Elimination
- Understanding the Effect of Counterfactual Explanations on Trust and Reliance on AI for Human-AI Collaborative Clinical Decision Making
- Pelta: Shielding Transformers to Mitigate Evasion Attacks in Federated Learning
- Some Options for Instantiation of Bipolar Argument Graphs with Deductive Arguments
All 214
- When Super-Resolution Meets Camouflaged Object Detection: A Comparison Study
- SSTFormer: Bridging Spiking Neural Network and Memory Support Transformer for Frame-Event based Recognition
- SLEM: Machine Learning for Path Modeling and Causal Inference with Super Learner Equation Modeling
- Learning Unbiased Image Segmentation: A Case Study with Plain Knee Radiographs
- 3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment
- Unmasking Nationality Bias: A Study of Human Perception of Nationalities in AI-Generated Articles
- Unifying Two-Stream Encoders with Transformers for Cross-Modal Retrieval
- Accurate, Explainable, and Private Models: Providing Recourse While Minimizing Training Data Leakage
- A Lightweight and Accurate Face Detection Algorithm Based on Retinaface
- Pengembangan Model untuk Mendeteksi Kerusakan pada Terumbu Karang dengan Klasifikasi Citra
- Towards an AI to Win Ghana's National Science and Maths Quiz
- Domain Adaptive Person Search via GAN-based Scene Synthesis for Cross-scene Videos
- All-pairs Consistency Learning for Weakly Supervised Semantic Segmentation
- Cooperative Multi-agent Bandits: Distributed Algorithms with Optimal Individual Regret and Constant Communication Costs
- Apple Vision Pro for Healthcare: "The Ultimate Display"? -- Entering the Wonderland of Precision Medicine
- Interpretable Goal-Based model for Vehicle Trajectory Prediction in Interactive Scenarios
- Deep Learning-Based Knowledge Injection for Metaphor Detection: A Comprehensive Review
- The Model Inversion Eavesdropping Attack in Semantic Communication Systems
- Vehicle Motion Forecasting using Prior Information and Semantic-assisted Occupancy Grid Maps
- Actor-Critic with variable time discretization via sustained actions
- Engineering LaCAM^ast: Towards Real-Time, Large-Scale, and Near-Optimal Multi-Agent Pathfinding
- Cloth2Tex: A Customized Cloth Texture Generation Pipeline for 3D Virtual Try-On
- Comparative Analysis of the wav2vec 2.0 Feature Extractor
- Vision-Based Autonomous Navigation for Unmanned Surface Vessel in Extreme Marine Conditions
- In-Context Alignment: Chat with Vanilla Language Models Before Fine-Tuning
- Lossy and Lossless (L2) Post-training Model Size Compression
- BarlowRL: Barlow Twins for Data-Efficient Reinforcement Learning
- SDLFormer: A Sparse and Dense Locality-enhanced Transformer for Accelerated MR Image Reconstruction
- Advancing Natural-Language Based Audio Retrieval with PaSST and Large Audio-Caption Data Sets
- CLASSLA-Stanza: The Next Step for Linguistic Processing of South Slavic Languages
- Blur aware metric depth estimation with multi-focus plenoptic cameras
- MindDiffuser: Controlled Image Reconstruction from Human Brain Activity with Semantic and Structural Diffusion
- Gloss Alignment Using Word Embeddings
- AutoPCF: Efficient Product Carbon Footprint Accounting with Large Language Models
- Federated Inference with Reliable Uncertainty Quantification over Wireless Channels via Conformal Prediction
- A Comparative Study of Image-to-Image Translation Using GANs for Synthetic Child Race Data
- OpinionConv: Conversational Product Search with Grounded Opinions
- Will your Doorbell Camera still recognize you as you grow old
- Semantic Interpretation and Validation of Graph Attention-based Explanations for GNN Models
- AquaSAM: Underwater Image Foreground Segmentation
- Varying-coefficients for regional quantile via KNN-based LASSO with applications to health outcome study
- Robust retrieval of material chemical states in X-ray microspectroscopy
- Exploring Transformers for Open-world Instance Segmentation
- D3G: Exploring Gaussian Prior for Temporal Sentence Grounding with Glance Annotation
- Image Copy-Move Forgery Detection via Deep Cross-Scale PatchMatch
- Adding Why to What? Analyses of an Everyday Explanation
- Iterative Sketching for Secure Coded Regression
- Studying Socially Unacceptable Discourse Classification (SUD) through different eyes: "Are we on the same page ?"
