Papers
Sat 18 Nov 2023
119 papers
- Visual AI and Linguistic Intelligence Through Steerability and ComposabilityMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
- An Embodied Generalist Agent in 3D WorldLLM agents and tool use → Multimodal and embodied agents
- MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware DiffusionDiffusion models → Image generation, text-to-image and editing
- MultiDelete for Multimodal Machine UnlearningLLM safety and security → Machine unlearning
- Active Prompt Learning in Vision Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Mitigating Exposure Bias in Discriminator Guided Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- (Why) Is My Prompt Getting Worse? Rethinking Regression Testing for Evolving LLM APIsLLM reasoning → Reasoning for agents, planning and code
- LightBTSeg: A lightweight breast tumor segmentation model using ultrasound images via dual-path joint knowledge distillationKnowledge distillation → Distillation for medical imaging
- Improving Adversarial Transferability by Stable DiffusionDiffusion models → Robustness, privacy and adversarial aspects
- Wasserstein Convergence Guarantees for a General Class of Score-Based Generative ModelsDiffusion models → Diffusion foundations and sampling
- RecExplainer: Aligning Large Language Models for Explaining Recommendation ModelsLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
- Case Repositories: Towards Case-Based Reasoning for AI AlignmentLLM reasoning → Reasoning for agents, planning and code +1
- The Case for Universal Basic Computing Power
- Security Fence Inspection at Airports Using Object Detection
- DatasetNeRF: Efficient 3D-aware Data Factory with Generative Radiance Fields
- PBWR: Parametric Building Wireframe Reconstruction from Aerial LiDAR Point Clouds
- Mesh Watermark Removal Attack and Mitigation: A Novel Perspective of Function Space
- FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugin
- Kuro Siwo: 33 billion m2 under the water. A global multi-temporal satellite dataset for rapid flood mapping
- Boost Adversarial Transferability by Uniform Scale and Mix Mask Method
- 3D-GOI: 3D GAN Omni-Inversion for Multifaceted and Multi-object Editing
- Energizing Federated Learning via Filter-Aware Attention
- One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning
- LATIS: Lambda Abstraction-based Thermal Image Super-resolution
- Dueling Optimization with a Monotone Adversary
- Diverse Shape Completion via Style Modulated Generative Adversarial Networks
- Exponentially Convergent Algorithms for Supervised Matrix Factorization
- Nonsmooth Projection-Free Optimization with Functional Constraints
- Morphology-Enhanced CAM-Guided SAM for weakly supervised Breast Lesion Segmentation
- Best uses of ChatGPT and Generative AI for computer science research
- Low-Precision Floating-Point for Efficient On-Board Deep Neural Network Processing
- LOSTU: Fast, Scalable, and Uncertainty-Aware Triangulation
- Deep Coherence Learning: An Unsupervised Deep Beamformer for High Quality Single Plane Wave Imaging in Medical Ultrasound
- Benchmarking Machine Learning Models for Quantum Error Correction
- From Optimization to Control: Quasi Policy Iteration
- Experts-in-the-Loop: Establishing an Effective Workflow in Crafting Privacy Q&A
- Evaluating the Inclusiveness of Artificial Intelligence Software in Enhancing Project Management Efficiency -- A Review
- Contextualizing Internet Memes Across Social Media Platforms
- Biarchetype analysis: simultaneous learning of observations and features based on extremes
- On the Hardness of Learning to Stabilize Linear Systems
- Benchmarking Feature Extractors for Reinforcement Learning-Based Semiconductor Defect Localization
- Vashantor: A Large-scale Multilingual Benchmark Dataset for Automated Translation of Bangla Regional Dialects to Bangla Language
- Estimating Uncertainty in Landslide Segmentation Models
- A Principled Framework for Knowledge-enhanced Large Language Model
- Invariant-based Mapping of Space During General Motion of an Observer
- Bayesian Neural Networks: A Min-Max Game Framework
- SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimation
- An Improved CNN-based Neural Network Model for Fruit Sugar Level Detection
- Utilizing Speech Emotion Recognition and Recommender Systems for Negative Emotion Handling in Therapy Chatbots
- Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalization
- Auxiliary Losses for Learning Generalizable Concept-based Models
- ShapeMatcher: Self-Supervised Joint Shape Canonicalization, Segmentation, Retrieval and Deformation
- Responsible AI Considerations in Text Summarization Research: A Review of Current Practices
- varepsilon-fractional Core Stability in Hedonic Games
- Introducing NCL-SM: A Fully Annotated Dataset of Images from Human Skeletal Muscle Biopsies
- Radiology Report Generation Using Transformers Conditioned with Non-imaging Data
- On the Out of Distribution Robustness of Foundation Models in Medical Image Segmentation
- Flat Minima in Linear Estimation and an Extended Gauss Markov Theorem
