Papers

New on arXiv

Sun 10 Nov 2024

119 papers

InvisMark: Invisible and Robust Watermarking for AI-generated Image ProvenanceLLM safety and security → Watermarking generated content and models
Multi-hop Upstream Anticipatory Traffic Signal Control with Deep Reinforcement LearningDeep reinforcement learning methods → RL for autonomous driving and traffic
Using Diffusion Models as Generative Replay in Continual Federated Learning -- What will Happen?Diffusion models → Robustness, privacy and adversarial aspects
vTune: Verifiable Fine-Tuning for LLMs Through BackdooringLLM safety and security → Safety alignment, refusal and guardrails
OffLight: An Offline Multi-Agent Reinforcement Learning Framework for Traffic Signal ControlOffline RL and imitation learning from data → Imitation and offline RL for driving
Meta-Learning Objectives for Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web AgentsWorld models → World models for language agents +1
CASC: Condition-Aware Semantic Communication with Latent Diffusion ModelsDiffusion models → Diffusion for compression and wireless
Diffusion Sampling Correction via Approximately 10 ParametersDiffusion models → Diffusion foundations and sampling
KMM: Key Frame Mask Mamba for Extended Motion GenerationState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
RL-Pruner: Structured Pruning Using Reinforcement Learning for CNN Compression and AccelerationDeep reinforcement learning methods → Deep RL algorithms and representations
Improved Video VAE for Latent Video Diffusion ModelDiffusion models → Diffusion foundations and sampling
Over-parameterized Student Model via Tensor Decomposition Boosted Knowledge DistillationKnowledge distillation → General knowledge distillation methods
Detecting AutoEncoder is Enough to Catch LDM Generated ImagesDiffusion models → Image generation, text-to-image and editing
Conditional [MASK] Discrete Diffusion Language ModelDiffusion models → Discrete and text diffusion
Reinforcement learning for Quantum Tiq-Taq-ToeDeep reinforcement learning methods → Quantum reinforcement learning
SequentialBreak: Large Language Models Can be Fooled by Embedding Jailbreak Prompts into Sequential Prompt ChainsLLM safety and security → Jailbreaking
How Does DPO Reduce Toxicity? A Mechanistic Neuron-Level AnalysisLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
A Variance Minimization Approach to Temporal-Difference LearningDeep reinforcement learning methods → RL theory and sample complexity
Optimal Execution with Reinforcement LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance
Self-Training Meets Consistency: Improving LLMs' Reasoning with Consistency-Driven Rationale EvaluationLLM reasoning → Test-time compute and efficient thinking +1
EconoServe: Maximizing Multi-Resource Utilization with SLO Guarantees in LLM ServingEfficient LLM inference and serving → Serving systems and request scheduling
Universal on-chip polarization handling with deep photonic networks
Recurrent Joint Embedding Predictive Architecture with Recurrent Forward Propagation Learning
Reaction-conditioned De Novo Enzyme Design with GENzyme
Unlearn to Relearn Backdoors: Deferred Backdoor Functionality Attacks on Deep Learning Models
Balancing Speed and Stability: The Trade-offs of FP8 vs. BF16 Training in LLMs
MatPilot: an LLM-enabled AI Materials Scientist under the Framework of Human-Machine Collaboration
Feature Fusion Transferability Aware Transformer for Unsupervised Domain Adaptation
ASTD Patterns for Integrated Continuous Anomaly Detection In Data Logs
Few-shot Semantic Learning for Robust Multi-Biome 3D Semantic Mapping in Off-Road Environments
Exploring social bots: A feature-based approach to improve bot detection in social networks
A Review of Fairness and A Practical Guide to Selecting Context-Appropriate Fairness Metrics in Machine Learning
MEANT: Multimodal Encoder for Antecedent Information
Are Neuromorphic Architectures Inherently Privacy-preserving? An Exploratory Study
MolMiner: Toward Controllable, 3D-Aware, Fragment-Based Molecular Design
Gen-AI for User Safety: A Survey
Adaptive and Temporally Consistent Gaussian Surfels for Multi-view Dynamic Reconstruction
Few measurement shots challenge generalization in learning to classify entanglement
Graph Neural Networks for modelling breast biomechanical compression
CriticAL: Critic Automation with Language Models
Enhancing frozen histological section images using permanent-section-guided deep learning with nuclei attention
HAFLQ: Heterogeneous Adaptive Federated LoRA Fine-tuned LLM with Quantization
Discovering emergent connections in quantum physics research via dynamic word embeddings
An Energy-Based Self-Adaptive Learning Rate for Stochastic Gradient Descent: Enhancing Unconstrained Optimization with VAV method
