Papers

New on arXiv

Sat 11 Jan 2025

105 papers

Personalized Preference Fine-tuning of Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics +1
FocalPO: Enhancing Preference Optimizing by Focusing on Correct Preference RankingsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
A Reduced Order Iterative Linear Quadratic Regulator (ILQR) Technique for the Optimal Control of Nonlinear Partial Differential EquationsDeep reinforcement learning methods → RL for games and combinatorial optimization
Guided Code Generation with LLMs: A Multi-Agent Framework for Complex Code TasksLLM reasoning → Reasoning for agents, planning and code +1
RoboHorizon: An LLM-Assisted Multi-View World Model for Long-Horizon Robotic ManipulationWorld models → Embodied and robot world models
ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code GenerationMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
ChemAgent: Self-updating Library in Large Language Models Improves Chemical ReasoningLLM reasoning → Clinical and biomedical applications
Boundary-enhanced time series data imputation with long-term dependency diffusion modelsDiffusion models → Flow matching, time series and science
Hierarchical Reinforcement Learning for Optimal Agent Grouping in Cooperative SystemsDeep reinforcement learning methods → RL for games and combinatorial optimization
VASparse: Towards Efficient Visual Hallucination Mitigation via Visual-Aware Token SparsificationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
Focus-N-Fix: Region-Aware Fine-Tuning for Text-to-Image GenerationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
First Token Probability Guided RAG for Telecom Question AnsweringRetrieval-augmented generation → RAG robustness and adaptive retrieval
Retrieval-Augmented Dialogue Knowledge Aggregation for Expressive Conversational Speech SynthesisRetrieval-augmented generation → Conversational and speech RAG
O1 Replication Journey -- Part 3: Inference-time Scaling for Medical ReasoningLLM reasoning → Clinical and biomedical applications
Reinforcement Learning for Enhancing Sensing Estimation in Bistatic ISAC Systems with UAV SwarmsDeep reinforcement learning methods → RL for robot navigation and UAV control
Qffusion: Controllable Portrait Video Editing via Quadrant-Grid Attention LearningDiffusion models → Audio, speech and music
Open Eyes, Then Reason: Fine-grained Visual Mathematical Understanding in MLLMsLLM reasoning → Multimodal reasoning +1
Influencing Humans to Conform to Preference Models for RLHFLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
Task Delay and Energy Consumption Minimization for Low-altitude MEC via Evolutionary Multi-objective Deep Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
A Hybrid Framework for Reinsurance Optimization: Integrating Generative Models and Reinforcement LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance
GenAI Confessions: Black-box Membership Inference for Generative Image ModelsLLM safety and security → Membership inference attacks
An Expectation-Maximization Algorithm-based Autoregressive Model for the Fuzzy Job Shop Scheduling Problem
Characterizing Mobile SoC for Accelerating Heterogeneous LLM Inference
Quantum Annealing for Robust Principal Component Analysis
Prediction Model of Aqua Fisheries Using IoT Devices
Perception-Guided EEG Analysis: A Deep Learning Approach Inspired by Level of Detail (LOD) Theory
A Short-Term Predict-Then-Cluster Framework for Meal Delivery Services
Challenging reaction prediction models to generalize to novel chemistry
Ultra Memory-Efficient On-FPGA Training of Transformers via Tensor-Compressed Optimization
The magnitude of categories of texts enriched by language models
Learning dynamical systems with hit-and-run random feature maps
MapGS: Generalizable Pretraining and Data Augmentation for Online Mapping via Novel View Synthesis
Visual Template Inference for Data Extraction from Documents
Parking Space Detection in the City of Granada
SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)
Common Sense Is All You Need
Enhancing Path Planning Performance through Image Representation Learning of High-Dimensional Configuration Spaces
Scaling Down Semantic Leakage: Investigating Associative Bias in Smaller Language Models
Dual use issues in the field of Natural Language Generation
Quantifying Relational Exploration in Cultural Heritage Knowledge Graphs with LLMs: A Neuro-Symbolic Approach
Dual-Modality Representation Learning for Molecular Property Prediction
Preconditioned Sharpness-Aware Minimization: Unifying Analysis and a Novel Learning Algorithm
A Comparative Performance Analysis of Classification and Segmentation Models on Bangladeshi Pothole Dataset
EmoXpt: Analyzing Emotional Variances in Human Comments and LLM-Generated Responses
