Papers
Tue 30 Apr 2024
265 papers
- At the edge of a generative cultural precipiceDiffusion models → Image generation, text-to-image and editing
- Large Language Model Agent for Fake News DetectionLLM agents and tool use → Web, search, and research agents
- Soft Preference Optimization: Aligning Language Models to Expert DistributionsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
- Leveraging Sub-Optimal Data for Human-in-the-Loop Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
- Modeling Caption Diversity in Contrastive Vision-Language PretrainingMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Why does Knowledge Distillation Work? Rethink its Attention and Fidelity MechanismKnowledge distillation → General knowledge distillation methods
- RLHF from Heterogeneous Feedback via Personalization and Preference AggregationLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- Semantically Consistent Video Inpainting with Conditional Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
- Guiding Attention in End-to-End Driving ModelsEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
- IgCONDA-PET: Weakly-Supervised PET Anomaly Detection using Implicitly-Guided Attention-Conditional Counterfactual Diffusion Modeling -- a Multi-Center, Multi-Cancer, and Multi-Tracer StudyDiffusion models → Medical imaging and segmentation
- Graphical Reasoning: LLM-based Semi-Open Relation ExtractionLLM reasoning → Knowledge- and tool-augmented reasoning
- General Purpose Verification for Chain of Thought PromptingLLM reasoning → Reasoning benchmarks and evaluation
- Towards a Search Engine for Machines: Unified Ranking for Multiple Retrieval-Augmented Large Language ModelsRetrieval-augmented generation → RAG pipeline design and evaluation
- Information-Theoretic Opacity-Enforcement in Markov Decision ProcessesDeep reinforcement learning methods → RL theory and sample complexity
- MotionLCM: Real-time Controllable Motion Generation via Latent Consistency ModelDiffusion models → Video generation
- Invisible Stitch: Generating Smooth 3D Scenes with Depth InpaintingDiffusion models → 3D, point cloud and scene generation
- Mixed Continuous and Categorical Flow Matching for 3D De Novo Molecule GenerationDiffusion models → Flow matching, time series and science
- Iterative Reasoning Preference OptimizationLLM reasoning → Mathematical reasoning +1
- Collaborative Control Method of Transit Signal Priority Based on Cooperative Game and Reinforcement LearningDeep reinforcement learning methods → RL for autonomous driving and traffic
- X-Diffusion: Generating Detailed 3D MRI Volumes From a Single Image Using Cross-Sectional Diffusion ModelsDiffusion models → Medical imaging and segmentation
- TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction TuningLLM safety and security → Backdoor and data poisoning attacks
- RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language ProcessingRetrieval-augmented generation → Generation and context integration
- TwinDiffusion: Enhancing Coherence and Efficiency in Panoramic Image Generation with Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
- Continual Model-based Reinforcement Learning for Data Efficient Wireless Network OptimisationDeep reinforcement learning methods → RL for energy, networks and operations
- A Survey of Imitation Learning Methods, Environments and MetricsOffline RL and imitation learning from data → Imitation learning methods
- Lancet: Accelerating Mixture-of-Experts Training via Whole Graph Computation-Communication OverlappingMixture-of-experts → Efficient MoE training and inference systems
- Countering Reward Over-optimization in LLM with Demonstration-Guided Reinforcement LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- CLIP-Mamba: CLIP Pretrained Mamba Models with OOD and Hessian EvaluationState-space sequence models (S4, Mamba) → Vision Mamba backbones
- Probing Unlearned Diffusion Models: A Transferable Adversarial Attack PerspectiveDiffusion models → Robustness, privacy and adversarial aspects +1
