Papers

New on arXiv

Sat 20 Dec 2025

155 papers

Resisting Correction: How RLHF Makes Language Models Ignore External Safety Signals in Natural ConversationLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
Emotion-Inspired Learning Signals (EILS): A Homeostatic Framework for Adaptive Autonomous AgentsLLM agents and tool use → Social simulation and multi-agent debate
Bidirectional RAG: Safe Self-Improving Retrieval-Augmented Generation Through Multi-Stage ValidationRetrieval-augmented generation → RAG pipeline design and evaluation +1
MatKV: Trading Compute for Flash Storage in LLM InferenceRetrieval-augmented generation → RAG pipeline design and evaluation
Learning Tennis Strategy Through Curriculum-Based Dueling Double Deep Q-NetworksDeep reinforcement learning methods → Deep RL algorithms and representations
Revisiting the Learning Objectives of Vision-Language Reward ModelsLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
HyDRA: Hierarchical and Dynamic Rank Adaptation for Mobile Vision Language ModelMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Distributed Control of Network Systems in the Space of Stabilizing Graph Neural Network PoliciesDeep reinforcement learning methods → RL for games and combinatorial optimization
GTMA: Dynamic Representation Optimization for OOD Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Adaptive-VoCo: Complexity-Aware Visual Token Compression for Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
STORM: Search-Guided Generative World Models for Robotic ManipulationWorld models → Embodied and robot world models +2
SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution ScenariosLLM agents and tool use → Software engineering coding agents
Plasticine: A Traceable Diffusion Model for Medical Image TranslationDiffusion models → Medical imaging and segmentation
Out-of-Distribution Detection in Molecular Complexes via Diffusion Models for Irregular GraphsDiffusion models → Flow matching, time series and science
Secret mixtures of experts inside your LLMMixture-of-experts → Expert routing strategies
An Agentic AI Framework for Training General Practitioner Student SkillsLLM agents and tool use → Medical and scientific domain agents
VeruSAGE: A Study of Agent-Based Verification for Rust SystemsLLM agents and tool use → Software engineering coding agents
MoE Pathfinder: Trajectory-driven Expert PruningMixture-of-experts → MoE large language models
AmPLe: Supporting Vision-Language Models via Adaptive-Debiased Ensemble Multi-Prompt LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
AOMGen: Photoreal, Physics-Consistent Demonstration Generation for Articulated Object ManipulationWorld models → Embodied and robot world models +1
Learning Semantic Atomic Skills for Multi-Task Robotic ManipulationOffline RL and imitation learning from data → Robot manipulation imitation learning
PSI3D: Plug-and-Play 3D Stochastic Inference with Slice-wise Latent Diffusion PriorDiffusion models → Medical imaging and segmentation
Efficient Zero-Shot Inpainting with Decoupled Diffusion GuidanceDiffusion models → 3D, point cloud and scene generation
LLM Agents Implement an NLG System from Scratch: Building Interpretable Rule-Based RDF-to-Text GeneratorsLLM agents and tool use → General LLM agent frameworks and benchmarks
LLM-based Few-Shot Early Rumor Detection with Imitation AgentLLM agents and tool use → Social simulation and multi-agent debate
Towards Efficient Agents: A Co-Design of Inference Architecture and SystemLLM agents and tool use → General LLM agent frameworks and benchmarks +1
Dynamic Entropy Tuning in Reinforcement Learning Low-Level Quadcopter Control: Stochasticity vs DeterminismDeep reinforcement learning methods → RL theory and sample complexity
Reinforcement Learning Position Control of a Quadrotor Using Soft Actor-Critic (SAC)Deep reinforcement learning methods → RL for robot navigation and UAV control
