Papers

New on arXiv

Sun 22 Jun 2025

165 papers

On-Policy Optimization of ANFIS Policies Using Proximal Policy OptimizationDeep reinforcement learning methods → RL theory and sample complexity
TalentMine: LLM-Based Extraction and Question-Answering from Multimodal Talent TablesRetrieval-augmented generation → RAG robustness and adaptive retrieval
From Pixels and Words to Waves: A Unified Framework for Spectral Dictionary vLLMsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Damba-ST: Domain-Adaptive Mamba for Efficient Urban Spatio-Temporal PredictionState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
Deciphering Emotions in Children Storybooks: A Comparative Analysis of Multimodal LLMs in Educational ApplicationsMultimodal LLMs / vision-language models → Multimodal emotion understanding
Memba: Membrane-driven Parameter-Efficient Fine-Tuning for MambaState-space sequence models (S4, Mamba) → Core SSM architectures for language
Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?LLM reasoning → Test-time compute and efficient thinking
Understanding Reasoning in Thinking Language Models via Steering VectorsLLM reasoning → Test-time compute and efficient thinking +1
Non-equilibrium Annealed Adjoint SamplerDiffusion models → Diffusion foundations and sampling
CDG-MAE: Cross-view Masked Modeling using Diffusion Generated ViewsDiffusion models → Diffusion foundations and sampling
Chain-of-Memory: Enhancing GUI Agents for Cross-Application NavigationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
Routing Mamba: Scaling State Space Models with Mixture-of-Experts ProjectionMixture-of-experts → MoE large language models +1
Sparse Feature Coactivation Reveals Causal Semantic Modules in Large Language ModelsMechanistic interpretability → SAE features and their applications
See-in-Pairs: Reference Image-Guided Comparative Vision-Language Models for Medical DiagnosisMultimodal LLMs / vision-language models → Medical vision-language models
Targeted False Positive Synthesis via Detector-guided Adversarial Diffusion Attacker for Robust Polyp DetectionDiffusion models → Robustness, privacy and adversarial aspects
Decentralized Consensus Inference-based Hierarchical Reinforcement Learning for Multi-Constrained UAV Pursuit-Evasion GameDeep reinforcement learning methods → RL for robot navigation and UAV control
InspireDebate: Multi-Dimensional Subjective-Objective Evaluation-Guided Reasoning and Optimization for DebatingLLM reasoning → Reasoning for agents, planning and code
Deep Research Agents: A Systematic Examination And RoadmapLLM agents and tool use → Web, search, and research agents
TEM^3-Learning: Time-Efficient Multimodal Multi-Task Learning for Advanced Assistive DrivingState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
MUPA: Towards Multi-Path Agentic Reasoning for Grounded Video Question AnsweringLLM agents and tool use → Multimodal and embodied agents
Mechanistic Interpretability in the Presence of Architectural ObfuscationMechanistic interpretability → Circuits and mechanistic analysis
CLGRPO: Reasoning Ability Enhancement for Small VLMsLLM reasoning → Multimodal reasoning +1
Splitformer: An improved early-exit architecture for automatic speech recognition on edge devicesEfficient LLM inference and serving → Early exit and edge inference
PDF Retrieval Augmented Question AnsweringRetrieval-augmented generation → RAG robustness and adaptive retrieval
Tight Stability Bounds for Robust Distributed Learning: Byzantine Failures Hurt Generalization More than Data PoisoningLLM safety and security → Backdoor and data poisoning attacks
Graphs Meet AI Agents: Taxonomy, Progress, and Future OpportunitiesLLM agents and tool use → Web, search, and research agents
OSDMamba: Enhancing Oil Spill Detection from Remote Sensing Images Using Selective State Space ModelState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
Data Curation Matters: Model Collapse and Spurious Shift Performance Prediction from Training on Uncurated Text EmbeddingsSynthetic data and self-improvement for LLMs → Model collapse from synthetic data
Enabling PSO-Secure Synthetic Data Sharing Using Diversity-Aware Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
Adapting Vision-Language Models for Evaluating World ModelsWorld models → Embodied and robot world models +1
A Comprehensive Graph Framework for Question Answering with Mode-Seeking Preference AlignmentRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG +1
GEMeX-RMCoT: An Enhanced Med-VQA Dataset for Region-Aware Multimodal Chain-of-Thought ReasoningLLM reasoning → Clinical and biomedical applications
Safety Certificate against Latent Variables with Partially Unidentifiable DynamicsDeep reinforcement learning methods → Safe and constrained RL
Dynamic Evolution of Complex Networks: A Reinforcement Learning Approach Applying Evolutionary Games to Community StructureDeep reinforcement learning methods → RL for games and combinatorial optimization
Permutation Equivariant Model-based Offline Reinforcement Learning for Auto-biddingOffline RL and imitation learning from data → Offline RL algorithms
Learning, Reasoning, Refinement: A Framework for Kahneman's Dual-System Intelligence in GUI AgentsLLM reasoning → Multimodal reasoning +1
PostAlign: Multimodal Grounding as a Corrective Lens for MLLMsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
GD-Retriever: Controllable Generative Text-Music Retrieval with Diffusion ModelsDiffusion models → Audio, speech and music
