Papers

New on arXiv

Sun 21 Dec 2025

138 papers

A Modular Reference Architecture for MCP-Servers Enabling Agentic BIM InteractionLLM agents and tool use → Tool learning and function calling
Multi-Agent LLM Committees for Autonomous Software Beta TestingLLM agents and tool use → Software engineering coding agents
Learning-Based Automated Adversarial Red-Teaming for Robustness Evaluation of Large Language ModelsLLM safety and security → Prompt injection and agent security
How Many Experts Are Enough? Towards Optimal Semantic Specialization for Mixture-of-ExpertsMixture-of-experts → Expert routing strategies
Delta-LLaVA: Base-then-Specialize Alignment for Token-Efficient Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
Remedy-R: Generative Reasoning for Machine Translation Evaluation without Error AnnotationsLLM reasoning → Reasoning benchmarks and evaluation
Thinking Beyond Labels: Vocabulary-Free Fine-Grained Recognition using Reasoning-Augmented LMMsLLM reasoning → Multimodal reasoning +1
CrashChat: A Multimodal Large Language Model for Multitask Traffic Crash Video AnalysisMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
CORE: Concept-Oriented Reinforcement for Bridging the Definition-Application Gap in Mathematical ReasoningLLM reasoning → Reinforcement learning for reasoning
InDRiVE: Reward-Free World-Model Pretraining for Autonomous Driving via Latent DisagreementWorld models → World models for autonomous driving +1
Brain-Gen: Towards Interpreting Neural Signals for Stimulus Reconstruction Using Transformers and Latent Diffusion ModelsDiffusion models → Medical imaging and segmentation
MDToC: Metacognitive Dynamic Tree of Concepts for Boosting Mathematical Problem-Solving of Large Language ModelsLLM reasoning → Mathematical reasoning
From Word to World: Can Large Language Models be Implicit Text-based World Models?World models → World models for language agents +1
EchoMotion: Unified Human Video and Motion Generation via Dual-Modality Diffusion TransformerDiffusion models → Video generation
Revealing Perception and Generation Dynamics in LVLMs: Mitigating Hallucinations via Validated Dominance CorrectionMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
Smark: A Watermark for Text-to-Speech Diffusion Models via Discrete Wavelet TransformDiffusion models → Robustness, privacy and adversarial aspects +1
In-Context Audio Control of Video Diffusion TransformersDiffusion models → Audio, speech and music
MEEA: Mere Exposure Effect-Driven Confrontational Optimization for LLM JailbreakingLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
IPCV: Information-Preserving Compression for MLLM Visual EncodersMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
MemEvolve: Meta-Evolution of Agent Memory SystemsLLM agents and tool use → Agent memory systems
Memorize-and-Generate: Towards Long-Term Consistency in Real-Time Video GenerationWorld models → Video-generation world models and simulators +1
Is Your Conditional Diffusion Model Actually Denoising?Diffusion models → Diffusion foundations and sampling
M3-Verse: A "Spot the Difference" Challenge for Large Multimodal ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
Explainable and Fine-Grained Safeguarding of LLM Multi-Agent Systems via Bi-Level Graph Anomaly DetectionLLM agents and tool use → Agent threats, guardrails and governance
A Theoretical Lens for RL-Tuned Language Models via Energy-Based ModelsLLM reasoning → Reinforcement learning for reasoning
Generating Risky Samples with Conformity Constraints via Diffusion ModelsDiffusion models → Diffusion foundations and sampling
Rectification Reimagined: A Unified Mamba Model for Image Correction and Rectangling with PromptsState-space sequence models (S4, Mamba) → Mamba for image restoration
CauTraj: A Causal-Knowledge-Guided Framework for Lane-Changing Trajectory Planning of Autonomous VehiclesEnd-to-end autonomous driving → End-to-end system architecture
CIRR: Causal-Invariant Retrieval-Augmented Recommendation with Faithful Explanations under Distribution ShiftRetrieval-augmented generation → RAG for recommendation
AsyncDiff: Asynchronous Timestep Conditioning for Enhanced Text-to-Image Diffusion InferenceDiffusion models → Diffusion foundations and sampling
Remoe: Towards Efficient and Low-Cost MoE Inference in Serverless ComputingMixture-of-experts → Efficient MoE training and inference systems
IntelliCode: A Multi-Agent LLM Tutoring System with Centralized Learner ModelingLLM agents and tool use → Educational agents and math problem solving
Pseudo-Expert Regularized Offline RL for End-to-End Autonomous Driving in Photorealistic Closed-Loop EnvironmentsEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
Measuring the Impact of Student Gaming Behaviors on Learner ModelingLLM safety and security → Backdoor and data poisoning attacks
Does It Tie Out? Towards Autonomous Legal Agents in Venture CapitalLLM agents and tool use → Financial trading and forecasting agents
Uni-Neur2Img: Unified Neural Signal-Guided Image Generation, Editing, and Stylization via Diffusion TransformersDiffusion models → Medical imaging and segmentation
A Multi-agent Text2SQL Framework using Small Language Models and Execution FeedbackLLM agents and tool use → Web, search, and research agents
ChronoDreamer: Action-Conditioned World Model as an Online Simulator for Robotic PlanningWorld models → Embodied and robot world models
Reflective Confidence: Correcting Reasoning Flaws via Online Self-CorrectionLLM reasoning → Test-time compute and efficient thinking