LIR3AG: A Lightweight Rerank Reasoning Strategy Framework for Retrieval-Augmented GenerationLLM reasoning → Knowledge- and tool-augmented reasoning +1
CTTA-T: Continual Test-Time Adaptation for Text Understanding via Teacher-Student with a Domain-aware and Generalized TeacherKnowledge distillation → Knowledge distillation for LLMs
Trustworthy and Explainable Deep Reinforcement Learning for Safe and Energy-Efficient Process Control: A Use Case in Industrial Compressed Air SystemsDeep reinforcement learning methods → RL for energy, networks and operations
MatSpray: Fusing 2D Material World Knowledge on 3D GeometryDiffusion models → 3D, point cloud and scene generation
Monitoring MonitorabilityLLM reasoning → Prompting and chain-of-thought reasoning
Who Can See Through You? Adversarial Shielding Against VLM-Based Attribute Inference AttacksMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
Offline Behavioral Data SelectionOffline RL and imitation learning from data → Offline RL algorithms
Breaking Minds, Breaking Systems: Jailbreaking Large Language Models via Human-like Psychological ManipulationLLM safety and security → Jailbreaking
Emergent Learner Agency in Implicit Human-AI Collaboration: How Supportive and Contrarian AI Personas Reshape InteractionLLM agents and tool use → Social simulation and multi-agent debate
Investigating Spatial Attention Bias in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Stable and Efficient Single-Rollout RL for Multimodal ReasoningLLM reasoning → Multimodal reasoning +1
LLaViDA: A Large Language Vision Driving Assistant for Explicit Reasoning and Enhanced Trajectory PlanningLLM reasoning → Chain-of-thought reasoning for driving +1
Sophia: A Persistent Agent Framework of Artificial LifeLLM agents and tool use → General LLM agent frameworks and benchmarks
LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical SupervisionLLM reasoning → Reasoning benchmarks and evaluation
TraCT: Disaggregated LLM Serving with CXL Shared Memory KV Cache at Rack-ScaleEfficient LLM inference and serving → KV cache optimization
External Hippocampus: Topological Cognitive Maps for Guiding Large Language Model ReasoningLLM reasoning → Reasoning benchmarks and evaluation
Is There a Better Source Distribution than Gaussian? Exploring Source Distributions for Image Flow MatchingDiffusion models → Flow matching, time series and science
Conscious Data Contribution via Community-Driven Chain-of-Thought DistillationLLM reasoning → Reasoning for agents, planning and code
Local Patches Meet Global Context: Scalable 3D Diffusion Priors for Computed Tomography ReconstructionDiffusion models → Medical imaging and segmentation
Propose, Solve, Verify: Self-Play Through Formal VerificationSynthetic data and self-improvement for LLMs → Self-play RL for reasoning
On Swarm Leader Identification using Probing PoliciesDeep reinforcement learning methods → RL for robot navigation and UAV control
Attachment Styles and AI Chatbot Interactions Among College Students
Computable Gap Assessment of Artificial Intelligence Governance in Children's Centres: Evidence-Mechanism-Governance-Indicator Modelling of UNICEF's Guidance on AI and Children 3.0 Based on the Graph-GAP Framework
Modeling Day-Long ECG Signals to Predict Heart Failure Risk with Explainable AI
Neural Brain Fields: A NeRF-Inspired Approach for Generating Nonexistent EEG Electrodes
Emergent Persuasion: Will LLMs Persuade Without Being Prompted?
Quadrant Segmentation VLM with Few-Shot Adaptation and OCT Learning-based Explainability Methods for Diabetic Retinopathy
AETAS: Analysis of Evolving Temporal Affect and Semantics for Legal History
Tiny-YOLOSAM: Fast Hybrid Image Segmentation
Frequency Regularization: Unveiling the Spectral Inductive Bias of Deep Neural Networks
Physics-Informed Machine Learning for Transformer Condition Monitoring -- Part I: Basic Concepts, Neural Networks, and Variants
