Papers
Sun 5 Nov 2023
110 papers
- Evaluating the Potential of Leading Large Language Models in Reasoning Biology QuestionsLLM reasoning → Clinical and biomedical applications
- AI-TA: Towards an Intelligent Question-Answer Teaching Assistant using Open-Source LLMsLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
- ChEF: A Comprehensive Evaluation Framework for Standardized Assessment of Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
- Octavius: Mitigating Task Interference in MLLMs via LoRA-MoEMixture-of-experts → Multimodal MoE models
- LLM-enhanced Self-training for Cross-domain Constituency ParsingSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
- GPT-4V-AD: Exploring Grounding Potential of VQA-oriented GPT-4V for Zero-shot Anomaly DetectionMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
- FloodBrain: Flood Disaster Reporting by Web-based Retrieval Augmented Generation with an LLMRetrieval-augmented generation → Agentic RAG, agents and memory
- UID as a Guiding Metric for Automated Authorship Obfuscation
- Ransomware Detection and Classification using Machine Learning
- Brain-Inspired Efficient Pruning: Exploiting Criticality in Spiking Neural Networks
- Procedural Fairness Through Decoupling Objectionable Data Generating Components
- Does Explainable AI Have Moral Value?
- Cross-layer scheme for low latency multiple description video streaming over Vehicular Ad-hoc NETworks (VANETs)
- Cross-Dialect Sentence Transformation: A Comparative Analysis of Language Models for Adapting Sentences to British English
- Gradual Optimization Learning for Conformational Energy Minimization
- Large language models implicitly learn to straighten neural sentence trajectories to construct a predictive representation of natural language
- Communication Efficient and Privacy-Preserving Federated Learning Based on Evolution Strategies
- CycleCL: Self-supervised Learning for Periodic Videos
- Enhancing AI Research Paper Analysis: Methodology Component Extraction using Factored Transformer-based Sequence Modeling Approach
- Differentially Private Pre-Trained Model Fusion using Decentralized Federated Graph Matching
- Newvision: application for helping blind people using deep learning
- Sketching Multidimensional Time Series for Fast Discord Mining
- Multi-channel learning for integrating structural hierarchies into context-dependent molecular representation
- Modelling Cellular Perturbations with the Sparse Additive Mechanism Shift Variational Autoencoder
- MirrorCalib: Utilizing Human Pose Information for Mirror-based Virtual Camera Calibration
- CausalCite: A Causal Formulation of Paper Citations
- Make a Donut: Hierarchical EMD-Space Planning for Zero-Shot Deformable Manipulation with Tools
- Towards Generic Anomaly Detection and Understanding: Large-scale Visual-linguistic Model (GPT-4V) Takes the Lead
- MuSHRoom: Multi-Sensor Hybrid Room Dataset for Joint 3D Reconstruction and Novel View Synthesis
- Robust Generalization Strategies for Morpheme Glossing in an Endangered Language Documentation Context
- Attention or Convolution: Transformer Encoders in Audio Language Models for Inference Efficiency
- Riemannian Laplace Approximation with the Fisher Metric
- Rule Learning as Machine Translation using the Atomic Knowledge Bank
- Log-Concavity of Multinomial Likelihood Functions Under Interval Censoring Constraints on Frequencies or Their Partial Sums
- Fast Sparse 3D Convolution Network with VDB
- One-Shot Strategic Classification Under Unknown Costs
- Causal Question Answering with Reinforcement Learning
- Certified Defense on the Fairness of Graph Neural Networks
- Fast Point Cloud to Mesh Reconstruction for Deformable Object Tracking
- Pyclipse, a library for deidentification of free-text clinical notes
- Attention Modules Improve Image-Level Anomaly Detection for Industrial Inspection: A DifferNet Case Study
- Staged Reinforcement Learning for Complex Tasks through Decomposed Environments
- Learning Independently from Causality in Multi-Agent Environments
- Scenario Diffusion: Controllable Driving Scenario Generation With Diffusion
- JRDB-Traj: A Dataset and Benchmark for Trajectory Forecasting in Crowds
- ISAR: A Benchmark for Single- and Few-Shot Object Instance Segmentation and Re-Identification
- AV-Lip-Sync+: Leveraging AV-HuBERT to Exploit Multimodal Inconsistency for Deepfake Detection of Frontal Face Videos
- Uncertainty Estimation for Safety-critical Scene Segmentation via Fine-grained Reward Maximization
- Exploiting Correlated Auxiliary Feedback in Parameterized Bandits
- Benchmarking a Benchmark: How Reliable is MS-COCO?
