Papers

New on arXiv

Wed 17 Jan 2024

216 papers

Federated Unlearning for Human Activity RecognitionLLM safety and security → Federated unlearning and poisoning
Machine Unlearning for Recommendation Systems: An InsightLLM safety and security → Membership inference attacks
Crowd-PrefRL: Preference-Based Reward Learning from CrowdsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
SeeClick: Harnessing GUI Grounding for Advanced Visual GUI AgentsLLM agents and tool use → GUI and mobile agents
A New Creative Generation Pipeline for Click-Through Rate with Stable Diffusion ModelDiffusion models → Image generation, text-to-image and editing
Efficient generative adversarial networks using linear additive-attention TransformersDiffusion models → Diffusion foundations and sampling
Aligning Large Language Models with Counterfactual DPOLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Sharing Knowledge in Multi-Task Deep Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
Improving Classification Performance With Human Feedback: Label a few, we label the restLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space ModelState-space sequence models (S4, Mamba) → Vision Mamba backbones
Evaluating LLMs' Mathematical and Coding Competency through Ontology-guided InterventionsLLM reasoning → Mathematical reasoning
CognitiveDog: Large Multimodal Model Based System to Translate Vision and Language into Action of Quadruped RobotMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Large Language Models Are Neurosymbolic ReasonersLLM reasoning → Reasoning for agents, planning and code +1
Synergistic Reinforcement and Imitation Learning for Vision-driven Autonomous Flight of UAV Along RiverOffline RL and imitation learning from data → Imitation learning methods
Siamese Meets Diffusion Network: SMDNet for Enhanced Change Detection in High-Resolution RS ImageryDiffusion models → Inverse problems and image restoration
T-FOLEY: A Controllable Waveform-Domain Diffusion Model for Temporal-Event-Guided Foley Sound SynthesisDiffusion models → Audio, speech and music
Deployable Reinforcement Learning with Variable Control RateDeep reinforcement learning methods → RL theory and sample complexity
Training-Free Semantic Video Composition via Pre-trained Diffusion ModelDiffusion models → Video generation
Beyond Anti-Forgetting: Multimodal Continual Instruction Tuning with Positive Forward TransferMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
UniVG: Towards UNIfied-modal Video GenerationDiffusion models → Video generation
Should agentic conversational AI change how we think about ethics? Characterising an interactional ethics centred on respectLLM reasoning → Reasoning benchmarks and evaluation +1
Compose and Conquer: Diffusion-Based 3D Depth Aware Composable Image SynthesisDiffusion models → 3D, point cloud and scene generation
VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion ModelsDiffusion models → Video generation
LLMs for Relational Reasoning: How Far are We?LLM reasoning → Reasoning benchmarks and evaluation
UOEP: User-Oriented Exploration Policy for Enhancing Long-Term User Experiences in Recommender SystemsDeep reinforcement learning methods → RL training of language and agent models
Data Attribution for Diffusion Models: Timestep-induced Bias in Influence EstimationDiffusion models → Diffusion foundations and sampling
Augmenting Math Word Problems via Iterative Question ComposingLLM reasoning → Mathematical reasoning
AttackEval: How to Evaluate the Effectiveness of Jailbreak Attacking on Large Language ModelsLLM safety and security → Jailbreaking
Continuous Time Continuous Space Homeostatic Reinforcement Learning (CTCS-HRRL) : Towards Biological Self-Autonomous AgentDeep reinforcement learning methods → Deep RL algorithms and representations
Attack and Reset for Unlearning: Exploiting Adversarial Noise toward Machine Unlearning through Parameter Re-initializationLLM safety and security → Machine unlearning
A GAN-based data poisoning framework against anomaly detection in vertical federated learningLLM safety and security → Federated unlearning and poisoning
COCO is "ALL'' You Need for Visual Instruction Fine-tuningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
ReFT: Reasoning with Reinforced Fine-TuningLLM reasoning → Test-time compute and efficient thinking
Cascading Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
From User Surveys to Telemetry-Driven AI Agents: Exploring the Potential of Personalized Productivity SolutionsLLM agents and tool use → General LLM agent frameworks and benchmarks
Towards Off-Policy Reinforcement Learning for Ranking Policies with Human FeedbackDeep reinforcement learning methods → RL training of language and agent models
PADS: Plug-and-Play 3D Human Pose Analysis via Diffusion Generative ModelingDiffusion models → 3D, point cloud and scene generation
Bridging State and History Representations: Understanding Self-Predictive RLDeep reinforcement learning methods → Deep RL algorithms and representations
Hybrid deep learning and physics-based neural network for programmable illumination computational microscopy