- Deep Tensor Network
- Beyond Images: An Integrative Multi-modal Approach to Chest X-Ray Report Generation
- Combining EEG and NLP Features for Predicting Students' Lecture Comprehension using Ensemble Classification
- Compositional Fusion of Signals in Data Embedding
- ECLM: Efficient Edge-Cloud Collaborative Learning with Continuous Environment Adaptation
- DSCom: A Data-Driven Self-Adaptive Community-Based Framework for Influence Maximization in Social Networks
- Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning
- The Persian Piano Corpus: A Collection Of Instrument-Based Feature Extracted Data Considering Dastgah
- CueGCL: Cluster-aware Personalized Self-Training for Unsupervised Graph Contrastive Learning
- SBTRec- A Transformer Framework for Personalized Tour Recommendation Problem with Sentiment Analysis
- Enhancing Transformer-Based Segmentation for Breast Cancer Diagnosis using Auto-Augmentation and Search Optimisation Techniques
- AIMS-EREA -- A framework for AI-accelerated Innovation of Materials for Sustainability -- for Environmental Remediation and Energy Applications
- HIDRO-VQA: High Dynamic Range Oracle for Video Quality Assessment
- Tactics2D: A Highly Modular and Extensible Simulator for Driving Decision-making
- Challenges in data-based geospatial modeling for environmental research and practice
- Choose Your Simulator Wisely: A Review on Open-source Simulators for Autonomous Driving
- Designing Interpretable ML System to Enhance Trust in Healthcare: A Systematic Review to Proposed Responsible Clinician-AI-Collaboration Framework
- Classification of Major Depressive Disorder Using Vertex-Wise Brain Sulcal Depth, Curvature, and Thickness with a Deep and a Shallow Learning Model
- Orca 2: Teaching Small Language Models How to Reason
- Synthetic Data Generation for Bridging Sim2Real Gap in a Production Environment
- Data Center Audio/Video Intelligence on Device (DAVID) -- An Edge-AI Platform for Smart-Toys
- Geometric Data Augmentations to Mitigate Distribution Shifts in Pollen Classification from Microscopic Images
- Hyperbolic Space with Hierarchical Margin Boosts Fine-Grained Learning from Coarse Labels
- SORTAD: Self-Supervised Optimized Random Transformations for Anomaly Detection in Tabular Data
- Lesion Search with Self-supervised Learning
- Implicit Event-RGBD Neural SLAM
- Bit Cipher -- A Simple yet Powerful Word Representation System that Integrates Efficiently with Language Models
- Joyful: Joint Modality Fusion and Graph Contrastive Learning for Multimodal Emotion Recognition
- Gendec: A Machine Learning-based Framework for Gender Detection from Japanese Names
- Learning Scene Context Without Images
- BrainZ-BP: A Non-invasive Cuff-less Blood Pressure Estimation Approach Leveraging Brain Bio-impedance and Electrocardiogram
- Behavior Optimized Image Generation
- Towards Robust and Accurate Visual Prompting
- Expanding Scene Graph Boundaries: Fully Open-vocabulary Scene Graph Generation via Visual-Concept Alignment and Retention
- EdgeFM: Leveraging Foundation Model for Open-set Learning on the Edge
- Multiple View Geometry Transformers for 3D Human Pose Estimation
- Make Pixels Dance: High-Dynamic Video Generation
- Polynomial-Time Solutions for ReLU Network Training: A Complexity Classification via Max-Cut and Zonotopes
- Learning Deterministic Finite Automata from Confidence Oracles
- Classification Methods Based on Machine Learning for the Analysis of Fetal Health Data
- Journey of Hallucination-minimized Generative AI Solutions for Financial Decision Makers
- Structure-Aware Sparse-View X-ray 3D Reconstruction
All 119
- Taxonomic analysis of asteroids with artificial neural networks
- HungerGist: An Interpretable Predictive Model for Food Insecurity
- NAS-ASDet: An Adaptive Design Method for Surface Defect Detection Network using Neural Architecture Search
- Single-shot Phase Retrieval from a Fractional Fourier Transform Perspective
- An Empirical Bayes Framework for Open-Domain Dialogue Generation
- Deception Detection from Linguistic and Physiological Data Streams Using Bimodal Convolutional Neural Networks
- Partially Randomizing Transformer Weights for Dialogue Response Diversity
- Unsupervised Estimation of Ensemble Accuracy
- Bridging Data-Driven and Knowledge-Driven Approaches for Safety-Critical Scenario Generation in Automated Vehicle Validation
- Short-term Volatility Estimation for High Frequency Trades using Gaussian processes (GPs)
- Representing visual classification as a linear combination of words
- Cognitive bias in large language models: Cautious optimism meets anti-Panglossian meliorism
- CAMRA: Copilot for AMR Annotation
- Learning Payment-Free Resource Allocation Mechanisms
- Explainable Product Classification for Customs
- Compact and Intuitive Airfoil Parameterization Method through Physics-aware Variational Autoencoder
- Understanding and Mitigating Classification Errors Through Interpretable Token Patterns
- PACOL: Poisoning Attacks Against Continual Learners
- Jenga Stacking Based on 6D Pose Estimation for Architectural Form Finding Process