Restore-R1: Efficient Image Restoration Agents via Reinforcement Learning with Multimodal LLM Perceptual FeedbackMultimodal LLMs / vision-language models → Image editing and quality assessment +1
SD2AIL: Adversarial Imitation Learning from Synthetic Demonstrations via Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics +1
MeanFlow-TSE: One-Step Generative Target Speaker Extraction with Mean FlowDiffusion models → Audio, speech and music
ESearch-R1: Learning Cost-Aware MLLM Agents for Interactive Embodied Search via Reinforcement LearningLLM reasoning → Spatial and embodied reasoning +2
OpenView: Empowering MLLMs with Out-of-view VQAMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Enhancing Medical Large Vision-Language Models via Alignment DistillationMultimodal LLMs / vision-language models → Medical vision-language models
Toward Training Superintelligent Software Agents through Self-Play SWE-RLLLM agents and tool use → Software engineering coding agents +1
Reason to Contrast: A Cascaded Multimodal Retrieval Framework
Elsewise: Authoring Open-ended Interactive Narrative with Possibility Space Visualization
No Universal Hyperbola: A Formal Disproof of the Epistemic Trade-Off Between Certainty and Scope in Symbolic and Generative AI
Emissions and Performance Trade-off Between Small and Large Language Models
Rubric-Conditioned LLM Grading: Alignment, Uncertainty, and Robustness
The Artificial Intelligence Value Chain: A Critical Appraisal. [Spanish Version]
When in Doubt, Consult: Expert Debate for Sexism Detection via Confidence-Based Routing
CosineGate: Semantic Dynamic Routing via Cosine Incompatibility in Residual Networks
A CNN-Based Malaria Diagnosis from Blood Cell Images with SHAP and LIME Explainability
TCFormer: A 5M-Parameter Transformer with Density-Guided Aggregation for Weakly-Supervised Crowd Counting
Complex Swin Transformer for Accelerating Enhanced SMWI Reconstruction
Learning to Design City-scale Transit Routes
Beyond the Prompt: An Empirical Study of Cursor Rules
Testing for latent structure via the Wilcoxon--Wigner random matrix of normalized rank statistics
Concurrent training methods for Kolmogorov-Arnold networks: Disjoint datasets and FPGA implementation
Multimodal Bayesian Network for Robust Assessment of Casualties in Autonomous Triage
Gabliteration: Adaptive Multi-Directional Neural Weight Modification for Selective Behavioral Alteration in Large Language Models
Structural Reinforcement Learning for Heterogeneous Agent Macroeconomics
Localising Shortcut Learning in Pixel Space via Ordinal Scoring Correlations for Attribution Representations (OSCAR)
Can LLMs Estimate Student Struggles? Human-AI Difficulty Alignment with Proficiency Simulation for Item Difficulty Prediction
Psychometric Validation of the Sophotechnic Mediation Scale and a New Understanding of the Development of GenAI Mastery: Lessons from 3,932 Adult Brazilian Workers
Application of deep learning approaches for medieval historical documents transcription
Cross-modal Counterfactual Explanations: Uncovering Decision Factors and Dataset Biases in Subjective Classification
Merge on workspaces as Hopf algebra Markov chain
Toward Human-Centered AI-Assisted Terminology Work
VizDefender: Unmasking Visualization Tampering through Proactive Localization and Intent Inference
Generative Modeling through Koopman Spectral Analysis: An Operator-Theoretic Perspective
Mix, MinHash, and Match: Cross-Source Agreement for Multilingual Pretraining Datasets
HARBOR: Holistic Adaptive Risk assessment model for BehaviORal healthcare
Hyperbolic Graph Embeddings: a Survey and an Evaluation on Anomaly Detection
Controllable Probabilistic Forecasting with Stochastic Decomposition Layers
FedVideoMAE: Efficient Federated Video Moderation with Differential Privacy and Secure Aggregation
Tempo as the Stable Cue: Hierarchical Mixture of Tempo and Beat Experts for Music to 3D Dance Generation
Reliable Audio Deepfake Detection in Variable Conditions via Quantum-Kernel SVMs
The Dead Salmons of AI Interpretability
RIS-Enabled Smart Wireless Environments: Fundamentals and Distributed Optimization
Eff-GRot: Efficient and Generalizable Rotation Estimation with Transformers
From Natural Language to Control Signals: A Conceptual Framework for Semantic Channel Finding in Complex Experimental Infrastructure
Label-Informed Outlier Detection Based on Granule Density
MaskFocus: Focusing Policy Optimization on Critical Steps for Masked Image Generation
Gaussian-Mixture-Model Q-Functions for Policy Iteration in Reinforcement Learning
Context-Aware Network Based on Multi-scale Spatio-temporal Attention for Action Recognition in Videos
Code2Doc: A Quality-First Curated Dataset for Code Documentation
InSight-o3: Empowering Multimodal Foundation Models with Generalized Visual Search
AMLID: An Adaptive Multispectral Landmine Identification Dataset for Drone-Based Detection
PIPCFR: Pseudo-outcome Imputation with Post-treatment Variables for Individual Treatment Effect Estimation
Breast Cancer Recurrence Risk Prediction Based on Multiple Instance Learning
Counterfactual Basis Extension and Representational Geometry: An MDL-Constrained Model of Conceptual Growth
ML Inference Scheduling with Predictable Latency
Unsupervised Feature Selection via Robust Autoencoder and Adaptive Graph Learning
KeenKT: Knowledge Mastery-State Disambiguation for Knowledge Tracing
Task Vector in TTS: Toward Emotionally Expressive Dialectal Speech Synthesis
EcoSplat: Efficiency-controllable Feed-forward 3D Gaussian Splatting from Multi-view Images
Fusion of Multiscale Features Via Centralized Sparse-attention Network for EEG Decoding

All 138