- Numeric Reward MachinesDeep reinforcement learning methods → Interpretable and logic-guided RL
- Pessimistic Value Iteration for Multi-Task Data Sharing in Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Knowledge Distillation vs. Pretraining from Scratch under a Fixed (Computation) BudgetKnowledge distillation → Knowledge distillation for LLMs
- Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal PerspectiveMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
- Soft Prompt Generation for Domain GeneralizationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Bridge to Non-Barrier Communication: Gloss-Prompted Fine-grained Cued Speech Gesture Generation with Diffusion ModelDiffusion models → Audio, speech and music
- DiffuseLoco: Real-Time Legged Locomotion Control with Diffusion from Offline DatasetsDeep reinforcement learning methods → RL for robot locomotion and manipulation
- GRAMMAR: Grounded and Modular Methodology for Assessment of Closed-Domain Retrieval-Augmented Language ModelRetrieval-augmented generation → RAG pipeline design and evaluation
- Espresso: Robust Concept Filtering in Text-to-Image ModelsDiffusion models → Robustness, privacy and adversarial aspects
- Mix of Experts Language Model for Named Entity RecognitionMixture-of-experts → MoE large language models
- PEVA-Net: Prompt-Enhanced View Aggregation Network for Zero/Few-Shot Multi-View 3D Shape RecognitionMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
- Strategic Integration of Artificial Intelligence in the C-Suite: The Role of the Chief AI Officer
- Reimagining AI in Social Work: Practitioner Perspectives on Incorporating Technology in their Practice
- Artificial intelligence and machine learning applications for cultured meat
- Harnessing Federated Generative Learning for Green and Sustainable Internet of Things
- Fish-bone diagram of research issue: Gain a bird's-eye view on a specific research topic
- Feature Purified Transformer With Cross-level Feature Guiding Decoder For Multi-class OOD and Anomaly Deteciton
- Enhancement of Subjective Content Descriptions by using Human Feedback
- Almanac Copilot: Towards Autonomous Electronic Health Record Navigation
- Tackling water table depth modeling via machine learning: From proxy observations to verifiability
- HCC Is All You Need: Alignment-The Sensible Kind Anyway-Is Just Human-Centered Computing
- Improving Disease Detection from Social Media Text via Self-Augmentation and Contrastive Learning
- On the weight dynamics of learning networks
- Federated Graph Learning for EV Charging Demand Forecasting with Personalization Against Cyberattacks
- Diagnosis of Parkinson's Disease Using EEG Signals and Machine Learning Techniques: A Comprehensive Study
- CodeHalu: Investigating Code Hallucinations in LLMs via Execution-based Verification
- Q-Newton: Hybrid Quantum-Classical Scheduling for Accelerating Neural Network Training with Newton's Gradient Descent
- SemVecNet: Generalizable Vector Map Generation for Arbitrary Sensor Configurations
- Who is Authentic Speaker
- Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network
- STT: Stateful Tracking with Transformers for Autonomous Driving
- SemantiCodec: An Ultra Low Bitrate Semantic Audio Codec for General Sound
- Aptly: Making Mobile Apps from Natural Language
- Synthetic Face Datasets Generation via Latent Space Exploration from Brownian Identity Diffusion
- Context-Aware Mobile Network Performance Prediction Using Network & Remote Sensing Data
- Machine Learning-based Estimation of Respiratory Fluctuations in a Healthy Adult Population using BOLD fMRI and Head Motion Parameters
- Constrained Decoding for Secure Code Generation
- GMC-PINNs: A new general Monte Carlo PINNs method for solving fractional partial differential equations on irregular domains
- Block-As-Domain Adaptation for Workload Prediction from fNIRS Data
- A Primer on the Inner Workings of Transformer-based Language Models
- A Logic for Reasoning About Aggregate-Combine Graph Neural Networks
