Papers

New on arXiv

Fri 26 Dec 2025

148 papers

StatLLaMA: Multi-Stage training for domain-optimized statistical large language modelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Socio-technical aspects of Agentic AILLM agents and tool use → General LLM agent frameworks and benchmarks
A Review of Diffusion-based Simulation-Based Inference: Foundations and Applications in Non-Ideal Data ScenariosDiffusion models → Flow matching, time series and science
AgenticTCAD: A LLM-based Multi-Agent Framework for Automated TCAD Code Generation and Device OptimizationLLM agents and tool use → Software engineering coding agents
DeFloMat: Detection with Flow Matching for Stable and Efficient Generative Object LocalizationDiffusion models → Medical imaging and segmentation
AI-Generated Code Is Not Reproducible (Yet): An Empirical Study of Dependency Gaps in LLM-Based Coding AgentsLLM agents and tool use → Software engineering coding agents
OxygenREC: An Instruction-Following Generative Framework for E-commerce RecommendationLLM reasoning → LLM reasoning for recommendation
PHANTOM: Physics-Aware Adversarial Attacks against Federated Learning-Coordinated EV Charging Management SystemDeep reinforcement learning methods → RL for energy, networks and operations
Self-Evaluation Unlocks Any-Step Text-to-Image GenerationDiffusion models → Image generation, text-to-image and editing
Cost Trade-offs of Reasoning and Non-Reasoning Large Language Models in Text-to-SQLLLM reasoning → Knowledge- and tool-augmented reasoning
VULCAN: Tool-Augmented Multi Agents for Iterative 3D Object ArrangementMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
Reinforcement Learning for Optimal Stopping in POMDPs with Application to Quickest Change DetectionDeep reinforcement learning methods → RL theory and sample complexity
Agent2World: Learning to Generate Symbolic World Models via Adaptive Multi-Agent FeedbackWorld models → World models for language agents +1
DeMoGen: Towards Decompositional Human Motion Generation with Energy-Based Diffusion ModelsDiffusion models → Video generation
SpotEdit: Selective Region Editing in Diffusion TransformersDiffusion models → Image generation, text-to-image and editing
SmartSnap: Proactive Evidence Seeking for Self-Verifying AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
VideoZoomer: Reinforcement-Learned Temporal Focusing for Long Video ReasoningLLM reasoning → Multimodal reasoning +1
Attack-Aware Deepfake Detection under Counter-Forensic ManipulationsLLM safety and security → Watermarking generated content and models
See Less, See Right: Bi-directional Perceptual Shaping For Multimodal ReasoningLLM reasoning → Multimodal reasoning +1
A2P-Vis: an Analyzer-to-Presenter Agentic Pipeline for Visual Insights Generation and ReportingLLM agents and tool use → Multimodal and embodied agents
Yume-1.5: A Text-Controlled Interactive World Generation ModelDiffusion models → Video generation
Context as a Tool: Context Management for Long-Horizon SWE-AgentsLLM agents and tool use → Software engineering coding agents
Agent-based simulation of online social networks and disinformationLLM agents and tool use → Social simulation and multi-agent debate
StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human AvatarsDiffusion models → Audio, speech and music
MAI-UI Technical Report: Real-World Centric Foundation GUI AgentsLLM agents and tool use → GUI and mobile agents
Backdoor Attacks on Prompt-Driven Video Segmentation Foundation ModelsLLM safety and security → Backdoor and data poisoning attacks
FUSCO: High-Performance Distributed Data Shuffling via Transformation-Communication FusionMixture-of-experts → Efficient MoE training and inference systems
iSHIFT: Lightweight Slow-Fast GUI Agent with Adaptive PerceptionMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
Look Closer! An Adversarial Parametric Editing Framework for Hallucination Mitigation in VLMsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
StereoVLA: Enhancing Vision-Language-Action Models with Stereo VisionVision-language-action models → 3D and spatial-aware VLA
Perceive and Calibrate: Analyzing and Enhancing Robustness of Medical Multi-Modal Large Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
SWE-RM: Execution-free Feedback For Software Engineering AgentsLLM reasoning → Reasoning for agents, planning and code +3
Semiparametric Preference Optimization: Your Language Model is Secretly a Single-Index ModelLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Accelerate Speculative Decoding with Sparse Computation in VerificationMixture-of-experts → Efficient MoE training and inference systems +1
High-Fidelity and Long-Duration Human Image Animation with Diffusion TransformerDiffusion models → Video generation
Flexible Multitask Learning with Factorized Diffusion PolicyDiffusion models → Diffusion and flow policies for robotics
MMCTOP: A Multimodal Textualization and Mixture-of-Experts Framework for Clinical Trial Outcome PredictionMixture-of-experts → Medical and biomedical MoE
CrownGen: Patient-customized Crown Generation via Point Diffusion ModelDiffusion models → Medical imaging and segmentation
Aerial World Model for Long-horizon Visual Generation and Navigation in 3D SpaceWorld models → World models for navigation
MASFIN: A Multi-Agent System for Decomposed Financial Reasoning and ForecastingLLM reasoning → Reasoning for agents, planning and code +1
Bridging the Copyright Gap: Do Large Vision-Language Models Recognize and Respect Copyrighted Content?LLM reasoning → Multimodal reasoning +1
EasyOmnimatte: Taming Pretrained Inpainting Diffusion Models for End-to-End Video Layered DecompositionDiffusion models → 3D, point cloud and scene generation