- An Empirical Study of Uncertainty in Polygon Annotation and the Impact of Quality Assurance
- A Goal-Driven Approach to Systems Neuroscience
- Extraction of Atypical Aspects from Customer Reviews: Datasets and Experiments with Language Models
- A Generative Multi-Resolution Pyramid and Normal-Conditioning 3D Cloth Draping
- Nepali Video Captioning using CNN-RNN Architecture
- Identifying Linearly-Mixed Causal Representations from Multi-Node Interventions
- Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learning
- Regret Analysis of Learning-Based Linear Quadratic Gaussian Control with Additive Exploration
- Digital Typhoon: Long-term Satellite Image Dataset for the Spatio-Temporal Modeling of Tropical Cyclones
- Enhanced adaptive cross-layer scheme for low latency HEVC streaming over Vehicular Ad-hoc Networks (VANETs)
- CCMR: High Resolution Optical Flow Estimation via Coarse-to-Fine Context-Guided Motion Reasoning
- Region of Interest (ROI) based adaptive cross-layer system for real-time video streaming over Vehicular Ad-hoc NETworks (VANETs)
- Compute at Scale: A Broad Investigation into the Data Center Industry
- Generative Face Video Coding Techniques and Standardization Efforts: A Review
- Drone-Enabled Load Management for Solar Small Cell Networks in Next-Gen Communications Optimization for Solar Small Cells
- New Approach for an Affective Computing-Driven Quality of Experience (QoE) Prediction
- An Approach for Multi-Object Tracking with Two-Stage Min-Cost Flow
- PotholeGuard: A Pothole Detection Approach by Point Cloud Semantic Segmentation
- Assessing the Promise and Pitfalls of ChatGPT for Automated Code Generation
- The Background Also Matters: Background-Aware Motion-Guided Objects Discovery
- A Critical Perceptual Pre-trained Model for Complex Trajectory Recovery
- The New Frontier of Cybersecurity: Emerging Threats and Innovations
- Pointer Networks with Q-Learning for Combinatorial Optimization
- Hierarchical Simplicity Bias of Neural Networks
- AIOps-Driven Enhancement of Log Anomaly Detection in Unsupervised Scenarios
- TFNet: Tuning Fork Network with Neighborhood Pixel Aggregation for Improved Building Footprint Extraction
- Divide & Conquer for Entailment-aware Multi-hop Evidence Retrieval
- An adaptive standardisation methodology for Day-Ahead electricity price forecasting
- Deep Learning-based 3D Point Cloud Classification: A Systematic Survey and Outlook
- Get the Ball Rolling: Alerting Autonomous Robots When to Help to Close the Healthcare Loop
- Optimizing Implicit Neural Representations from Point Clouds via Energy-Based Models
- Learning Class and Domain Augmentations for Single-Source Open-Domain Generalization
- Automated Camera Calibration via Homography Estimation with GNNs
- scBeacon: single-cell biomarker extraction via identifying paired cell clusters across biological conditions with contrastive siamese networks
- Synthetic Tumor Manipulation: With Radiomics Features
- FSDA-DG: Improving Cross-Domain Generalizability of Medical Image Segmentation with Few Source Domain Annotations
- mahaNLP: A Marathi Natural Language Processing Library
- Temporal Sequencing of Documents
- Steady-State Analysis and Online Learning for Queues with Hawkes Arrivals
- Group Testing for Accurate and Efficient Range-Based Near Neighbor Search for Plagiarism Detection
- Multiple Object Tracking based on Occlusion-Aware Embedding Consistency Learning
- BanMANI: A Dataset to Identify Manipulated Social Media News in Bangla
- Topic model based on co-occurrence word networks for unbalanced short text datasets
- KITS: Inductive Spatio-Temporal Kriging with Increment Training Strategy
- Relation Extraction Model Based on Semantic Enhancement Mechanism
- Time Series Synthesis Using the Matrix Profile for Anonymization
- Ego-Network Transformer for Subsequence Classification in Time Series Data
- Temporal Treasure Hunt: Content-based Time Series Retrieval System for Discovering Insights
- Rotation Invariant Transformer for Recognizing Object in UAVs
- Multi-Agent 3D Map Reconstruction and Change Detection in Microgravity with Free-Flying Robots
All 110
- Fast Minimization of Expected Logarithmic Loss via Stochastic Dual Averaging
- IPVNet: Learning Implicit Point-Voxel Features for Open-Surface 3D Reconstruction
- High-dimensional Bid Learning for Energy Storage Bidding in Energy Markets
- 3D-Aware Talking-Head Video Motion Transfer
- On the Second-Order Convergence of Biased Policy Gradient Algorithms
- Multi-objective Reinforcement Learning with Nonlinear Preferences: Provable Approximation for Maximizing Expected Scalarized Return
- VR-NeRF: High-Fidelity Virtualized Walkable Spaces
- Dense Video Captioning: A Survey of Techniques, Datasets and Evaluation Protocols
- Augment the Pairs: Semantics-Preserving Image-Caption Pair Augmentation for Grounding-Based Vision and Language Models
- TokenMotion: Motion-Guided Vision Transformer for Video Camouflaged Object Detection Via Learnable Token Selection