- Leveraging Active Subspaces to Capture Epistemic Model Uncertainty in Deep Generative Models for Molecular Design
- SPAFIT: Stratified Progressive Adaptation Fine-tuning for Pre-trained Large Language Models
- In-Context Learning with Long-Context Models: An In-Depth Exploration
- Grounding Realizable Entities
- Synthetic Image Verification in the Era of Generative AI: What Works and What Isn't There Yet
- Towards End-to-End Semi-Supervised Table Detection with Semantic Aligned Matching Transformer
- Credentials in the Occupation Ontology
- Semi-Supervised Hierarchical Multi-Label Classifier Based on Local Information
- Capabilities: An Ontology
- M-DEW: Extending Dynamic Ensemble Weighting to Handle Missing Values
- Uncovering What, Why and How: A Comprehensive Benchmark for Causation Understanding of Video Anomaly
- Bypassing Skip-Gram Negative Sampling: Dimension Regularization as a More Efficient Alternative for Graph Embeddings
- Revisiting RGBT Tracking Benchmarks from the Perspective of Modality Validity: A New Benchmark, Problem, and Solution
- Discovering intrinsic multi-compartment pharmacometric models using Physics Informed Neural Networks
- BayesBlend: Easy Model Blending using Pseudo-Bayesian Model Averaging, Stacking and Hierarchical Stacking in Python
- Expanding the Horizon: Enabling Hybrid Quantum Transfer Learning for Long-Tailed Chest X-Ray Classification
- HistNERo: Historical Named Entity Recognition for the Romanian Language
- GUing: A Mobile GUI Search Engine using a Vision-Language Model
- Utilizing Machine Learning and 3D Neuroimaging to Predict Hearing Loss: A Comparative Analysis of Dimensionality Reduction and Regression Techniques
- Data-Driven Permissible Safe Control with Barrier Certificates
- Transforming Dutch: Debiasing Dutch Coreference Resolution Systems for Non-binary Pronouns
- A Flexible 2.5D Medical Image Segmentation Approach with In-Slice and Cross-Slice Attention
- Reconstructing networks from simple and complex contagions
- Graph Neural Network Approach to Semantic Type Detection in Tables
- Training a high-performance retinal foundation model with half-the-data and 400 times less compute
- Creative Beam Search: LLM-as-a-Judge For Improving Response Generation
- Structure learning of Hamiltonians from real-time evolution
- Imprecise Markov Semigroups and their Ergodicity
- Recommenadation aided Caching using Combinatorial Multi-armed Bandits
- BrainODE: Dynamic Brain Signal Analysis via Graph-Aided Neural Ordinary Differential Equations
All 265
- Towards trustable SHAP scores
- PAODING: A High-fidelity Data-free Pruning Toolkit for Debloating Pre-trained Neural Networks
- Lightplane: Highly-Scalable Components for Neural 3D Fields
- KAN: Kolmogorov-Arnold Networks
- DOCCI: Descriptions of Connected and Contrasting Images
- Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generation
- Scale-Robust Timely Asynchronous Decentralized Learning
- Quantifying Nematodes through Images: Datasets, Models, and Baselines of Deep Learning
- PrivComp-KG : Leveraging Knowledge Graph and Large Language Models for Privacy Policy Compliance Verification
- Better & Faster Large Language Models via Multi-token Prediction
- A Framework for Leveraging Human Computation Gaming to Enhance Knowledge Graphs for Accuracy Critical Generative AI Applications
- CurvFed: Curvature-Aligned Federated Learning for Fairness without Demographics
- PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarios
- PANGeA: Procedural Artificial Narrative using Generative AI for Turn-Based Video Games
- The lazy (NTK) and rich (μP) regimes: a gentle tutorial
- ThangDLU at #SMM4H 2024: Encoder-decoder models for classifying text data on social disorders in children and adolescents
- Automated Generation of High-Quality Medical Simulation Scenarios Through Integration of Semi-Structured Data and Large Language Models
- A rank decomposition for the topological classification of neural representations
- Harmonic LLMs are Trustworthy