GRAF: Multi-turn Jailbreaking via Global Refinement and Active FabricationLLM safety and security → Jailbreaking
Towards Robust Fact-Checking: A Multi-Agent System with Advanced Evidence RetrievalLLM agents and tool use → Web, search, and research agents
LLM Probability Concentration: How Alignment Shrinks the Generative HorizonLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Multi-Amateur Contrastive Decoding for Text Generation
Particle Swarm Optimization for Quantum Circuit Synthesis: Performance Analysis and Insights
DeepSupp: Attention-Driven Correlation Pattern Analysis for Dynamic Time Series Support and Resistance Levels Identification
Fast Clifford Neural Layers
Cross-Attention Message-Passing Transformers for Code-Agnostic Decoding in 6G Networks
Learning to Segment for Vehicle Routing Problems
Theories of "Sexuality" in Natural Language Processing Bias Research
Service Placement in Small Cell Networks Using Distributed Best Arm Identification in Linear Bandits
Hindsight-Guided Momentum (HGM) Optimizer: An Approach to Adaptive Learning Rate
Innovative Research on IoT Architecture and Robotic Operating Platforms: Applications of Large Language Models and Generative AI
Bayesian-Guided Diversity in Sequential Sampling for Recommender Systems
TIM: A Large-Scale Dataset and large Timeline Intelligence Model for Open-domain Timeline Summarization
Refine Medical Diagnosis Using Generation Augmented Retrieval and Clinical Practice Guidelines
An Attack Method for Medical Insurance Claim Fraud Detection based on Generative Adversarial Network
Can AI support student engagement in classroom activities in higher education?
eccDNAMamba: A Pre-Trained Model for Ultra-Long eccDNA Sequence Analysis
Bird's-eye view safety monitoring for the construction top under the tower crane
Which Consciousness Can Be Artificialized? Local Percept-Perceiver Phenomenon for the Existence of Machine Consciousness
Deep Learning-based Alignment Measurement in Knee Radiographs
Limitations of NERF with pre-trained Vision Features for Few-Shot 3D Reconstruction
Multimodal Fusion SLAM with Fourier Attention
Shrinking the Generation-Verification Gap with Weak Verifiers
Prompt Engineering Techniques for Mitigating Cultural Bias Against Arabs and Muslims in Large Language Models: A Systematic Review
Two Sonification Methods for the MindCube
Wisdom of Crowds Through Myopic Self-Confidence Adaptation
Joint Embedding Predictive Architecture for self-supervised pretraining on polymer molecular graphs
DeInfoReg: A Decoupled Learning Framework for Better Training Throughput
Call Me Maybe: Enhancing JavaScript Call Graph Construction using Graph Neural Networks
The Impact of Medication Non-adherence on Adverse Outcomes: Evidence from Schizophrenia Patients via Survival Analysis
Online Learning of Whittle Indices for Restless Bandits with Non-Stationary Transition Kernels
CareLab at #SMM4H-HeaRD 2025: Insomnia Detection and Food Safety Event Extraction with Domain-Aware Transformers
DExNet: Combining Observations of Domain Adapted Critics for Leaf Disease Classification with Limited Data
STACT-Time: Spatio-Temporal Cross Attention for Cine Thyroid Ultrasound Time Series Classification
Pitfalls of Conformal Predictions for Medical Image Classification
Pattern-Based Phase-Separation of Tracer and Dispersed Phase Particles in Two-Phase Defocusing Particle Tracking Velocimetry
AI Through the Human Lens: Investigating Cognitive Theories in Machine Psychology
Probabilistic and reinforced mining of association rules
CoachGPT: A Scaffolding-based Academic Writing Assistant
QuranMorph: Morphologically Annotated Quranic Corpus
AI Harmonizer: Expanding Vocal Expression with a Generative Neurosymbolic Music AI System
SE-Merging: A Self-Enhanced Approach for Dynamic Model Merging
φ∞: Clause Purification, Embedding Realignment, and the Total Suppression of the Em Dash in Autoregressive Language Models
Bayesian Multiobject Tracking With Neural-Enhanced Motion and Measurement Models
RoboArena: Distributed Real-World Evaluation of Generalist Robot Policies
The Syntactic Acceptability Dataset (Preview): A Resource for Machine Learning and Linguistic Analysis of English
Conceptualization, Operationalization, and Measurement of Machine Companionship: A Scoping Review
Mental Health Equity in LLMs: Leveraging Multi-Hop Question Answering to Detect Amplified and Silenced Perspectives
Dynamic Temporal Positional Encodings for Early Intrusion Detection in IoT
RL for Reasoning by Adaptively Revealing Rationales
CT Radiomics-Based Explainable Machine Learning Model for Accurate Differentiation of Malignant and Benign Endometrial Tumors: A Two-Center Study
Chengyu-Bench: Benchmarking Large Language Models for Chinese Idiom Understanding and Use
Enhancing VICReg: Random-Walk Pairing for Improved Generalization and Better Global Semantics Capturing
ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation
GRASP: Grouped Regression with Adaptive Shrinkage Priors
Evaluating Prompt-Based and Fine-Tuned Approaches to Czech Anaphora Resolution
RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
Federated Learning-Based Data Collaboration Method for Enhancing Edge Cloud AI System Security Using Large Language Models
Statistical Multicriteria Evaluation of LLM-Generated Text
Identifiable Convex-Concave Regression via Sub-gradient Regularised Least Squares

All 165