Precision Mars Entry Navigation with Atmospheric Density Adaptation via Neural Networks
Inverse analysis of granular flows using differentiable graph neural network simulator
Estimating the severity of dental and oral problems via sentiment classification over clinical reports
TranSentence: Speech-to-speech Translation via Language-agnostic Sentence-level Speech Encoding without Language-parallel Data
Computing in the Era of Large Generative Models: From Cloud-Native to AI-Native
RELIANCE: Reliable Ensemble Learning for Information and News Credibility Evaluation
Even-if Explanations: Formal Foundations, Priorities and Complexity
Subjective Causality
Tight Group-Level DP Guarantees for DP-SGD with Sampling via Mixture of Gaussians Mechanisms
Symmetry breaking in geometric quantum machine learning in the presence of noise
Early Prediction of Geomagnetic Storms by Machine Learning Algorithms
Design and development of opto-neural processors for simulation of neural networks trained in image detection for potential implementation in hybrid robotics
Self-supervised New Activity Detection in Sensor-based Smart Environments
A novel hybrid time-varying graph neural network for traffic flow forecasting
Exploiting Hierarchical Interactions for Protein Surface Learning
Convex and Bilevel Optimization for Neuro-Symbolic Inference and Learning
Large Language Models Help Reveal Unhealthy Diet and Body Concerns in Online Eating Disorders Communities
ClimateGPT: Towards AI Synthesizing Interdisciplinary Research on Climate Change
Functional Linear Non-Gaussian Acyclic Model for Causal Discovery
Blackout Mitigation via Physics-guided RL
Uncertainty Modeling in Ultrasound Image Segmentation for Precise Fetal Biometric Measurements
Automatic 3D Multi-modal Ultrasound Segmentation of Human Placenta using Fusion Strategies and Deep Learning
Impact of Large Language Model Assistance on Patients Reading Clinical Notes: A Mixed-Methods Study
Physics-Informed Calibration of Aeromagnetic Compensation in Magnetic Navigation Systems using Liquid Time-Constant Networks
CT Liver Segmentation via PVT-based Encoding and Refined Decoding
Multiple Locally Linear Kernel Machines
SymTC: A Symbiotic Transformer-CNN Net for Instance Segmentation of Lumbar Spine MRI
MITS-GAN: Safeguarding Medical Imaging from Tampering with Generative Adversarial Networks
Is Hyper-Parameter Optimization Different for Software Analytics?
Learning Shortcuts: On the Misleading Promise of NLU in Language Models
Land Cover Image Classification
Robustness Evaluation of Machine Learning Models for Robot Arm Action Recognition in Noisy Environments
MedBlindTuner: Towards Privacy-preserving Fine-tuning on Biomedical Images with Transformers and Fully Homomorphic Encryption
Evaluating tree-based imputation methods as an alternative to MICE PMM for drawing inference in empirical studies
Bilevel Optimization under Unbounded Smoothness: A New Algorithm and Convergence Analysis
eipy: An Open-Source Python Package for Multi-modal Data Integration using Heterogeneous Ensembles
Fully-blind Neural Network Based Equalization for Severe Nonlinear Distortions in 112 Gbit/s Passive Optical Networks
Towards Scalable and Robust Model Versioning
Handling Large-scale Cardinality in building recommendation systems
Deep learning enhanced mixed integer optimization: Learning to reduce model dimensionality
BERTologyNavigator: Advanced Question Answering with BERT-based Semantics
On-Off Pattern Encoding and Path-Count Encoding as Deep Neural Network Representations
Dimensional Neuroimaging Endophenotypes: Neurobiological Representations of Disease Heterogeneity Through Machine Learning
Accelerating Data Generation for Neural Operators via Krylov Subspace Recycling
Enhancing Surveillance Camera FOV Quality via Semantic Line Detection and Classification with Deep Hough Transform
Community Detection in the Multi-View Stochastic Block Model
Exploration of Activation Fault Reliability in Quantized Systolic Array-Based DNN Accelerators
Deep Ensemble Shape Calibration: Multi-Field Post-hoc Calibration in Online Advertising
MorphGrower: A Synchronized Layer-by-layer Growing Approach for Plausible Neuronal Morphology Generation
Functional Autoencoder for Smoothing and Representation Learning
Technical Report: On the Convergence of Gossip Learning in the Presence of Node Inaccessibility
Learning to Generalize over Subpartitions for Heterogeneity-aware Domain Adaptive Nuclei Segmentation
IPR-NeRF: Ownership Verification meets Neural Radiance Field
VeriBug: An Attention-based Framework for Bug-Localization in Hardware Designs
Identifying Three-Dimensional Radiative Patterns Associated with Early Tropical Cyclone Intensification
GARField: Group Anything with Radiance Fields
TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusion
Randomized Kaczmarz with geometrically smoothed momentum
Vlogger: Make Your Dream A Vlog
POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images
Through the Looking-Glass: Transparency Implications and Challenges in Enterprise AI Knowledge Systems

All 216