- RTG-SLAM: Real-time 3D Reconstruction at Scale using Gaussian Splatting
- When to Retrieve: Teaching LLMs to Utilize Information Retrieval Effectively
- GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting
- Naturally Supervised 3D Visual Grounding with Language-Regularized Concept Learners
- SwipeGANSpace: Swipe-to-Compare Image Generation via Efficient Latent Space Exploration
- Continuum limit of p-biharmonic equations on graphs
- Neural Controlled Differential Equations with Quantum Hidden Evolutions
- Beyond MOS: Subjective Image Quality Score Preprocessing Method Based on Perceptual Similarity
- ATOMMIC: An Advanced Toolbox for Multitask Medical Imaging Consistency to facilitate Artificial Intelligence applications from acquisition to analysis in Magnetic Resonance Imaging
- Towards Generalist Robot Learning from Internet Video: A Survey
- PCA for Point Processes
- Towards Scenario- and Capability-Driven Dataset Development and Evaluation: An Approach in the Context of Mapless Automated Driving
- Masked Multi-Query Slot Attention for Unsupervised Object Discovery
- VimTS: A Unified Video and Image Text Spotter for Enhancing the Cross-domain Generalization
- Provably Robust Conformal Prediction with Improved Efficiency
- MetaCoCo: A New Few-Shot Classification Benchmark with Spurious Correlation
- ESP-Zero: Unsupervised enhancement of zero-shot classification for Extremely Sparse Point cloud
- On Training a Neural Network to Explain Binaries
- Analyzing and Exploring Training Recipes for Large-Scale Transformer-Based Weather Prediction
- Fake it to make it: Using synthetic data to remedy the data shortage in joint multimodal speech-and-gesture synthesis
- Be Aware of the Neighborhood Effect: Modeling Selection Bias under Interference
- SemiPL: A Semi-supervised Method for Event Sound Source Localization
- Seeing Through the Clouds: Cloud Gap Imputation with Prithvi Foundation Model
- Data-Driven Invertible Neural Surrogates of Atmospheric Transmission
- Artificial Intelligence in Bone Metastasis Analysis: Current Advancements, Opportunities and Challenges
- Debiased Collaborative Filtering with Kernel-Based Causal Balancing
- Perceptual Constancy Constrained Single Opinion Score Calibration for Image Quality Assessment
- Towards Interactively Improving ML Data Preparation Code via "Shadow Pipelines"
- AI techniques for near real-time monitoring of contaminants in coastal waters on board future Phisat-2 mission
- URVFL: Undetectable Data Reconstruction Attack on Vertical Federated Learning
- Automatic Cardiac Pathology Recognition in Echocardiography Images Using Higher Order Dynamic Mode Decomposition and a Vision Transformer for Small Datasets
- A Spatio-Temporal based Frame Indexing Algorithm for QoS Improvement in Live Low-Motion Video Streaming
- War Elephants: Rethinking Combat AI and Human Oversight
- Enhancing Deep Learning Model Explainability in Brain Tumor Datasets using Post-Heuristic Approaches
- Causal Perception Inspired Representation Learning for Trustworthy Image Quality Assessment
- RepEval: Effective Text Evaluation with LLM Representation
- Neural Dynamic Data Valuation via Stochastic State-Adjoint Trajectories
- Extending Llama-3's Context Ten-Fold Overnight
- One-Stage Open-Vocabulary Temporal Action Detection Leveraging Temporal Multi-scale and Action Label Features
- Ultra Inertial Poser: Scalable Motion Capture and Tracking from Sparse Inertial Sensors and Ultra-Wideband Ranging
- Physics-Informed Machine Learning On Polar Ice: A Survey
- MIPI 2024 Challenge on Nighttime Flare Removal: Methods and Results
- MoST: Multi-modality Scene Tokenization for Motion Prediction
- MicroDreamer: Efficient 3D Generation in ~20 Seconds by Score-based Iterative Reconstruction
- Generating Robust Counterfactual Witnesses for Graph Neural Networks
- MGCBS: An Optimal and Efficient Algorithm for Solving Multi-Goal Multi-Agent Path Finding Problem
- Inexact subgradient methods for semialgebraic functions
