Papers

New on arXiv

Sat 19 Apr 2025

139 papers

Leveraging Generative AI Models to Explore Human IdentityDiffusion models → Image generation, text-to-image and editing
Improving the Serving Performance of Multi-LoRA Large Language Models via Efficient LoRA and KV Cache ManagementEfficient LLM inference and serving → KV cache optimization
SOTOPIA-S4: a user-friendly system for flexible, customizable, and large-scale social simulationLLM agents and tool use → Social simulation and multi-agent debate
LegalRAG: A Hybrid RAG System for Multilingual Legal Information RetrievalRetrieval-augmented generation → Legal and financial RAG
A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic ContentLLM safety and security → Safety alignment, refusal and guardrails
LLM-Enabled Style and Content Regularization for Personalized Text-to-Image GenerationDiffusion models → Image generation, text-to-image and editing
Unlearning Works Better Than You Think: Local Reinforcement-Based Selection of Auxiliary ObjectivesDeep reinforcement learning methods → RL for games and combinatorial optimization
Quantum-Enhanced Reinforcement Learning for Power Grid Security AssessmentDeep reinforcement learning methods → Quantum reinforcement learning
SphereDiff: Tuning-free 360deg Static and Dynamic Panorama Generation via Spherical Latent RepresentationDiffusion models → 3D, point cloud and scene generation
Hydra: An Agentic Reasoning Approach for Enhancing Adversarial Robustness and Mitigating Hallucinations in Vision-Language ModelsLLM reasoning → Hallucination detection and mitigation +2
How Well Can General Vision-Language Models Learn Medicine By Watching Public Educational Videos?Multimodal LLMs / vision-language models → Medical vision-language models
The Geometry of Self-Verification in a Task-Specific Reasoning ModelLLM reasoning → Test-time compute and efficient thinking
Efficient Spiking Point Mamba for Point Cloud AnalysisState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
Improving RL Exploration for LLM Reasoning through Retrospective ReplayLLM reasoning → Reinforcement learning for reasoning
A Multimodal Recaptioning Framework to Account for Perceptual Diversity Across Languages in Vision-Language ModelingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
An Empirical Study of LLM Reasoning Ability Under Strict Output Length ConstraintLLM reasoning → Test-time compute and efficient thinking
Manipulating Multimodal Agents via Cross-Modal Prompt InjectionMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +2
Visual Prompting for One-shot Controllable Video Editing without InversionDiffusion models → Video generation
FAIRGAME: a Framework for AI Agents Bias Recognition using Game TheoryLLM agents and tool use → Social simulation and multi-agent debate
Learning from Stochastic Teacher Representations Using Student-Guided Knowledge DistillationKnowledge distillation → General knowledge distillation methods
From Missing Pieces to Masterpieces: Image Completion with Context-Adaptive DiffusionDiffusion models → 3D, point cloud and scene generation
The Path to Reconciling Quality and Safety in Text-to-Image Generation: Dataset, Method, and EvaluationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment +1
SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLMLLM reasoning → Reinforcement learning for reasoning
ProtPainter: Draw or Drag Protein via Topology-guided DiffusionDiffusion models → Flow matching, time series and science
Mixed-Precision Conjugate Gradient Solvers with RL-Driven Precision TuningDeep reinforcement learning methods → RL theory and sample complexity
Text-Audio-Visual-conditioned Diffusion Model for Video Saliency PredictionDiffusion models → Video generation
Towards Explainable Fake Image Detection with Multi-Modal Large Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative ReasonersLLM reasoning → Multimodal reasoning +2
Template-Based Financial Report Generation in Agentic and Decomposed Information RetrievalLLM agents and tool use → Financial trading and forecasting agents
Beyond Retraining: Training-Free Unknown Class Filtering for Source-Free Open Set Domain Adaptation of Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Understanding the Repeat Curse in Large Language Models from a Feature PerspectiveMechanistic interpretability → SAE features and their applications
Learning Joint ID-Textual Representation for ID-Preserving Image SynthesisDiffusion models → Image generation, text-to-image and editing
Enhancing Multimodal In-Context Learning for Image Classification through Coreset OptimizationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Direct Advantage Regression: Aligning LLMs with Online AI RewardLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Hypothetical Documents or Knowledge Leakage? Rethinking LLM-based Query ExpansionLLM reasoning → Knowledge- and tool-augmented reasoning
DIP: Efficient Large Multimodal Model Training with Dynamic Interleaved PipelineMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
PVLM: Parsing-Aware Vision Language Model with Dynamic Contrastive Learning for Zero-Shot Deepfake AttributionMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
Bayesian Principles Improve Prompt Learning In Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
