Papers

New on arXiv

Wed 14 May 2025

271 papers

Mind the Metrics: Patterns for Telemetry-Aware In-IDE AI Application Development using the Model Context Protocol (MCP)LLM agents and tool use → Tool learning and function calling
Beyond the Black Box: Interpretability of LLMs in FinanceMechanistic interpretability → Knowledge and representations inside LLMs
MorphMark: Flexible Adaptive Watermarking for Large Language ModelsLLM safety and security → Watermarking generated content and models
Bridging Human Oversight and Black-box Driver Assistance: Vision-Language Models for Predictive Alerting in Lane Keeping Assist SystemsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
A Data Synthesis Method Driven by Large Language Models for Proactive Mining of Implicit User Intentions in TourismSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
Understanding Gen Alpha Digital Language: Evaluation of LLM Safety Systems for Content ModerationLLM safety and security → Safety alignment, refusal and guardrails
Relative Drawing Identification Complexity is Invariant to Modality in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Mission Balance: Generating Under-represented Class Samples using Video Diffusion ModelsDiffusion models → Medical imaging and segmentation
Dyadic Mamba: Long-term Dyadic Human Motion SynthesisState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
KRISTEVA: Close Reading as a Novel Task for Benchmarking Interpretive ReasoningLLM reasoning → Reasoning benchmarks and evaluation
Adversarial Attack on Large Language Models using Exponentiated Gradient DescentLLM safety and security → Jailbreaking
A Multimodal Multi-Agent Framework for Radiology Report GenerationLLM agents and tool use → Medical and scientific domain agents
FAST: An Efficient Scheduler for All-to-All GPU CommunicationMixture-of-experts → Efficient MoE training and inference systems
Trustless Autonomy: Understanding Motivations, Benefits, and Governance Dilemmas in Self-Sovereign Decentralized AI AgentsLLM agents and tool use → Agent threats, guardrails and governance
General Dynamic Goal Recognition using Goal-Conditioned and Meta Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
Risk-Aware Safe Reinforcement Learning for Control of Stochastic Linear SystemsDeep reinforcement learning methods → Safe and constrained RL
Unfettered Forceful Skill Acquisition with Physical Reasoning and Coordinate Frame LabelingLLM reasoning → Spatial and embodied reasoning +1
EnerVerse-AC: Envisioning Embodied Environments with Action ConditionOffline RL and imitation learning from data → Robot manipulation imitation learning
Enabling Group Fairness in Graph Unlearning via Bi-level DebiasingLLM safety and security → Graph unlearning
ManipBench: Benchmarking Vision-Language Models for Low-Level Robot ManipulationLLM reasoning → Spatial and embodied reasoning +1
EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World ModelsWorld models → Video-generation world models and simulators
DRA-GRPO: Your GRPO Needs to Know Diverse Reasoning Paths for Mathematical ReasoningLLM reasoning → Reinforcement learning for reasoning
Language Agents Mirror Human Causal Reasoning Biases. How Can We Help Them Think Like Scientists?LLM reasoning → Reasoning benchmarks and evaluation +1
LightLab: Controlling Light Sources in Images with Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
DataMIL: Selecting Data for Robot Imitation Learning with DatamodelsOffline RL and imitation learning from data → Robot manipulation imitation learning
Adversarial Suffix Filtering: a Defense Pipeline for LLMsLLM safety and security → Jailbreaking
Variational Visual Question Answering for Uncertainty-Aware Selective PredictionLLM reasoning → Multimodal reasoning +1
VTLA: Vision-Tactile-Language-Action Model with Preference Learning for Insertion ManipulationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Ethics and Persuasion in Reinforcement Learning from Human Feedback: A Procedural Rhetorical ApproachLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Don't Forget your Inverse DDIM for Image EditingDiffusion models → Image generation, text-to-image and editing
BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and DatasetDiffusion models → Image generation, text-to-image and editing
Learning Long-Context Diffusion Policies via Past-Token PredictionDiffusion models → Diffusion and flow policies for robotics