- A Smartphone-Based Method for Assessing Tomato Nutrient Status through Trichome Density Measurement
- Do Large Language Models Understand Conversational Implicature -- A case study with a chinese sitcom
- Temporal Graph ODEs for Irregularly-Sampled Time Series
- Context-Aware Machine Translation with Source Coreference Explanation
- A Unified Theory of Exact Inference and Learning in Exponential Family Latent Variable Models
- Towards Real-world Video Face Restoration: A New Benchmark
- Online and Offline Robust Multivariate Linear Regression
- EvGNN: An Event-driven Graph Neural Network Accelerator for Edge Vision
- Finetuning greedy kernel models by exchange algorithms
- Safe Training with Sensitive In-domain Data: Leveraging Data Fragmentation To Mitigate Linkage Attacks
- IID Relaxation by Logical Expressivity: A Research Agenda for Fitting Logics to Neurosymbolic Requirements
- More Compute Is What You Need
- FactCheck Editor: Multilingual Text Editor with End-to-End fact-checking
- SpecstatOR: Speckle statistics-based iOCT Segmentation Network for Ophthalmic Surgery
- Hybrid Bit and Semantic Communications
- Bayesian Functional Connectivity and Graph Convolutional Network for Working Memory Load Classification
- AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples
- Augmented neural forms with parametric boundary-matching operators for solving ordinary differential equations
- How to Sustainably Monitor ML-Enabled Systems? Accuracy and Energy Efficiency Tradeoffs in Concept Drift Detection
- AnomalyXFusion: Multi-modal Anomaly Synthesis with Diffusion
- Does Generative AI speak Nigerian-Pidgin?: Issues about Representativeness and Bias for Multilingualism in LLMs
- Can Large Language Models put 2 and 2 together? Probing for Entailed Arithmetical Relationships
- S~onajaht: Definition Embeddings and Semantic Search for Reverse Dictionary Creation
- InstantFamily: Masked Attention for Zero-shot Multi-ID Image Generation
- Let's Focus: Focused Backdoor Attack against Federated Transfer Learning
- Physical Backdoor: Towards Temperature-based Backdoor Attacks in the Physical World
- Transformer-Enhanced Motion Planner: Attention-Guided Sampling for State-Specific Decision Making
- UniFS: Universal Few-shot Instance Perception with Point Representations
- 3D Gaussian Blendshapes for Head Avatar Animation
- Can humans teach machines to code?
- Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detection
- Cross-Block Fine-Grained Semantic Cascade for Skeleton-Based Sports Action Recognition
- SemanticFormer: Holistic and Semantic Traffic Scene Representation for Trajectory Prediction using Knowledge Graphs
- Evaluating Telugu Proficiency in Large Language Models_ A Comparative Analysis of ChatGPT and Gemini
- Navigating Brain Language Representations: A Comparative Analysis of Neural Language Models and Psychologically Plausible Models
- Expressivity and Speech Synthesis
- A Negotiator's Backup Plan: Optimal Concessions with a Reservation Value
- Large Language Model Informed Patent Image Retrieval
- Evaluating Lexicon Incorporation for Depression Symptom Estimation
- PEFSL: A deployment Pipeline for Embedded Few-Shot Learning on a FPGA SoC
- Deep Learning Forecasts Caldera Collapse Events at Kilauea Volcano
- Human-AI Interaction in Industrial Robotics: Design and Empirical Evaluation of a User Interface for Explainable AI-Based Robot Program Optimization
- Reliable or Deceptive? Investigating Gated Features for Smooth Visual Explanations in CNNs
- Improving LLM Classification of Logical Errors by Integrating Error Relationship into Prompts
- StablePT: Towards Stable Prompting for Few-shot Learning via Input Separation
- Multi-Scale Heterogeneity-Aware Hypergraph Representation for Histopathology Whole Slide Images
- G2LTraj: A Global-to-Local Generation Approach for Trajectory Prediction
- End-to-end information extraction in handwritten documents: Understanding Paris marriage records from 1880 to 1940
- Computational Approaches for Integrating out Subjectivity in Cognate Synonym Selection