Exploring Pose-Based Anomaly Detection for Retail Security: A Real-World Shoplifting Dataset and Benchmark
Ladder-residual: parallelism-aware architecture for accelerating large model inference with communication overlapping
A Tight VC-Dimension Analysis of Clustering Coresets with Applications
ACORD: An Expert-Annotated Retrieval Dataset for Legal Contract Drafting
Recommending the right academic programs: An interest mining approach using BERTopic
Survey Transfer Learning: Recycling Data with Silicon Responses
Evolutionary Optimization of Physics-Informed Neural Networks: Evo-PINN Frontiers and Opportunities
Active Rule Mining for Multivariate Anomaly Detection in Radio Access Networks
Natural Language Processing and Deep Learning Models to Classify Phase of Flight in Aviation Safety Occurrences
Discrete Speech Unit Extraction via Independent Component Analysis
Where to Go Next Day: Multi-scale Spatial-Temporal Decoupled Model for Mid-term Human Mobility Prediction
A Survey on Spoken Italian Datasets and Corpora
CoreNet: Conflict Resolution Network for Point-Pixel Misalignment and Sub-Task Suppression of 3D LiDAR-Camera Object Detection
Natural Language Supervision for Low-light Image Enhancement
Copula-enhanced Vision Transformer for high myopia diagnosis through OU UWF fundus images
Dispersion Measures as Predictors of Lexical Decision Time, Word Familiarity, and Lexical Complexity
Dynamic Causal Structure Discovery and Causal Effect Estimation
DivTrackee versus DynTracker: Promoting Diversity in Anti-Facial Recognition against Dynamic FR Strategy
Determination of galaxy photometric redshifts using Conditional Generative Adversarial Networks (CGANs)
Scaffolding Creativity: Integrating Generative AI Tools and Real-world Experiences in Business Education
Multi-View Factorizing and Disentangling: A Novel Framework for Incomplete Multi-View Multi-Label Classification
Fine-tuning Large Language Models for Improving Factuality in Legal Question Answering
Neural Codec Source Tracing: Toward Comprehensive Attribution in Open-Set Condition
Resource Allocation under the Latin Square Constraint
Online Algorithm for Aggregating Experts' Predictions with Unbounded Quadratic Loss
PASS: Presentation Automation for Slide Generation and Speech
Analyzing the Role of Context in Forecasting with Large Language Models
TopoFormer: Integrating Transformers and ConvLSTMs for Coastal Topography Prediction
A New Flexible Train-Test Split Algorithm, an approach for choosing among the Hold-out, K-fold cross-validation, and Hold-out iteration
Improving Requirements Classification with SMOTE-Tomek Preprocessing
Sequential Classification of Aviation Safety Occurrences with Natural Language Processing
NVS-SQA: Exploring Self-Supervised Quality Representation Learning for Neurally Synthesized Scenes without References
A Diffusive Data Augmentation Framework for Reconstruction of Complex Network Evolutionary History
Flash Window Attention: speedup the attention computation for Swin Transformer
Speech Recognition for Automatically Assessing Afrikaans and isiXhosa Preschool Oral Narratives
Enhancing Multi-Modal Video Sentiment Classification Through Semi-Supervised Clustering
YO-CSA-T: A Real-time Badminton Tracking System Utilizing YOLO Based on Contextual and Spatial Attention
The Internet of Large Language Models: An Orchestration Framework for LLM Training and Knowledge Exchange Toward Artificial General Intelligence
SP-SLAM: Neural Real-Time Dense SLAM With Scene Priors
CNN-powered micro- to macro-scale flow modeling in deformable porous media
MedCT: A Clinical Terminology Graph for Generative AI Applications in Healthcare
Assessing instructor-AI cooperation for grading essay-type questions in an introductory sociology course
Automated Detection and Analysis of Minor Deformations in Flat Walls Due to Railway Vibrations Using LiDAR and Machine Learning
Discovering an Image-Adaptive Coordinate System for Photography Processing
Cross-Technology Interference: Detection, Avoidance, and Coexistence Mechanisms in the ISM Bands
On the Computational Capability of Graph Neural Networks: A Circuit Complexity Bound Perspective
ARES: Auxiliary Range Expansion for Outlier Synthesis
CPDR: Towards Highly-Efficient Salient Object Detection via Crossed Post-decoder Refinement
UCloudNet: A Residual U-Net with Deep Supervision for Cloud Image Segmentation
Synthetic Feature Augmentation Improves Generalization Performance of Language Models
Deep Learning on Hester Davis Scores for Inpatient Fall Prediction
Aug3D: Augmenting large scale outdoor datasets for Generalizable Novel View Synthesis
Reliable Imputed-Sample Assisted Vertical Federated Learning
Tensor Product Attention Is All You Need
AlgoPilot: Fully Autonomous Program Synthesis Without Human-Written Programs
DiscQuant: A Quantization Method for Neural Networks Inspired by Discrepancy Theory

All 105