CodeCrash: Exposing LLM Fragility to Misleading Natural Language in Code ReasoningLLM reasoning → Reasoning for agents, planning and code
PEFT A2Z: Parameter-Efficient Fine-Tuning Survey for Large Language and Vision ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
EmbedAgent: Benchmarking Large Language Models in Embedded System Development
On the Residual-based Neural Network for Unmodeled Distortions in Coordinate Transformation
Analyzing Feedback Mechanisms in AI-Generated MCQs: Insights into Readability, Lexical Properties, and Levels of Challenge
Mind the Language Gap: Automated and Augmented Evaluation of Bias in LLMs for High- and Low-Resource Languages
RINN: One Sample Radio Frequency Imaging based on Physics Informed Neural Network
Power Transformer Health Index and Life Span Assessment: A Comprehensive Review of Conventional and Machine Learning based Approaches
Optimal Scheduling of Dynamic Transport
Adversarial Attack for RGB-Event based Visual Object Tracking
Optimal Lattice Boltzmann Closures through Multi-Agent Reinforcement Learning
Exploring Pseudo-Token Approaches in Transformer Neural Processes
Planet as a Brain: Towards Internet of AgentSites based on AIOS Server
Data Augmentation Using Neural Acoustic Fields With Retrieval-Augmented Pre-training
ScholarMate: A Mixed-Initiative Tool for Qualitative Knowledge Work and Information Sensemaking
Balancing Fairness and Performance in Healthcare AI: A Gradient Reconciliation Approach
LOOPE: Learnable Optimal Patch Order in Positional Embeddings for Vision Transformers
Machine learning enhanced atom probe tomography analysis: a snapshot review
Bottom-Up Synthesis of Knowledge-Grounded Task-Oriented Dialogues with Iteratively Self-Refined Prompts
SEGA: Drivable 3D Gaussian Head Avatar from a Single Image
Learning Enhanced Structural Representations with Block-Based Uncertainties for Ocean Floor Mapping
Density Measures for Language Generation
Do You Really Need Public Data? Surrogate Public Data for Differential Privacy on Tabular Data
Diverse Prompts: Illuminating the Prompt Space of Large Language Models with MAP-Elites
What Matters in Linearizing Language Models? A Comparative Study of Architecture, Scale, and Task Adaptation
Accelerating LLM Inference with Flexible N:M Sparsity via A Fully Digital Compute-in-Memory Accelerator
Integrating Single-Cell Foundation Models with Graph Neural Networks for Drug Response Prediction
Mathematical Programming Models for Exact and Interpretable Formulation of Neural Networks
LLM-Enhanced Black-Litterman Portfolio Optimization
Multispectral airborne laser scanning for tree species classification: a benchmark of machine learning and deep learning algorithms
Multimodal Coreference Resolution for Chinese Social Media Dialogues: Dataset and Benchmark Approach
Expanding the Generative AI Design Space through Structured Prompting and Multimodal Interfaces
Local distribution-based adaptive oversampling for imbalanced regression
DCFG: Diverse Cross-Channel Fine-Grained Feature Learning and Progressive Fusion Siamese Tracker for Thermal Infrared Target Tracking
FGSGT: Saliency-Guided Siamese Network Tracker Based on Key Fine-Grained Feature Information for Thermal Infrared Target Tracking
Exploring Generalizable Pre-training for Real-world Change Detection via Geometric Estimation
Learning to Score
Balancing Privacy and Action Performance: A Penalty-Driven Approach to Image Anonymization
Learning and Generating Diverse Residential Load Patterns Using GAN with Weakly-Supervised Training and Weight Selection
RadioDiff-Inverse: Diffusion Enhanced Bayesian Inverse Estimation for ISAC Radio Map Construction
ISTD-YOLO: A Multi-Scale Lightweight High-Performance Infrared Small Target Detection Algorithm
Probing the Subtle Ideological Manipulation of Large Language Models
CHAINSFORMER: Numerical Reasoning on Knowledge Graphs from a Chain Perspective
CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Survey
RAMCT: Novel Region-adaptive Multi-channel Tracker with Iterative Tikhonov Regularization for Thermal Infrared Tracking
Generative emulation of chaotic dynamics with coherent prior
Cross-attention for State-based model RWKV-7
Experience-based Refinement of Task Planning Knowledge in Autonomous Robots
HoLa: B-Rep Generation using a Holistic Latent Representation
Visual Consensus Prompting for Co-Salient Object Detection
ColorVein: Colorful Cancelable Vein Biometrics
Towards Anomaly-Aware Pre-Training and Fine-Tuning for Graph Anomaly Detection
Any Image Restoration via Efficient Spatial-Frequency Degradation Adaptation
Rethinking Traffic Flow Forecasting: From Transition to Generatation
A Knowledge-Informed Deep Learning Paradigm for Generalizable and Stability-Optimized Car-Following Models
ROI-Guided Point Cloud Geometry Compression Towards Human and Machine Vision
Single Document Image Highlight Removal via A Large-Scale Real-World Dataset and A Location-Aware Network
A Novel Frequency-Spatial Domain Aware Network for Fast Thermal Prediction in 2.5D ICs
Assessing AI-Generated Questions' Alignment with Cognitive Frameworks in Educational Assessment
Exploring Modality Guidance to Enhance VFM-based Feature Fusion for UDA in 3D Semantic Segmentation
Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale
SimplifyMyText: An LLM-Based System for Inclusive Plain Language Text Simplification

All 139