WavReward: Spoken Dialogue Models With Generalist Reward EvaluatorsLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
Distilling Realizable Students from Unrealizable TeachersKnowledge distillation → On-policy and self-distillation for LLMs
Spec2VolCAMU-Net: A Spectrogram-to-Volume Model for EEG-to-fMRI Reconstruction based on Multi-directional Time-Frequency Convolutional Attention Encoder and Vision-Mamba U-NetState-space sequence models (S4, Mamba) → Physiological signal modeling
PT-MoE: An Efficient Finetuning Framework for Integrating Mixture-of-Experts into Prompt TuningMixture-of-experts → MoE large language models
Robust Finite-Memory Policy Gradients for Hidden-Model POMDPsDeep reinforcement learning methods → RL theory and sample complexity
Layered Unlearning for Adversarial RelearningLLM safety and security → Machine unlearning
Flash-VL 2B: Optimizing Vision-Language Model Performance for Ultra-Low Latency and High ThroughputMultimodal LLMs / vision-language models → Visual token pruning and efficiency
Reinforcement Learning for Individual Optimal Policy from Heterogeneous DataOffline RL and imitation learning from data → Offline RL algorithms +1
aUToPath: Unified Planning and Control for Autonomous Vehicles in Urban Environments Using Hybrid Lattice and Free-Space SearchEnd-to-end autonomous driving → Imitation-learning end-to-end planners
MrTrack: Register Mamba for Needle Tracking with Rapid Reciprocating Motion during Ultrasound-Guided Aspiration BiopsyState-space sequence models (S4, Mamba) → Mamba for medical image analysis
Evaluating GPT- and Reasoning-based Large Language Models on Physics Olympiad Problems: Surpassing Human Performance and Implications for Educational AssessmentLLM reasoning → Mathematical reasoning
Mini Diffuser: Fast Multi-task Diffusion Policy Training Using Two-level Mini-batchesDiffusion models → Diffusion and flow policies for robotics
Exploring Pose-Guided Imitation Learning for Robotic Precise InsertionOffline RL and imitation learning from data → Robot manipulation imitation learning
FaceShield: Explainable Face Anti-Spoofing with Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
The Influence of Human-inspired Agentic Sophistication in LLM-driven Strategic ReasonersLLM reasoning → Reasoning for agents, planning and code +1
Qwen3 Technical ReportLLM reasoning → Reasoning benchmarks and evaluation +1
MAKE: Multi-Aspect Knowledge-Enhanced Vision-Language Pretraining for Zero-shot Dermatological AssessmentMultimodal LLMs / vision-language models → Medical vision-language models
TensorRL-QAS: Reinforcement learning with tensor networks for improved quantum architecture searchDeep reinforcement learning methods → Quantum reinforcement learning
Diffusion Recommender Models and the Illusion of Progress: A Concerning Study of Reproducibility and a Conceptual MismatchDiffusion models → Diffusion recommenders
Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image AnalysisDiffusion models → Diffusion foundations and sampling
Insights into DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI ArchitecturesMixture-of-experts → Efficient MoE training and inference systems
RAG-Enabled Intent Reasoning for Application-Network InteractionRetrieval-augmented generation → Agentic RAG, agents and memory
Unsupervised Multiview Contrastive Language-Image Joint Learning with Pseudo-Labeled Prompts Via Vision-Language Model for 3D/4D Facial Expression RecognitionMultimodal LLMs / vision-language models → Multimodal emotion understanding
DCSNet: A Lightweight Knowledge Distillation-Based Model with Explainable AI for Lung Cancer Diagnosis from Histopathological ImagesKnowledge distillation → Distillation for medical imaging
Scent of Knowledge: Optimizing Search-Enhanced Reasoning with Information ForagingLLM reasoning → Knowledge- and tool-augmented reasoning +1
TransDiffuser: Diverse Trajectory Generation with Decorrelated Multi-modal Representation for End-to-end Autonomous DrivingDiffusion models → Diffusion and flow policies for robotics +1
Reproducibility Study of "Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents"LLM agents and tool use → General LLM agent frameworks and benchmarks
Generating Full-field Evolution of Physical Dynamics from Irregular Sparse ObservationsDiffusion models → Flow matching, time series and science
MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-LearningMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
