Papers

New on arXiv

Sat 22 Mar 2025

134 papers

Advancing Intelligent Sequence Modeling: Evolution, Trade-offs, and Applications of State-Space Architectures from S4 to MambaState-space sequence models (S4, Mamba) → Core SSM architectures for language
Reasoning with LLMs for Zero-Shot Vulnerability DetectionLLM reasoning → Reasoning for agents, planning and code
Think Before Refusal : Triggering Safety Reflection in LLMs to Mitigate False Refusal BehaviorLLM reasoning → Reasoning for agents, planning and code
good4cir: Generating Detailed Synthetic Captions for Composed Image RetrievalMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
Understanding Inverse Reinforcement Learning under Overparameterization: Non-Asymptotic Analysis and Global OptimalityOffline RL and imitation learning from data → Inverse reinforcement learning +1
Enhancing Retrieval Systems with Inference-Time Logical ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
4D-Bench: Benchmarking Multi-modal Large Language Models for 4D Object UnderstandingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
DVG-Diffusion: Dual-View Guided Diffusion Model for CT Reconstruction from X-RaysDiffusion models → Medical imaging and segmentation
A Roadmap Towards Improving Multi-Agent Reinforcement Learning With Causal Discovery And InferenceLLM reasoning → Causal reasoning in LLMs
Every Sample Matters: Leveraging Mixture-of-Experts and High-Quality Data for Efficient and Accurate Code LLMMixture-of-experts → MoE large language models
GOAL: Global-local Object Alignment LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Bandwidth Reservation for Time-Critical Vehicular Applications: A Multi-Operator EnvironmentDeep reinforcement learning methods → RL for energy, networks and operations
Building Resource-Constrained Language Agents: A Korean Case Study on Chemical Toxicity InformationLLM agents and tool use → General LLM agent frameworks and benchmarks
Enhancing Arabic Automated Essay Scoring with Synthetic Data and Error InjectionSynthetic data and self-improvement for LLMs → LLM synthetic data generation
V2P-Bench: Evaluating Video-Language Understanding with Visual Prompts for Better Human-Model InteractionMultimodal LLMs / vision-language models → Video understanding with MLLMs
DynASyn: Multi-Subject Personalization Enabling Dynamic Action SynthesisDiffusion models → Image generation, text-to-image and editing
A Survey on Mathematical Reasoning and Optimization with Large Language ModelsLLM reasoning → Mathematical reasoning
Trigger without Trace: Towards Stealthy Backdoor Attack on Text-to-Image Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
GUI-Xplore: Empowering Generalizable GUI Agents with One ExplorationLLM agents and tool use → GUI and mobile agents
PipeBoost: Resilient Pipelined Architecture for Fast Serverless LLM ScalingEfficient LLM inference and serving → Serving systems and request scheduling
RAIDER: Tool-Equipped Large Language Model Agent for Robotic Action Issue Detection, Explanation and RecoveryLLM agents and tool use → General LLM agent frameworks and benchmarks
MAMAT: 3D Mamba-Based Atmospheric Turbulence Removal and its Object Detection CapabilityState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human FeedbackMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
Computationally and Sample Efficient Safe Reinforcement Learning Using Adaptive Conformal PredictionDeep reinforcement learning methods → Safe and constrained RL
Towards Transformer-Based Aligned Generation with Self-Coherence GuidanceDiffusion models → Image generation, text-to-image and editing
ComfyGPT: A Self-Optimizing Multi-Agent System for Comprehensive ComfyUI Workflow GenerationLLM agents and tool use → Software engineering coding agents
OMR-Diffusion:Optimizing Multi-Round Enhanced Training in Diffusion Models for Improved Intent UnderstandingDiffusion models → Image generation, text-to-image and editing
Improving Diffusion Generative Models via Truncated Karhunen--Lo`eve ExpansionDiffusion models → Diffusion foundations and sampling
LZMidi: Compression-Based Symbolic Music GenerationDiffusion models → Audio, speech and music
A Modular Dataset to Demonstrate LLM Abstraction CapabilityLLM reasoning → Reasoning benchmarks and evaluation
On The Sample Complexity Bounds In Bilevel Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
Planning and Learning in Average Risk-aware MDPsDeep reinforcement learning methods → RL theory and sample complexity
Transferable Latent-to-Latent Locomotion Policy for Efficient and Versatile Motion Control of Diverse Legged RobotsDeep reinforcement learning methods → RL for robot locomotion and manipulation
Feature Selection Based on Reinforcement Learning and Hazard State Classification for Magnetic Adhesion Wall-Climbing RobotsDeep reinforcement learning methods → Safe and constrained RL
OmniScience: A Domain-Specialized LLM for Scientific Reasoning and DiscoveryLLM reasoning → Knowledge- and tool-augmented reasoning +1
Guidance Free Image Editing via Explicit ConditioningDiffusion models → Diffusion foundations and sampling
ConSol: Sequential Probability Ratio Testing to Find Consistent LLM Reasoning Paths EfficientlyLLM reasoning → Test-time compute and efficient thinking
