Papers

New on arXiv

Mon 20 Jan 2025

199 papers

TutorLLM: Customizing Learning Recommendations with Knowledge Tracing and Retrieval-Augmented GenerationRetrieval-augmented generation → RAG for recommendation
QualityFlow: An Agentic Workflow for Program Synthesis Controlled by LLM Quality ChecksLLM agents and tool use → Software engineering coding agents
Evaluating Binary Decision Biases in Large Language Models: Implications for Fair Agent-Based Financial SimulationsLLM agents and tool use → Financial trading and forecasting agents
How Strategic Agents Respond: Comparing Analytical Models with LLM-Generated Responses in Strategic ClassificationLLM agents and tool use → Social simulation and multi-agent debate
Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Zep: A Temporal Knowledge Graph Architecture for Agent MemoryLLM agents and tool use → Agent memory systems
Guided Persona-based AI Surveys: Can we replicate personal mobility preferences at scale using LLMs?LLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Chat3GPP: An Open-Source Retrieval-Augmented Generation Framework for 3GPP DocumentsRetrieval-augmented generation → RAG pipeline design and evaluation
The Dual-use Dilemma in LLMs: Do Empowering Ethical Capacities Make a Degraded Utility?LLM reasoning → Reasoning benchmarks and evaluation
Multilinguality in LLM-Designed Reward Functions for Restless Bandits: Effects on Task Performance and FairnessLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
MyGO Multiplex CoT: A Method for Self-Reflection in Large Language Models via Double Chain of Thought ThinkingLLM reasoning → Prompting and chain-of-thought reasoning
Ensemble score filter with image inpainting for data assimilation in tracking surface quasi-geostrophic dynamics with partial observationsDiffusion models → Flow matching, time series and science
ImageRef-VL: Enabling Contextual Image Referencing in Vision-Language ModelsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
Benchmarking LLMs' Mathematical Reasoning with Unseen Random Variables QuestionsLLM reasoning → Mathematical reasoning
Synthetic Data Can Mislead Evaluations: Membership Inference as Machine Text DetectionSynthetic data and self-improvement for LLMs → LLM synthetic data generation +1
Glinthawk: A Two-Tiered Architecture for Offline LLM InferenceEfficient LLM inference and serving → Serving systems and request scheduling
EfficientVITON: An Efficient Virtual Try-On Model using Optimized Diffusion ProcessDiffusion models → 3D, point cloud and scene generation
Poison-RAG: Adversarial Data Poisoning Attacks on Retrieval-Augmented Generation in Recommender SystemsRetrieval-augmented generation → Privacy and security of RAG
SILO: Solving Inverse Problems with Latent OperatorsDiffusion models → Inverse problems and image restoration
Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex TasksLLM agents and tool use → GUI and mobile agents +1
SeRpEnt: Selective Resampling for Expressive State Space ModelsState-space sequence models (S4, Mamba) → Core SSM architectures for language
Exploring Preference-Guided Diffusion Model for Cross-Domain RecommendationDiffusion models → Diffusion recommenders
T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference ScalingLLM reasoning → Test-time compute and efficient thinking
Trojan Detection Through Pattern Recognition for Large Language ModelsLLM safety and security → Backdoor and data poisoning attacks
SR-FoT: A Syllogistic-Reasoning Framework of Thought for Large Language Models Tackling Knowledge-based Reasoning TasksLLM reasoning → Reasoning benchmarks and evaluation
Rethinking Membership Inference Attacks Against Transfer LearningLLM safety and security → Membership inference attacks
Graph Defense Diffusion ModelDiffusion models → Flow matching, time series and science
Teaching Large Language Models to Regress Accurate Image Quality Scores using Score DistributionMultimodal LLMs / vision-language models → Image editing and quality assessment
Secure Resource Allocation via Constrained Deep Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
Whose Boat Does it Float? Improving Personalization in Preference Tuning via Inferred User PersonasLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
The impact of intrinsic rewards on exploration in Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
Technical Report for the Forgotten-by-Design Project: Targeted Obfuscation for Machine LearningLLM safety and security → Machine unlearning
SimLabel: Consistency-Guided OOD Detection with Pretrained Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
MASS: Overcoming Language Bias in Image-Text MatchingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Curiosity-Driven Reinforcement Learning from Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
Improving thermal state preparation of Sachdev-Ye-Kitaev model with reinforcement learning on quantum hardwareDeep reinforcement learning methods → Quantum reinforcement learning
RACCOON: A Retrieval-Augmented Generation Approach for Location Coordinate Capture from News ArticlesRetrieval-augmented generation → RAG for recommendation
A Survey on Diffusion Models for Anomaly DetectionDiffusion models → Flow matching, time series and science
Agent-R: Training Language Model Agents to Reflect via Iterative Self-TrainingLLM reasoning → Reasoning for agents, planning and code +2
Verifying Cross-modal Entity Consistency in News using Vision-language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