Physics-Informed Machine Learning for Transformer Condition Monitoring -- Part II: Physics-Informed Neural Networks and Uncertainty Quantification
HookMIL: Revisiting Context Modeling in Multiple Instance Learning for Computational Pathology
Beyond Augmentation: Cross-Modal Transformer Fusion with Bi-directional Attention for Low-Data Aneurysm Screening
CosmoCore-Evo: Evolutionary Dream-Replay Reinforcement Learning for Adaptive Code Generation
Physics-Informed Neural Solvers for Periodic Quantum Eigenproblems
SecureCode: A Production-Grade Multi-Turn Dataset for Training Security-Aware Code Generation Models
Generalization Gaps in Political Fake News Detection: An Empirical Study on the LIAR Dataset
Pushing the limits of one-dimensional NMR spectroscopy for automated structure elucidation using artificial intelligence
WoundNet-Ensemble: A Novel IoMT System Integrating Self-Supervised Deep Learning and Multi-Model Fusion for Automated, High-Accuracy Wound Classification and Healing Progression Monitoring
Detection of AI Generated Images Using Combined Uncertainty Measures and Particle Swarm Optimised Rejection Mechanism
A Formal Descriptive Language for Learning Dynamics: A Five-Layer Structural Coordinate System
Feature-Enhanced Graph Neural Networks for Classification of Synthetic Graph Generative Models: A Benchmarking Study
Prediction and Forecast of Short-Term Drought Impacts Using Machine Learning to Support Mitigation and Adaptation Efforts
Selection-Induced Contraction of Innovation Statistics in Gated Kalman Filters
Teaching and Critiquing Conceptualization and Operationalization in NLP
NASTaR: NovaSAR Automated Ship Target Recognition Dataset
PlantDiseaseNet-RT50: A Fine-tuned ResNet50 Architecture for High-Accuracy Plant Disease Detection Beyond Standard CNNs
Enhancing Decision-Making in Windows PE Malware Classification During Dataset Shifts with Uncertainty Estimation
Large Language Models as Discounted Bayesian Filters
Insider Threat Detection Using GCN and Bi-LSTM with Explicit and Implicit Graph Representations
Research on a hybrid LSTM-CNN-Attention model for text-based web content classification
APC-GNN++: An Adaptive Patient-Centric GNN with Context-Aware Attention and Mini-Graph Explainability for Diabetes Classification
The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning
Self-organizing maps for water quality assessment in reservoirs and lakes: A systematic literature review
Mitigating Spurious Correlations in NLI via LLM-Synthesized Counterfactuals and Dynamic Balanced Sampling
SoK: Understanding (New) Security Issues Across AI4Code Use Cases
NOVA: Discovering Well-Conditioned Winograd Transforms through Numerical Optimization of Vandermonde Arithmetic
Agent-Based Output Drift Detection for Breast Cancer Response Prediction in a Multisite Clinical Decision Support System
Object-Centric Framework for Video Moment Retrieval
On the Universality of Transformer Architectures; How Much Attention Is Enough?
Snowveil: A Framework for Decentralised Preference Discovery
A Distributed Hierarchical Spatio-Temporal Edge-Enhanced Graph Neural Network for City-Scale Dynamic Logistics Routing
MeniMV: A Multi-view Benchmark for Meniscus Injury Severity Grading
Federated Learning Based Decentralized Adaptive Intelligent Transmission Protocol for Privacy Preserving 6G Networks
E-RGB-D: Real-Time Event-Based Perception with Structured Light
Few-Shot Learning of a Graph-Based Neural Network Model Without Backpropagation
Why Most Optimism Bandit Algorithms Have the Same Regret Analysis: A Simple Unifying Theorem
Through the PRISm: Importance-Aware Scene Graphs for Image Retrieval
Automated Mosaic Tesserae Segmentation via Deep Learning Techniques
AraToken: Optimizing Arabic Tokenization with Normalization Pipeline and Language Extension for Qwen3
The Challenger: When Do New Data Sources Justify Switching Machine Learning Models?

All 155