Neural Network Operator-Based Fractal Approximation: Smoothness Preservation and Convergence Analysis
DoYouTrustAI: A Tool to Teach Students About AI Misinformation and Prompt Engineering
The Effect of Explainable AI-based Decision Support on Human Task Performance: A Meta-Analysis
EqualizeIR: Mitigating Linguistic Biases in Retrieval Models
ChatBench: From Static Benchmarks to Human-AI Evaluation
Process Optimization and Deployment for Sensor-Based Human Activity Recognition Based on Deep Learning
Revisiting Outage for Edge Inference Systems
Robust Blind Channel Estimation for Bursty Impulsive Noise with a Constrained EM Approach
Differentiable Optimization for Deep Learning-Enhanced DC Approximation of AC Optimal Power Flow
Meta-Representational Predictive Coding: Neuroscience-Informed Self-Supervised Learning
Threshold Adaptation in Spiking Networks Enables Shortest Path Finding and Place Disambiguation
EXPLICATE: Enhancing Phishing Detection through Explainable AI and LLM-Powered Interpretability
Synthetic media and computational capitalism: towards a critical theory of artificial intelligence
Machine Learning - Driven Materials Discovery: Unlocking Next-Generation Functional Materials - A review
Automated diagnosis of lung diseases using vision transformer: a comparative study on chest x-ray classification
LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Models
IceBench: A Benchmark for Deep Learning based Sea Ice Type Classification
Satisfactory Medical Consultation based on Terminology-Enhanced Information Retrieval and Emotional In-Context Learning
Accelerating and enhancing thermodynamic simulations of electrochemical interfaces
Detecting and Mitigating DDoS Attacks with AI: A Survey
A Causal Adjustment Module for Debiasing Scene Graph Generation
ClaraVid: A Holistic Scene Reconstruction Benchmark From Aerial Perspective With Delentropy-Based Complexity Profiling
A novel gradient-based method for decision trees optimizing arbitrary differential loss functions
Graphical Transformation Models
Adapt, Agree, Aggregate: Semi-Supervised Ensemble Labeling for Graph Convolutional Networks
A Study on the Improvement of Code Generation Quality Using Large Language Models Leveraging Product Documentation
FundusGAN: A Hierarchical Feature-Aware Generative Framework for High-Fidelity Fundus Image Generation
Fractal-IR: A Unified Framework for Efficient and Scalable Image Restoration
On the Minimax Regret of Sequential Probability Assignment via Square-Root Entropy
Metacognition in Content-Centric Computational Cognitive C4 Modeling
OvercookedV2: Rethinking Overcooked for Zero-Shot Coordination
RefCut: Interactive Segmentation with Reference Guidance
LightLoc: Learning Outdoor LiDAR Localization at Light Speed
Feather-SQL: A Lightweight NL2SQL Framework with Dual-Model Collaboration Paradigm for Small Language Models
ParsiPy: NLP Toolkit for Historical Persian Texts in Python
Poisson-Process Topic Model for Integrating Knowledge from Pre-trained Language Models
Neural Network Approach to Stochastic Dynamics for Smooth Multimodal Density Estimation
Relation Extraction with Instance-Adapted Predicate Descriptions
GaussianFocus: Constrained Attention Focus for 3D Gaussian Splatting
Enhancing Fourier Neural Operators with Local Spatial Features
Progressive Prompt Detailing for Improved Alignment in Text-to-Image Generative Models
Topology preserving Image segmentation using the iterative convolution-thresholding method
From 2D Alignment to 3D Plausibility: Unifying Heterogeneous 2D Priors and Penetration-Free Diffusion for Occlusion-Robust Two-Hand Reconstruction
Assessing workflow impact and clinical utility of AI-assisted brain aneurysm detection: a multi-reader study
MEPNet: Medical Entity-balanced Prompting Network for Brain CT Report Generation
Energy-Aware LLMs: A step towards sustainable AI for downstream applications
Hierarchy-Aware and Channel-Adaptive Semantic Communication for Bandwidth-Limited Data Fusion
Renewable Energy Transition in South America: Predictive Analysis of Generation Capacity by 2050
Lifelong Evolution of Swarms
CODA: Repurposing Continuous VAEs for Discrete Tokenization
Improving Preference Extraction In LLMs By Identifying Latent Knowledge Through Classifying Probes
HiLoTs: High-Low Temporal Sensitive Representation Learning for Semi-Supervised LiDAR Segmentation in Autonomous Driving
Serial Low-rank Adaptation of Vision Transformer
RDTF: Resource-efficient Dual-mask Training Framework for Multi-frame Animated Sticker Generation
GS-LTS: 3D Gaussian Splatting-Based Adaptive Modeling for Long-Term Service Robots
Co-op: Correspondence-based Novel Object Pose Estimation
Aportes para el cumplimiento del Reglamento (UE) 2024/1689 en rob'otica y sistemas aut'onomos
BackMix: Regularizing Open Set Recognition by Removing Underlying Fore-Background Priors
EMPLACE: Self-Supervised Urban Scene Change Detection
Normalized Matching Transformer
Multi-modality Anomaly Segmentation on the Road
Slide2Text: Leveraging LLMs for Personalized Textbook Generation from PowerPoint Presentations
PT-PINNs: A Parametric Engineering Turbulence Solver based on Physics-Informed Neural Networks

All 134