Training-free Conditional Image Embedding Framework Leveraging Large Vision Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Fast Inference of Visual Autoregressive Model with Adjacency-Adaptive Dynamical Draft TreesEfficient LLM inference and serving → Fast autoregressive visual generation
A Comedy of Estimators: On KL Regularization in RL Training of LLMsLLM reasoning → Reinforcement learning for reasoning
Scalable Class-Incremental Learning Based on Parametric Neural CollapseKnowledge distillation → Distillation for continual learning
Knowledge Reasoning of Large Language Models Integrating Graph-Structured Information for Pest and Disease Control in TobaccoLLM reasoning → Knowledge- and tool-augmented reasoning
LOIP:Collaborative Lossless LLM Inference Serving with Offloading-based Pipeline Parallelism on Edge DevicesEfficient LLM inference and serving → Serving systems and request scheduling
Tilt Matching for Scalable Sampling and Fine-TuningDiffusion models → Flow matching, time series and science
Analyzing Code Injection Attacks on LLM-based Multi-Agent Systems in Software DevelopmentLLM agents and tool use → Agent threats, guardrails and governance
High-Entropy Tokens as Multimodal Failure Points in Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
Measuring Stability Beyond Accuracy in Small Open-Source Medical Large Language Models for Pediatric Endocrinology
Safety boundary maintenance in consumer AI systems responding to pediatric health queries: a cross-platform benchmark evaluation under naturalistic and adversarially pressured conditions
Uncertainty-Aware Dynamic Knowledge Graphs for Reliable Question Answering
Bounded Hyperbolic Tangent: A Stable and Efficient Alternative to Pre-Layer Normalization in Large Language Models
NewsScope: Schema-Grounded Cross-Domain News Claim Extraction with Open Models
Beyond Interaction Effects: Two Logics for Studying Population Inequalities
Pediatric Pneumonia Detection from Chest X-Rays:A Comparative Study of Transfer Learning and Custom CNNs
Intrinsic-Metric Physics-Informed Neural Networks (IM-PINN) for Reaction-Diffusion Dynamics on Complex Riemannian Manifolds
Quantitative Rule-Based Strategy modeling in Classic Indian Rummy: A Metric Optimization Approach
Coordinate Matrix Machine: A Human-level Concept Learning to Classify Very Similar Documents
State-of-the-art Small Language Coder Model: Mify-Coder
A Comprehensive Study of Deep Learning Model Fixing Approaches
Hybrid-Code v2: Zero-Hallucination Clinical ICD-10 Coding via Neuro-Symbolic Verification and Automated Knowledge Base Expansion
A Unified AI, Embedded, Simulation, and Mechanical Design Approach to an Autonomous Delivery Robot
Efficient Multi-Model Orchestration for Self-Hosted Large Language Models
Space AI: Leveraging Artificial Intelligence for Space to Improve Life on Earth
Lightweight Inference-Time Personalization for Frozen Knowledge Graph Embeddings
Integrating Wide and Deep Neural Networks with Squeeze-and-Excitation Blocks for Multi-Target Property Prediction in Additively Manufactured Fiber Reinforced Composites
HalluMat: Detecting Hallucinations in LLM-Generated Materials Science Content Through Multi-Stage Verification
iOSPointMapper: RealTime Pedestrian and Accessibility Mapping with Mobile AI
BLISS: Bandit Layer Importance Sampling Strategy for Efficient Training of Graph Neural Networks
LLM-Guided Exemplar Selection for Few-Shot Wearable-Sensor Human Activity Recognition
Completed Hyperparameter Transfer across Modules, Width, Depth, Batch and Duration
Towards Efficient Post-Training via Fourier-Driven Adapter Architectures
The Syntax of qulk-clauses in Yemeni Ibbi Arabic: A Minimalist Approach
Subgoaling Relaxation-based Heuristics for Numeric Planning with Infinite Actions
Human-like visual computing advances explainability and few-shot learning in deep neural networks for complex physiological data
The Effectiveness of Approximate Regularized Replay for Efficient Supervised Fine-Tuning of Large Language Models
Feature Learning with Multi-Stage Vision Transformers on Inter-Modality HER2 Status Scoring and Tumor Classification on Whole Slides
SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence
Emotion classification using EEG headset signals and Random Forest
The Multi-View Paradigm Shift in MRI Radiomics: Predicting MGMT Methylation in Glioblastoma
Expert System for Bitcoin Forecasting: Integrating Global Liquidity via TimeXer Transformers
Role Support in Knowledge-Graph Error Ranking: Predictor Regimes and Evaluation Policies
LangPrecip: Language-Aware Multimodal Precipitation Nowcasting
Optimistic Feasible Search for Closed-Loop Fair Threshold Decision-Making
MoFu: Scale-Aware Modulation and Fourier Fusion for Multi-Subject Video Generation
LLMBoost: Make Large Language Models Stronger with Boosting
LLA: Enhancing Security and Privacy for Generative Models with Logic-Locked Accelerators
Beyond Single Bugs: Benchmarking Large Language Models for Multi-Vulnerability Detection
PDx -- Adaptive Credit Risk Forecasting Model in Digital Lending using Machine Learning Operations
PortionNet: Distilling 3D Geometric Knowledge for Food Nutrition Estimation
Statistical and Machine Learning Analysis of Traffic Accidents on US 158 in Currituck County: A Comparison with HSM Predictions
Real-Time In-Cabin Driver Behavior Recognition on Low-Cost Edge Hardware
ProEdit: Inversion-based Editing From Prompts Done Right
PRAXIS: Integrating Program Analysis with Observability for Root-Cause Analysis
Pruning as a Game: Equilibrium-Driven Sparsification of Neural Networks
Learning Association via Track-Detection Matching for Multi-Object Tracking
Explainable Multimodal Regression via Information Decomposition

All 148