Papers

New on arXiv

Sat 2 Nov 2024

127 papers

What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind AttacksLLM safety and security → Jailbreaking +1
TODO: Enhancing LLM Alignment with Ternary PreferencesLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
WaKA: Data Attribution using K-Nearest Neighbors and Membership Privacy PrinciplesLLM safety and security → Membership inference attacks
Guided Synthesis of Labeled Brain MRI Data Using Latent Diffusion Models for Segmentation of Enlarged VentriclesDiffusion models → Medical imaging and segmentation
The Role of Domain Randomization in Training Diffusion Policies for Whole-Body Humanoid ControlDiffusion models → Diffusion and flow policies for robotics
Privacy Leakage Overshadowed by Views of AI: A Study on Human Oversight of Privacy in Language Model AgentLLM agents and tool use → Agent threats, guardrails and governance
Adaptive World Models: Learning Behaviors by Latent Imagination Under Non-StationarityWorld models → World models for navigation
Can Multimodal Large Language Model Think Analogically?LLM reasoning → Multimodal reasoning +1
Diffusion Models as Cartoonists: The Curious Case of High Density RegionsDiffusion models → Diffusion foundations and sampling
Hexa-MoE: Efficient and Heterogeneous-aware Training for Mixture-of-ExpertsMixture-of-experts → Efficient MoE training and inference systems
Interacting Large Language Model Agents. Interpretable Models and Social LearningLLM agents and tool use → Social simulation and multi-agent debate
ProGen: Revisiting Probabilistic Spatial-Temporal Time Series Forecasting from a Continuous Generative Perspective Using Stochastic Differential EquationsDiffusion models → Flow matching, time series and science
PMoL: Parameter Efficient MoE for Preference Mixing of LLM AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
B4: A Black-Box Scrubbing Attack on LLM WatermarksLLM safety and security → Watermarking generated content and models
Enhancing Neural Network Interpretability with Feature-Aligned Sparse AutoencodersMechanistic interpretability → Sparse autoencoder training and evaluation
Infinite-Resolution Integral Noise Warping for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
GarmentLab: A Unified Simulation and Benchmark for Garment ManipulationDeep reinforcement learning methods → RL for robot locomotion and manipulation
Hollowed Net for On-Device Personalization of Text-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
Reasoning Limitations of Multimodal Large Language Models. A Case Study of Bongard ProblemsLLM reasoning → Multimodal reasoning +1
Fast and Memory-Efficient Video Diffusion Using Streamlined InferenceDiffusion models → Video generation
Prompt Tuning with Diffusion for Few-Shot Pre-trained Policy GeneralizationOffline RL and imitation learning from data → Diffusion and flow policies for offline RL +1
Supervised Score-Based Modeling by Gradient BoostingDiffusion models → Diffusion foundations and sampling
Task-Aware Harmony Multi-Task Decision Transformer for Offline Reinforcement LearningOffline RL and imitation learning from data → Decision transformers and sequence modeling
NEO: Saving GPU Memory Crisis with CPU Offloading for Online LLM InferenceEfficient LLM inference and serving → Serving systems and request scheduling
Dictionary Insertion Prompting for Multilingual Reasoning on Multilingual Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
X-Drive: Cross-modality consistent multi-sensor data synthesis for driving scenariosWorld models → World modeling from LiDAR generation +1
Infant Agent: A Tool-Integrated, Logic-Driven Agent with Cost-Effective API UsageLLM agents and tool use → General LLM agent frameworks and benchmarks
Rule Based Rewards for Language Model SafetyLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document UnderstandingMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
Self-Consistency Falls Short! The Adverse Effects of Positional Bias on Long-Context ProblemsLLM reasoning → Test-time compute and efficient thinking
TabVer: Tabular Fact Verification with Natural LogicLLM reasoning → Knowledge- and tool-augmented reasoning
PRISM: A Personalized, Rapid, and Immersive Skill Mastery framework for personalizing experiential learning through Generative AI
FinBERT-BiLSTM: A Deep Learning Model for Predicting Volatile Cryptocurrency Market Prices Using Market Sentiment Dynamics
Longitudinal Wrist PPG Analysis for Reliable Hypertension Risk Screening Using Deep Learning
Machine Learning Assisted Postural Movement Recognition using Photoplethysmography(PPG)
Utilizing Human Behavior Modeling to Manipulate Explanations in AI-Assisted Decision Making: The Good, the Bad, and the Scary
Open LLMs are Necessary for Current Private Adaptations and Outperform their Closed Alternatives
