Papers
Sat 30 Dec 2023
84 papers
- Improving the Stability and Efficiency of Diffusion Models for Content Consistent Super-ResolutionDiffusion models → Inverse problems and image restoration
- FlashVideo: A Framework for Swift Inference in Text-to-Video GenerationDiffusion models → Video generation
- Explainability-Driven Leaf Disease Classification Using Adversarial Training and Knowledge DistillationKnowledge distillation → Detection and dense prediction distillation
- Red Teaming for Large Language Models At Scale: Tackling Hallucinations on Mathematics TasksLLM safety and security → Prompt injection and agent security
- Advancing TTP Analysis: Harnessing the Power of Large Language Models with Retrieval Augmented GenerationRetrieval-augmented generation → Privacy and security of RAG
- COMMA: Co-Articulated Multi-Modal LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Probing the Limits and Capabilities of Diffusion Models for the Anatomic Editing of Digital TwinsDiffusion models → Medical imaging and segmentation
- Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA EnsemblesLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
- The Problem of AlignmentLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
- Inpaint4DNeRF: Promptable Spatio-Temporal NeRF Inpainting with Generative Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
- ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge GraphLLM reasoning → Knowledge- and tool-augmented reasoning
- Enhancing Causal Reasoning in Large Language Models: A Causal Attribution Model for Precision Fine-TuningLLM reasoning → Causal reasoning in LLMs +1
- Pushing Boundaries: Exploring Zero Shot Object Classification with Large Multimodal ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
- LLM-Assist: Enhancing Closed-Loop Planning with Language-Based ReasoningLLM reasoning → Chain-of-thought reasoning for driving
- Diffusion Model with Perceptual LossDiffusion models → Diffusion foundations and sampling
- Deploying ADVISER: Impact and Lessons from Using Artificial Intelligence for Child Vaccination Uptake in Nigeria
- Symbolic Cognitive Diagnosis via Hybrid Optimization for Intelligent Education Systems
- What's my role? Modelling responsibility for AI-based safety-critical systems
- A Toolbox for Modelling Engagement with Educational Videos
- Machine Learning (ML)-assisted Beam Management in millimeter (mm)Wave Distributed Multiple Input Multiple Output (D-MIMO) systems
- WildGEN: Long-horizon Trajectory Generation for Wildlife
- HoloBeam: Learning Optimal Beamforming in Far-Field Holographic Metasurface Transceivers
- Why is the User Interface a Dark Pattern? : Explainable Auto-Detection and its Analysis
- Trace and Edit Relation Associations in GPT
- Uncovering Regulatory Affairs Complexity in Medical Products: A Qualitative Assessment Utilizing Open Coding and Natural Language Processing (NLP)
- Mapping Walnut Water Stress with High Resolution Multispectral UAV Imagery and Machine Learning
- 3D Human Pose Perception from Egocentric Stereo Videos
- Attractor reconstruction with reservoir computers: The effect of the reservoir's conditional Lyapunov exponents on faithful attractor reconstruction
- Automating Leukemia Diagnosis with Autoencoders: A Comparative Study
- Towards Bridging the Gap between High-Level Reasoning and Execution on Robots
- Balanced Graph Structure Information for Brain Disease Detection
- Unifying Self-Supervised Clustering and Energy-Based Models
- PlanarNeRF: Online Learning of Planar Primitives with Neural Radiance Fields
- ConfusionPrompt: Practical Private Inference for Online Large Language Models
- SHARE: Single-view Human Adversarial REconstruction
- Two-Step Offline Preference-Based Reinforcement Learning with Constrained Actions
- On the Burstiness of Distributed Machine Learning Traffic
- DXAI: Explaining Classification by Image Decomposition
- Bidirectional Temporal Plan Graph: Enabling Switchable Passing Orders for More Efficient Multi-Agent Path Finding Plan Execution
- GAN-GA: A Generative Model based on Genetic Algorithm for Medical Image Generation
- Matching of Users and Creators in Two-Sided Markets with Departures
- Principal-Agent Reward Shaping in MDPs
- A Novel Reinforcement Learning Routing Algorithm for Congestion Control in Complex Networks
- Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit
- The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness
- BusReF: Infrared-Visible images registration and fusion focus on reconstructible area using one set of features
- Evaluation is all you need. Prompting Generative Large Language Models for Annotation Tasks in the Social Sciences. A Primer using Open Models
- Deep Generative Symbolic Regression
- Second-Order Uncertainty Quantification: Variance-Based Measures
- An ℓ1-Plug-and-Play Approach for MPI Using a Zero Shot Denoiser with Evaluation on the 3D Open MPI Dataset
- Investigating Zero-Shot Generalizability on Mandarin-English Code-Switched ASR and Speech-to-text Translation of Recent Foundation Models with Self-Supervision and Weak Supervision
- HybridGait: A Benchmark for Spatial-Temporal Cloth-Changing Gait Recognition with Hybrid Explorations
- GazeCLIP: Enhancing Gaze Estimation Through Text-Guided Multimodal Learning
- Morphing Tokens Draw Strong Masked Image Models
- Promoting Segment Anything Model towards Highly Accurate Dichotomous Image Segmentation
- Boosting Large Language Model for Speech Synthesis: An Empirical Study
- Laboratory Experiments of Model-based Reinforcement Learning for Adaptive Optics Control
- Image Super-Resolution Reconstruction Network based on Enhanced Swin Transformer via Alternating Aggregation of Local-Global Features
- How to Evaluate Coreference in Literary Texts?
- A Novel Approach for Defect Detection of Wind Turbine Blade Using Virtual Reality and Deep Learning
- Transformer Multivariate Forecasting: Less is More?
- Enhancing dysarthria speech feature representation with empirical mode decomposition and Walsh-Hadamard transform
- Open-TI: Open Traffic Intelligence with Augmented Language Model
- AI and Tempo Estimation: A Review
- KAXAI: An Integrated Environment for Knowledge Analysis and Explainable AI
- A Novel Explanation Against Linear Neural Networks
- Principle Interference in Technical and Scientific Translation
- L3Cube-MahaSocialNER: A Social Media based Marathi NER Dataset and BERT models
- Mitigating the Impact of False Negatives in Dense Retrieval with Contrastive Confidence Regularization
- A clean-label graph backdoor attack method in node classification task
- Policy Optimization with Smooth Guidance Learned from State-Only Demonstrations
- DiffHybrid-UQ: Uncertainty Quantification for Differentiable Hybrid Neural Modeling
- Automatic hip osteoarthritis grading with uncertainty estimation from computed tomography using digitally-reconstructed radiographs
- A comprehensive framework for occluded human pose estimation
- CamPro: Camera-based Anti-Facial Recognition
- TPatch: A Triggered Physical Adversarial Patch
- SSL-OTA: Unveiling Backdoor Threats in Self-Supervised Learning for Object Detection
- Deep Radon Prior: A Fully Unsupervised Framework for Sparse-View CT Reconstruction
- Unicron: Economizing Self-Healing LLM Training at Scale
- Contrastive learning-based agent modeling for deep reinforcement learning
- Quantifying intra-tumoral genetic heterogeneity of glioblastoma toward precision medicine using MRI and a data-inclusive machine learning algorithm
- SALSA: Sequential Approximate Leverage-Score Algorithm with Application in Analyzing Big Time Series Data
- A Maritime Industry Experience for Vessel Operational Anomaly Detection: Utilizing Deep Learning Augmented with Lightweight Interpretable Models
- Causal State Distillation for Explainable Reinforcement Learning