Block Flow: Learning Straight Flow on Data BlocksDiffusion models → Flow matching, time series and science
EndoChat: Grounded Multimodal Large Language Model for Endoscopic SurgeryMultimodal LLMs / vision-language models → Medical vision-language models
CatV2TON: Taming Diffusion Transformers for Vision-Based Virtual Try-On with Temporal ConcatenationDiffusion models → 3D, point cloud and scene generation
Nested Annealed Training Scheme for Generative Adversarial NetworksDiffusion models → Diffusion foundations and sampling
RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?LLM reasoning → Prompting and chain-of-thought reasoning
Multi-round, Chain-of-thought Post-editing for Unfaithful SummariesLLM reasoning → Reasoning benchmarks and evaluation
A Survey of World Models for Autonomous DrivingWorld models → World models for autonomous driving +1
KPL: Training-Free Medical Knowledge Mining of Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
Reasoning Language Models: A BlueprintLLM reasoning → Reasoning benchmarks and evaluation
Ditto: Accelerating Diffusion Model via Temporal Value SimilarityDiffusion models → Diffusion foundations and sampling
Embedding-Driven Diversity Sampling to Improve Few-Shot Synthetic Data GenerationSynthetic data and self-improvement for LLMs → Medical synthetic data and agents
Approach to Visual Attractiveness of Event Space Through Data-Driven Environment and Spatial Perception
Data Stewardship Decoded: Mapping Its Diverse Manifestations and Emerging Relevance at a time of AI
Practical Application and Limitations of AI Certification Catalogues in the Light of the AI Act
Can Generative AI be Egalitarian?
Do AI assistants help students write formal specifications? A study with ChatGPT and the B-Method
FruitPAL: An IoT-Enabled Framework for Automatic Monitoring of Fruit Consumption in Smart Healthcare
Retail Market Analysis
Assessment of the January 2025 Los Angeles County wildfires: A multi-modal analysis of impact, response, and population exposure
Task and Perception-aware Distributed Source Coding for Correlated Speech under Bandwidth-constrained Channels
Collaborative Channel Access and Transmission for NR Sidelink and Wi-Fi Coexistence over Unlicensed Spectrum
Momentum Contrastive Learning with Enhanced Negative Sampling and Hard Negative Filtering
The OpenLAM Challenges
EVolutionary Independent DEtermiNistiC Explanation
A Cutting Mechanics-based Machine Learning Modeling Method to Discover Governing Equations of Machining Dynamics
Redundancy Principles for MLLMs Benchmarks
A Layered Multi-Expert Framework for Long-Context Mental Health Assessments
DEFEND: A Large-scale 1M Dataset and Foundation Model for Tobacco Addiction Prevention
Can OpenAI o1 Reason Well in Ophthalmology? A 6,990-Question Head-to-Head Evaluation Study
Longitudinal Abuse and Sentiment Analysis of Hollywood Movie Dialogues using Language Models
Consolidating TinyML Lifecycle with Large Language Models: Reality, Illusion, or Opportunity?
Generating visual explanations from deep networks using implicit neural representations
Human-AI Collaborative Game Testing with Vision Language Models
Can Bayesian Neural Networks Make Confident Predictions?
The Value of Nothing: Multimodal Extraction of Human Values Expressed by TikTok Influencers
Is logical analysis performed by transformers taking place in self-attention or in the fully connected part?
Disentangling stellar atmospheric parameters in astronomical spectra using Generative Adversarial Neural Networks
Hypergraph Representations of scRNA-seq Data for Improved Clustering with Random Walks
A Review Paper of the Effects of Distinct Modalities and ML Techniques to Distracted Driving Detection
A generalizable 3D framework and model for self-supervised learning in medical imaging
Are generative models fair? A study of racial bias in dermatological image generation
Optimizing Pretraining Data Mixtures with LLM-Estimated Utility
Personalized Federated Learning for Cellular VR: Online Learning and Dynamic Caching
Non-Reversible Langevin Algorithms for Constrained Sampling
FaceQSORT: a Multi-Face Tracking Method based on Biometric and Appearance Features
Episodic memory in AI agents poses risks that should be studied and mitigated
MedicoSAM: Robust Improvement of SAM for Medical Imaging
Transformer Vibration Forecasting for Advancing Rail Safety and Maintenance 4.0
Explain-Query-Test: Self-Evaluating LLMs Via Explanation and Comprehension Discrepancy
Prediction of Lung Metastasis from Hepatocellular Carcinoma using the SEER Database
GL-ICNN: An End-To-End Interpretable Convolutional Neural Network for the Diagnosis and Prediction of Alzheimer's Disease
The Transition from Centralized Machine Learning to Federated Learning for Mental Health in Education: A Survey of Current Methods and Future Directions
YouLeQD: Decoding the Cognitive Complexity of Questions and Engagement in Online Educational Videos from Learners' Perspectives
Leveraging graph neural networks and mobility data for COVID-19 forecasting
Trustformer: A Trusted Federated Transformer
Human services organizations and the responsible integration of AI: Considering ethics and contextualizing risk(s)
Spatially-Delineated Domain-Adapted AI Classification: An Application for Oncology Data
Randomness, exchangeability, and conformal prediction
Randomized Kaczmarz Methods with Beyond-Krylov Convergence

All 199