- Assistive Chatbots for healthcare: a succinct review
- How Generalizable are Deepfake Image Detectors? An Empirical Study
- On Monotonic Aggregation for Open-domain QA
- Predicting Drug-Drug Interactions Using Knowledge Graphs
- Dual input neural networks for positional sound source localization
- EFaR 2023: Efficient Face Recognition Competition
- Under-Display Camera Image Restoration with Scattering Effect
- Expression Prompt Collaboration Transformer for Universal Referring Video Object Segmentation
- Current and Future Challenges in Knowledge Representation and Reasoning
- Towards Top-Down Stereo Image Quality Assessment via Stereo Attention
- Application for White Spot Syndrome Virus (WSSV) Monitoring using Edge Machine Learning
- Class-level Structural Relation Modelling and Smoothing for Visual Representation Learning
- Large Language Model Prompt Chaining for Long Legal Document Classification
- A Comprehensive Assessment Benchmark for Rigorously Evaluating Deep Learning Image Classifiers
- OmniDataComposer: A Unified Data Structure for Multimodal Data Fusion and Infinite Data Generation
- Social Media, Topic Modeling and Sentiment Analysis in Municipal Decision Support
- Constructing Custom Thermodynamics Using Deep Learning
- Multimodal Color Recommendation in Vector Graphic Documents
- Collective Human Opinions in Semantic Textual Similarity
- I-WAS: a Data Augmentation Method with GPT-2 for Simile Detection
- Parallel Learning by Multitasking Neural Networks
- Explainable machine learning to enable high-throughput electrical conductivity optimization and discovery of doped conjugated polymers
- Asynchronous Evolution of Deep Neural Network Architectures
- From Unimodal to Multimodal: improving sEMG-Based Pattern Recognition via deep generative models
- Heterogeneous 360 Degree Videos in Metaverse: Differentiated Reinforcement Learning Approaches
- Application-Oriented Benchmarking of Quantum Generative Learning Using QUARK
- 3D Gaussian Splatting for Real-Time Radiance Field Rendering
- Federated Zeroth-Order Optimization using Trajectory-Informed Surrogate Gradients
- DataTales: Investigating the use of Large Language Models for Authoring Data-Driven Articles
- Exploiting Spatial-Temporal Context for Interacting Hand Reconstruction on Monocular RGB Video
- Learning Specialized Activation Functions for Physics-informed Neural Networks
- Path Signatures for Diversity in Probabilistic Trajectory Optimisation
- ConDistFL: Conditional Distillation for Federated Learning from Partially Annotated Data
- Toward Improving Predictive Risk Modelling for New Zealand's Child Welfare System Using Clustering Methods
- An Empirical Analysis of Range for 3D Object Detection
- The Five-Dollar Model: Generating Game Maps and Sprites from Sentence Embeddings
- Generative Models for Anomaly Detection and Design-Space Dimensionality Reduction in Shape Optimization
- SODFormer: Streaming Object Detection with Transformer Using Events and Frames
- InfeRE: Step-by-Step Regex Generation via Chain of Inference
- Implicit neural representations for joint decomposition and registration of gene expression images in the marmoset brain
- A Comparative Study on TF-IDF feature Weighting Method and its Analysis using Unstructured Dataset
- Adapting Foundation Models for Information Synthesis of Wireless Communication Specifications
- Measure of Uncertainty in Human Emotions
- Top K Relevant Passage Retrieval for Biomedical Question Answering
- AgentSims: An Open-Source Sandbox for Large Language Model Evaluation
- MSAC: Multiple Speech Attribute Control Method for Reliable Speech Emotion Recognition
- Scope Loss for Imbalanced Classification and RL Exploration
- Synthetic Augmentation with Large-scale Unconditional Pre-training
- Improving Performance of Semi-Supervised Learning by Adversarial Attacks
- Multi-Granularity Attention Model for Group Recommendation
- Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning
- Continual Pre-Training of Large Language Models: How to (re)warm your model?
- Generalization bound for estimating causal effects from observational network data
- Coarse-to-Fine: Learning Compact Discriminative Representation for Single-Stage Image Retrieval
- Real-time Strawberry Detection Based on Improved YOLOv5s Architecture for Robotic Harvesting in open-field environment
- Cooperative Multi-Type Multi-Agent Deep Reinforcement Learning for Resource Management in Space-Air-Ground Integrated Networks
- AI Chatbots as Multi-Role Pedagogical Agents: Transforming Engagement in CS Education
- NEOLAF, an LLM-powered neural-symbolic cognitive architecture
- Fourier neural operator for real-time simulation of 3D dynamic urban microclimate
- SimplyRetrieve: A Private and Lightweight Retrieval-Centric Generative AI Tool
- PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection
- PAIF: Perception-Aware Infrared-Visible Image Fusion for Attack-Tolerant Semantic Segmentation
- PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning
- Prompted Contrast with Masked Motion Modeling: Towards Versatile 3D Action Representation Learning
- Optimal Clustering with Dependent Costs in Bayesian Networks
- CheXFusion: Effective Fusion of Multi-View Features using Transformers for Long-Tailed Chest X-Ray Classification