Papers

New on arXiv

Sat 18 Jan 2025

105 papers

Stability Enhancement in Reinforcement Learning via Adaptive Control Lyapunov FunctionDeep reinforcement learning methods → Safe and constrained RL
SCDM: Score-Based Channel Denoising Model for Digital Semantic CommunicationsDiffusion models → Diffusion for compression and wireless
Mixture of Experts (MoE): A Big Data PerspectiveMixture-of-experts → MoE theory and gating functions
Risk-Informed Diffusion Transformer for Long-Tail Trajectory Prediction in the Crash ScenarioDiffusion models → Diffusion and flow policies for robotics
Classical and Deep Reinforcement Learning Inventory Control Policies for Pharmaceutical Supply Chains with Perishability and Non-StationarityDeep reinforcement learning methods → RL for energy, networks and operations
Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic EnvironmentsLLM agents and tool use → General LLM agent frameworks and benchmarks
Diffusion-Based Imitation Learning for Social Pose GenerationDiffusion models → Diffusion and flow policies for robotics +1
Systems Engineering for Autonomous Vehicles; Supervising AI using Large Language Models (SSuperLLM)End-to-end autonomous driving → Large language models for driving
Visual RAG: Expanding MLLM visual knowledge without fine-tuningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Addressing Multilabel Imbalance with an Efficiency-Focused Approach Using Diffusion Model-Generated Synthetic SamplesDiffusion models → Diffusion foundations and sampling
GAUDA: Generative Adaptive Uncertainty-guided Diffusion-based Augmentation for Surgical SegmentationDiffusion models → Medical imaging and segmentation
FlashSR: One-step Versatile Audio Super-resolution via Diffusion DistillationDiffusion models → Audio, speech and music
Non-Expansive Mappings in Two-Time-Scale Stochastic Approximation: Finite-Time AnalysisDeep reinforcement learning methods → RL theory and sample complexity
Jailbreaking Large Language Models in Infinitely Many WaysLLM safety and security → Jailbreaking
Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary FeedbackLLM reasoning → Mathematical reasoning
MedFILIP: Medical Fine-grained Language-Image Pre-trainingMultimodal LLMs / vision-language models → Medical vision-language models
MAPS: Advancing Multi-Modal Reasoning in Expert-Level Physical ScienceLLM reasoning → Spatial and embodied reasoning +1
PEARL: Preconditioner Enhancement through Actor-critic Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
GEC-RAG: Improving Generative Error Correction via Retrieval-Augmented Generation for Automatic Speech Recognition SystemsRetrieval-augmented generation → Conversational and speech RAG
FSMoE: A Flexible and Scalable Training System for Sparse Mixture-of-Experts ModelsMixture-of-experts → Efficient MoE training and inference systems
Revisiting Ensemble Methods for Stock Trading and Crypto Trading Tasks at ACM ICAIF FinRL Contest 2023-2024Deep reinforcement learning methods → Adversarial robustness and RL in finance
An Interpretable Neural Control Network with Adaptable Online Learning for Sample Efficient Robot Locomotion LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
Neural Algorithmic Reasoning for Hypergraphs with Looped TransformersLLM reasoning → Prompting and chain-of-thought reasoning
Can Multimodal LLMs do Visual Temporal Understanding and Reasoning? The answer is No!LLM reasoning → Multimodal reasoning +1
Hybrid-Quantum Neural Architecture Search for The Proximal Policy Optimization AlgorithmDeep reinforcement learning methods → Quantum reinforcement learning
Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacksLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
DASKT: A Dynamic Affect Simulation Method for Knowledge Tracing
A Method for Multi-Hop Question Answering on Persian Knowledge Graph
An Integrated Approach to AI-Generated Content in e-health
Fast and Accurate Identification of Hardware Trojan Locations in Gate-Level Netlist using Nearest Neighbour Approach integrated with Machine Learning Technique
Self-supervised Graph Transformer with Contrastive Learning for Brain Connectivity Analysis towards Improving Autism Detection
Fanar: An Arabic-Centric Multimodal Generative AI Platform
Language Representation Favored Zero-Shot Cross-Domain Cognitive Diagnosis
ARD-VAE: A Statistical Formulation to Find the Relevant Latent Dimensions of Variational Autoencoders
A Generative Security Application Engineering Curriculum
Unfolding Tensors to Identify the Graph in Discrete Latent Bipartite Graphical Models
OpenEarthMap-SAR: A Benchmark Synthetic Aperture Radar Dataset for Global High-Resolution Land Cover Mapping
CEReBrO: Compact Encoder for Representations of Brain Oscillations Using Efficient Alternating Attention
Fixed Point Computation: Beating Brute Force with Smoothed Analysis
A Benchmark of French ASR Systems Based on Error Severity
Distributed Quasi-Newton Method for Fair and Fast Federated Learning