Fitting Multiple Machine Learning Models with Performance Based Clustering
Foundation Model for Composite Microstructures: Reconstruction, Stiffness, and Nonlinear Behavior Prediction
Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement
The KIPARLA Forest treebank of spoken Italian: an overview of initial design choices
Extended multi-stream temporal-attention module for skeleton-based human action recognition (HAR)
In-Context Learning for Preserving Patient Privacy: A Framework for Synthesizing Realistic Patient Portal Messages
CineXDrama: Relevance Detection and Sentiment Analysis of Bangla YouTube Comments on Movie-Drama using Transformers: Insights from Interpretability Tool
Is Linear Feedback on Smoothed Dynamics Sufficient for Stabilizing Contact-Rich Plans?
A Next-Generation Approach to Airline Reservations: Integrating Cloud Microservices with AI and Blockchain for Enhanced Operational Performance
Probabilistic Consensus through Ensemble Validation: A Framework for LLM Reliability
Image Segmentation from Shadow-Hints using Minimum Spanning Trees
Thermodynamically-Informed Iterative Neural Operators for Heterogeneous Elastic Localization
Epistemic Integrity in Large Language Models
I2VControl-Camera: Precise Video Camera Control with Adjustable Motion Strength
Does This Summary Answer My Question? Modeling Query-Focused Summary Readers with Rational Speech Acts
Causal Representation Learning from Multimodal Biomedical Observations
PRISM: Privacy-preserving Inter-Site MRI Harmonization via Disentangled Representation Learning
Offline Handwritten Signature Verification Using a Stream-Based Approach
Understanding the Role of Equivariance in Self-supervised Learning
CULL-MT: Compression Using Language and Layer pruning for Machine Translation
Individual Regret in Cooperative Stochastic Multi-Armed Bandits
Graph Neural Network Surrogates to leverage Mechanistic Expert Knowledge towards Reliable and Immediate Pandemic Response
Mitigating covariate shift in non-colocated data with learned parameter priors
Barriers to Complexity-Theoretic Proofs that "AGI" Using Machine Learning is Impossible
LProtector: An LLM-driven Vulnerability Detection System
Hermes: A Large Language Model Framework on the Journey to Autonomous Networks
DDIM-Driven Coverless Steganography Scheme with Real Key
Superpixel Segmentation: A Long-Lasting Ill-Posed Problem
VocalTweets: Investigating Social Media Offensive Language Among Nigerian Musicians
ClinicalBench: Can LLMs Beat Traditional ML Models in Clinical Prediction?
Accelerating Large Language Model Training with 4D Parallelism and Memory Consumption Estimator
Dropout the High-rate Downsampling: A Novel Design Paradigm for UHD Image Restoration
Multi-Parameter Molecular MRI Quantification using Physics-Informed Self-Supervised Learning
Prompt-Efficient Fine-Tuning for GPT-like Deep Models to Reduce Hallucination and to Improve Reproducibility in Scientific Text Generation Using Stochastic Optimisation Techniques
SamRobNODDI: Q-Space Sampling-Augmented Continuous Representation Learning for Robust and Generalized NODDI
Local Implicit Wavelet Transformer for Arbitrary-Scale Super-Resolution
CTC-Assisted LLM-Based Contextual ASR
Predictors of disease outbreaks at continentalscale in the African region: Insights and predictions with geospatial artificial intelligence using earth observations and routine disease surveillance data
Neuro-Symbolic Rule Lists
UniGAD: Unifying Multi-level Graph Anomaly Detection
Generating Mixcode Popular Songs with Artificial Intelligence: Concepts, Plans, and Speculations
Automated Strategy Invention for Confluence of Term Rewrite Systems
Locally Adaptive One-Class Classifier Fusion with Dynamic ℓp-Norm Constraints for Robust Anomaly Detection
Overcoming a Learning Bottleneck in Impartial Games: A Circuit Complexity Approach
Fineweb-Edu-Ar: Machine-translated Corpus to Support Arabic Small Language Models
A Hybrid Approach for COVID-19 Detection: Combining Wasserstein GAN with Transfer Learning
Local vs. Global Models for Hierarchical Forecasting
CausalStock: Deep End-to-end Causal Discovery for News-driven Stock Movement Prediction
SplatFormer: Point Transformer for Robust 3D Gaussian Splatting
Class Granularity: How richly does your knowledge graph represent the real world?
SAN: Structure-Aware Network for Complex and Long-tailed Chinese Text Recognition
PKF: Probabilistic Data Association Kalman Filter for Multi-Object Tracking
The Phantom of PCIe: Constraining Generative Artificial Intelligences for Practical Peripherals Trace Synthesizing
Metric Learning for Tag Recommendation: Tackling Data Sparsity and Cold Start Issues
LLM Vocabulary Compression for Low-Compute Environments

All 119