Interpretable Embeddings for Segmentation-Free Single-Cell Analysis in Multiplex Imaging
Unlocking the Archives: Using Large Language Models to Transcribe Handwritten Historical Documents
MADOD: Generalizing OOD Detection to Unseen Domains via G-Invariance Meta-Learning
Cross-D Conv: Cross-Dimensional Transferable Knowledge Base via Fourier Shifting Operation
Entropic Hetero-Associative Memory
TypeScore: A Text Fidelity Metric for Text-to-Image Generative Models
Multi-Channel Hypergraph Contrastive Learning for Matrix Completion
Learning with Hidden Factorial Structure
Medical X-Ray Image Enhancement Using Global Contrast-Limited Adaptive Histogram Equalization
Network Causal Effect Estimation In Graphical Models Of Contagion And Latent Confounding
Artificial Intelligence Driven Course Generation: A Case Study Using ChatGPT
Use Digital Twins to Support Fault Diagnosis From System-level Condition-monitoring Data
Online and Offline Evaluations of Collaborative Filtering and Content Based Recommender Systems
Can Large Language Model Predict Employee Attrition?
The Implicit Bias of Gradient Descent on Separable Multiclass Data
Optimizing Violence Detection in Video Classification Accuracy through 3D Convolutional Neural Networks
AMREx: AMR for Explainable Fact Verification
Convolutional Filtering with RKHS Algebras
A Mechanistic Explanatory Strategy for XAI
Cloned Identity Detection in Social-Sensor Clouds based on Incomplete Profiles
Visual Fourier Prompt Tuning
Generalized Eigenvalue Problems with Generative Priors
FEET: A Framework for Evaluating Embedding Techniques
FEED: Fairness-Enhanced Meta-Learning for Domain Generalization
False Data Injection Attack Detection in Edge-based Smart Metering Networks with Federated Learning
From Federated Learning to Quantum Federated Learning for Space-Air-Ground Integrated Networks
Convergence proofs and strong error bounds for forward-backward stochastic differential equations using neural network simulations
Regret of exploratory policy improvement and q-learning
Receding Hamiltonian-Informed Optimal Neural Control and State Estimation for Closed-Loop Dynamical Systems
Marginal Causal Flows for Validation and Inference
Causal reasoning in difference graphs
Deep Multi-contrast Cardiac MRI Reconstruction via vSHARP with Auxiliary Refinement Network
Uncertainty measurement for complex event prediction in safety-critical systems
Arena-Lite: Efficient and Reliable Large Language Model Evaluation via Tournament-Based Direct Comparisons
NLP and Education: using semantic similarity to evaluate filled gaps in a large-scale Cloze test in the classroom
Improving Energy Efficiency in Manufacturing: A Novel Expert System Shell
The impact of MRI image quality on statistical and predictive analysis on voxel based morphology
Conformalized High-Density Quantile Regression via Dynamic Prototypes-based Probability Density Estimation
An Innovative CGL-MHA Model for Sarcasm Sentiment Recognition Using the MindSpore Framework
Confidence Aware Learning for Reliable Face Anti-spoofing
Diversidade lingu'istica e inclus~ao digital: desafios para uma ia brasileira
Enhancing Diabetic Retinopathy Detection with CNN-Based Models: A Comparative Study of UNET and Stacked UNET Architectures
Hierarchical and Density-based Causal Clustering
Guiding Neural Collapse: Optimising Towards the Nearest Simplex Equiangular Tight Frame
Optimizing Federated Learning by Entropy-Based Client Selection
Efficient Sparse Training with Structured Dropout
AutoPT: How Far Are We from the End2End Automated Web Penetration Testing?
The Interaction Layer: An Exploration for Co-Designing User-LLM Interactions in Parental Wellbeing Support Systems
Rotational Odometry using Ultra Low Resolution Thermal Cameras
MonoPlane: Exploiting Monocular Geometric Cues for Generalizable 3D Plane Reconstruction
RLE: A Unified Perspective of Data Augmentation for Cross-Spectral Re-identification
Real-Time Spatio-Temporal Reconstruction of Dynamic Endoscopic Scenes with 4D Gaussian Splatting
One Arrow, Many Targets: Probing LLMs for Multi-Attribute Controllable Text Summarization
Spatial Transformers for Radio Map Estimation
MultiPull: Detailing Signed Distance Functions by Pulling Multi-Level Queries at Multi-Step
PRIMO: Progressive Induction for Multi-hop Open Rule Generation
Class-specific feature selection for classification explainability
XNB: Explainable Class-Specific NaIve-Bayes Classifier
Transfer Learning for Finetuning Large Language Models
Swan and ArabicMTEB: Dialect-Aware, Arabic-Centric, Cross-Lingual, and Cross-Cultural Embedding Models and Benchmarks
Learning Rules Explaining Interactive Theorem Proving Tactic Prediction
Guiding Multi-agent Multi-task Reinforcement Learning by a Hierarchical Framework with Logical Reward Shaping
CmdCaliper: A Semantic-Aware Command-Line Embedding Model and Dataset for Security Research

All 127