Certifying Robustness via Topological Representations
Fixed-Gaussian Spectral Algorithms: Minimax Optimal Rates for Misspecified Learning and Transfer
JSONSchemaBench: A Rigorous Benchmark of Structured Outputs for Language Models
QGAPHEnsemble : Combining Hybrid QLSTM Network Ensemble via Adaptive Weighting for Short Term Weather Forecasting
Dynamic Continual Learning: Harnessing Parameter Uncertainty for Improved Network Adaptation
Zero-shot and Few-shot Learning with Instruction-following LLMs for Claim Matching in Automated Fact-checking
What price to pay? Auto-tuning a building MPC controller for optimal economic cost
Reliable Text-to-SQL with Adaptive Abstention
Learning Nonverbal Cues in Multiparty Social Interactions for Robotic Facilitators
Exploring Siamese Networks in Self-Supervised Fast MRI Reconstruction
Fake Advertisements Detection Using Automated Multimodal Learning: A Case Study for Vietnamese Real Estate Data
Practical and Ready-to-Use Methodology to Assess the re-identification Risk in Anonymized Datasets
BAP v2: An Enhanced Task Framework for Instruction Following in Minecraft Dialogues
An Interpretable Measure for Quantifying Predictive Dependence between Continuous Random Variables -- Extended Version
No More Sliding Window: Efficient 3D Medical Image Segmentation with Differentiable Top-k Patch Sampling
Graph Coloring to Reduce Computation Time in Prioritized Planning
Efficient auto-labeling of large-scale poultry datasets (ALPD) using an ensemble model with self- and active-learning approaches
Dynamic Trend Fusion Module for Traffic Flow Prediction
CS-Net:Contribution-based Sampling Network for Point Cloud Simplification
Decoupling Appearance Variations with 3D Consistent Features in Gaussian Splatting
LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detection
Measuring Fairness in Financial Transaction Machine Learning Models
ML-SceGen: A Multi-level Scenario Generation Framework
Simultaneous Computation with Multiple Prioritizations in Multi-Agent Motion Planning
Model Monitoring in the Absence of Labeled Data via Feature Attributions Distributions
Enhancing Diagnostic in 3D COVID-19 Pneumonia CT-scans through Explainable Uncertainty Bayesian Quantification
Infrared and Visible Image Fusion: From Data Compatibility to Task Adaption
Deformable Image Registration of Dark-Field Chest Radiographs for Local Lung Signal Change Assessment
An Experimental Study on Joint Modeling for Sound Event Localization and Detection with Source Distance Estimation
Quadcopter Position Hold Function using Optical Flow in a Smartphone-based Flight Computer
Development of Application-Specific Large Language Models to Facilitate Research Ethics Review
Computational Discovery of Chiasmus in Ancient Religious Text
Semi-supervised Semantic Segmentation for Remote Sensing Images via Multi-scale Uncertainty Consistency and Cross-Teacher-Student Attention
A CNN-Transformer for Classification of Longitudinal 3D MRI Images -- A Case Study on Hepatocellular Carcinoma Prediction
Characterizing the Effects of Translation on Intertextuality using Multilingual Embedding Spaces
Robust Local Polynomial Regression with Similarity Kernels
In the Picture: Medical Imaging Datasets, Artifacts, and their Living Review
A Unified Regularization Approach to High-Dimensional Generalized Tensor Bandits
Code Benchmarks Should Prioritize Rigor, Reliability, and Reproducibility
Algorithmic Derivation of Human Spatial Navigation Indices From Eye Movement Data
Exploring Transferable Homogeneous Groups for Compositional Zero-Shot Learning
Distributionally Robust Policy Evaluation and Learning for Continuous Treatment with Observational Data
Multi-modal Fusion and Query Refinement Network for Video Moment Retrieval and Highlight Detection
EMO2: End-Effector Guided Audio-Driven Avatar Video Generation
Harnessing the Potential of Large Language Models in Modern Marketing Management: Applications, Future Directions, and Strategic Recommendations
Deep Operator Networks for Bayesian Parameter Estimation in PDEs
Class-Imbalanced-Aware Adaptive Dataset Distillation for Scalable Pretrained Model on Credit Scoring
MappedTrace: Tracing Pointer Remotely with Compiler-generated Maps
Precision Adaptive Imputation Network : An Unified Technique for Mixed Datasets
Speech Emotion Detection Based on MFCC and CNN-LSTM Architecture
Unveiling the Mystery of Weight in Large Foundation Models: Gaussian Distribution Never Fades
LUT-DLA: Lookup Table as Efficient Extreme Low-Bit Deep Learning Accelerator
MOFA: Discovering Materials for Carbon Capture with a GenAI- and Simulation-Based Workflow
DNA 1.0 Technical Report
UAV-Assisted Multi-Task Federated Learning with Task Knowledge Sharing
Iterative Tree Analysis for Medical Critics
ClusterViG: Efficient Globally Aware Vision GNNs via Image Partitioning
A Resource-Efficient Training Framework for Remote Sensing Text--Image Retrieval
HOPS: High-order Polynomials with Self-supervised Dimension Reduction for Load Forecasting

All 105