- LVOS: A Benchmark for Large-scale Long-term Video Object Segmentation
- Calibration of Large Language Models on Code Summarization
- Revisiting N-Gram Models: Their Impact in Modern Neural Networks for Handwritten Text Recognition
- QLSC: A Query Latent Semantic Calibrator for Robust Extractive Question Answering
- Modeling Orthographic Variation in Occitan's Dialects
- A Light-weight Transformer-based Self-supervised Matching Network for Heterogeneous Images
- Does Whisper understand Swiss German? An automatic, qualitative, and human evaluation
- Comprehensive Forecasting-Based Analysis of Hybrid and Stacked Stateful/ Stateless Models
- Data Set Terminology of Deep Learning in Medicine: A Historical Review and Recommendation
- Statistics and explainability: a fruitful alliance
- Robust Pedestrian Detection via Constructing Versatile Pedestrian Knowledge Bank
- Octopus v4: Graph of language models
- Masked Spatial Propagation Network for Sparsity-Adaptive Depth Refinement
- Provably Efficient Information-Directed Sampling Algorithms for Multi-Agent Reinforcement Learning
- On Improving the Algorithm-, Model-, and Data- Efficiency of Self-Supervised Learning
- Training-free Graph Neural Networks and the Power of Labels as Features
- Approximate Nearest Neighbour Search on Dynamic Datasets: An Investigation
- MAP-Former: Multi-Agent-Pair Gaussian Joint Prediction
- Quater-GCN: Enhancing 3D Human Pose Estimation with Orientation and Semi-supervised Training
- C2FDrone: Coarse-to-Fine Drone-to-Drone Detection using Vision Transformer Networks
- Statistical Mechanics Calculations Using Variational Autoregressive Networks and Quantum Annealing
- Mapping New Realities: Ground Truth Image Creation with Pix2Pix Image-to-Image Translation
- High dimensional analysis reveals conservative sharpening and a stochastic edge of stability
- Aspect and Opinion Term Extraction Using Graph Attention Network
- DELINE8K: A Synthetic Data Pipeline for the Semantic Segmentation of Historical Documents
- AI, Pluralism, and (Social) Compensation
- Suvach -- Generated Hindi QA benchmark
- Learning to Communicate Functional States with Nonverbal Expressions for Improved Human-Robot Collaboration
- ViTHSD: Exploiting Hatred by Targets for Hate Speech Detection on Vietnamese Social Media Texts
- Enhancing Intrinsic Features for Debiasing via Investigating Class-Discerning Common Attributes in Bias-Contrastive Pair
- Scheduling Weight Transitions for Quantization-Aware Training
- Improved AutoEncoder with LSTM module and KL divergence
- HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning
- A University Framework for the Responsible use of Generative AI in Research
- A Minimal Set of Parameters Based Depth-Dependent Distortion Model and Its Calibration Method for Stereo Vision Systems
- Pilot Contamination in Massive MIMO Systems: Challenges and Future Prospects
- Multi-hop Question Answering over Knowledge Graphs using Large Language Models
- Deep Lead Optimization: Leveraging Generative AI for Structural Modification
- Weighted Point Set Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metric
- Transcrib3D: 3D Referring Expression Resolution through Large Language Models
- Regression for matrix-valued data via Kronecker products factorization
- Flight Trajectory Prediction Using an Enhanced CNN-LSTM Network
- TableVQA-Bench: A Visual Question Answering Benchmark on Multiple Table Domains
- NeRF-Insert: 3D Local Editing with Multimodal Control Signals
- Exploring Quasi-Global Solutions to Compound Lens Based Computational Imaging Systems
- Revenge of the Fallen? Recurrent Models Match Transformers at Predicting Human Language Comprehension Metrics
- Game-MUG: Multimodal Oriented Game Situation Understanding and Commentary Generation Dataset
- XFeat: Accelerated Features for Lightweight Image Matching
- Explicit Correlation Learning for Generalizable Cross-Modal Deepfake Detection
- DelGrad: Exact event-based gradients for training delays and weights on spiking neuromorphic hardware