Few-Shot Anomaly-Driven Generation for Anomaly Classification and SegmentationDiffusion models → Flow matching, time series and science
Zero-Shot Multi-modal Large Language Model v.s. Supervised Deep Learning: A Comparative Study on CT-Based Intracranial Hemorrhage SubtypingMultimodal LLMs / vision-language models → Medical vision-language models
AMSnet 2.0: A Large AMS Database with AI Segmentation for Net DetectionMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
Latent Theory of Mind: A Decentralized Diffusion Architecture for Cooperative ManipulationDiffusion models → Diffusion and flow policies for robotics
ELIS: Efficient LLM Iterative Scheduling System with Response Length PredictorEfficient LLM inference and serving → Serving systems and request scheduling
TopoDiT-3D: Topology-Aware Diffusion Transformer with Bottleneck Structure for 3D Point Cloud GenerationDiffusion models → 3D, point cloud and scene generation
Beyond General Prompts: Automated Prompt Refinement using Contrastive Class Alignment Scores for Disambiguating Objects in Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Seeing Beyond the Scene: Enhancing Vision-Language Models with Interactional ReasoningLLM reasoning → Spatial and embodied reasoning +1
Beyond the Known: Decision Making with Counterfactual Reasoning Decision TransformerOffline RL and imitation learning from data → Decision transformers and sequence modeling
OpenLKA: An Open Dataset of Lane Keeping Assist from Recent Car Models under Real-world Driving ConditionsEnd-to-end autonomous driving → VLMs for autonomous driving
Generating time-consistent dynamics with discriminator-guided image diffusion modelsDiffusion models → Flow matching, time series and science
Ornithologist: Towards Trustworthy "Reasoning" about Central Bank CommunicationsLLM reasoning → Reasoning for agents, planning and code
SALM: A Multi-Agent Framework for Language Model-Driven Social Network SimulationLLM agents and tool use → Social simulation and multi-agent debate
Trends in Motion Prediction Toward Deployable and Generalizable Autonomy: A Revisit and PerspectivesWorld models → World models for autonomous driving
S-DAT: A Multilingual, GenAI-Driven Framework for Automated Divergent Thinking AssessmentLLM reasoning → Reasoning benchmarks and evaluation
Atomic Consistency Preference Optimization for Long-Form Question AnsweringLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
The Architecture of Cognitive Amplification: Enhanced Cognitive Scaffolding as a Resolution to the Comfort-Growth Paradox in Human-AI Cognitive Integration
Extracting Knowledge Graphs from User Stories using LangChain
An Efficient deep learning model to Predict Stock Price Movement Based on Limit Order Book
Using Cross-Domain Detection Loss to Infer Multi-Scale Information for Improved Tiny Head Tracking
Sequence-Only Prediction of Binding Affinity Changes: A Robust and Interpretable Model for Antibody Engineering
Should We Simultaneously Calibrate Multiple Computer Models?
Evaluation in EEG Emotion Recognition: State-of-the-Art Review and Unified Framework
NMCSE: Noise-Robust Multi-Modal Coupling Signal Estimation Method via Optimal Transport for Cardiovascular Disease Detection
GenAI Security: Outsmarting the Bots with a Proactive Testing Framework
Robust Knowledge Graph Embedding via Denoising
Load Forecasting in the Era of Smart Grids: Opportunities and Advanced Machine Learning Models
Interpretable Multi-Task PINN for Emotion Recognition and EDA Prediction
Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation
Dim and Small Target Detection for Drone Broadcast Frames Based on Time-Frequency Analysis
Towards scalable surrogate models based on Neural Fields for large scale aerodynamic simulations
LLM4CD: Leveraging Large Language Models for Open-World Knowledge Augmented Cognitive Diagnosis
ProdRev: A DNN framework for empowering customers using generative pre-trained transformers
Contrastive Cross-Course Knowledge Tracing via Concept Graph Guided Knowledge Transfer
Source framing triggers systematic evaluation bias in Large Language Models
TARGET: Benchmarking Table Retrieval for Generative Tasks
Cybersecurity threat detection based on a UEBA framework using Deep Autoencoders
BrainNetMLP: An Efficient and Effective Baseline for Functional Brain Network Classification
Empirical Performance Evaluation of Lane Keeping Assist on Modern Production Vehicles

All 271