Papers

New on arXiv

Sun 13 Jul 2025

162 papers

Two-Stage Sketch-Based Smoke Illustration Generation using Stream FunctionDiffusion models → Image generation, text-to-image and editing
MountainLion: A Multi-Modal LLM-Based Agent System for Interpretable and Adaptive Financial TradingLLM agents and tool use → Financial trading and forecasting agents
From Reasoning to Super-Intelligence: A Search-Theoretic PerspectiveLLM reasoning → Prompting and chain-of-thought reasoning
eSapiens's DEREK Module: Deep Extraction & Reasoning Engine for Knowledge with LLMsLLM reasoning → Knowledge- and tool-augmented reasoning +1
Meta-Reinforcement Learning for Fast and Data-Efficient Spectrum Allocation in Dynamic Wireless NetworksDeep reinforcement learning methods → RL for energy, networks and operations
Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces ThemLLM reasoning → Reinforcement learning for reasoning
LaSM: Layer-wise Scaling Mechanism for Defending Pop-up Attack on GUI AgentsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
NegRefine: Refining Negative Label-Based Zero-Shot OOD DetectionMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Leveraging Distribution Matching to Make Approximate Machine Unlearning FasterLLM safety and security → Machine unlearning
Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and ReflowDiffusion models → Flow matching, time series and science
Knowing When to Quit: Probabilistic Early Exits for Speech SeparationEfficient LLM inference and serving → Early exit and edge inference
Explainable AI in Genomics: Transcription Factor Binding Site Prediction with Mixture of ExpertsMixture-of-experts → Medical and biomedical MoE
Sound and Complete Neurosymbolic Reasoning with LLM-Grounded InterpretationsLLM reasoning → Reasoning benchmarks and evaluation
Advancing Text-to-3D Generation with Linearized Lookahead Variational Score DistillationDiffusion models → 3D, point cloud and scene generation
Universal Physics Simulation: A Foundational Diffusion ApproachDiffusion models → Flow matching, time series and science
Large Language Models Encode Semantics and Alignment in Linearly Separable RepresentationsLLM safety and security → Safety alignment, refusal and guardrails
Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AIEfficient LLM inference and serving → Token pruning and merging for ViTs
Towards Concise and Adaptive Thinking in Large Reasoning Models: A SurveyLLM reasoning → Test-time compute and efficient thinking
Negotiating Comfort: Simulating Personality-Driven LLM Agents in Shared Residential Social NetworksLLM agents and tool use → Social simulation and multi-agent debate
Cultivating Pluralism In Algorithmic Monoculture: The Community Alignment DatasetLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Can Group Relative Policy Optimization Improve Thai Legal Reasoning and Question Answering?LLM reasoning → Reasoning for agents, planning and code +1
Bridging Bots: from Perception to Action via Multimodal-LMs and Knowledge GraphsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Towards Fine-Grained Adaptation of CLIP via a Self-Trained Alignment ScoreMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP +1
I2I-PR: Deep Iterative Refinement for Phase Retrieval using Image-to-Image Diffusion ModelsDiffusion models → Inverse problems and image restoration
DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient DifferencesLLM safety and security → Federated unlearning and poisoning
Demystifying Flux ArchitectureDiffusion models → Image generation, text-to-image and editing
eSapiens: A Platform for Secure and Auditable Retrieval-Augmented GenerationRetrieval-augmented generation → Agentic RAG, agents and memory
Enhancing Stereo Sound Event Detection with BiMamba and Pretrained PSELDnetState-space sequence models (S4, Mamba) → Speech and audio SSMs
Learning to Control Dynamical Agents via Spiking Neural Networks and Metropolis-Hastings SamplingDeep reinforcement learning methods → Spiking and neuromorphic RL
Consistency Trajectory Planning: High-Quality and Efficient Trajectory Optimization for Offline Model-Based Reinforcement LearningOffline RL and imitation learning from data → Diffusion and flow policies for offline RL
An Analysis of Action-Value Temporal-Difference Methods That Learn State ValuesDeep reinforcement learning methods → RL theory and sample complexity
QuarterMap: Efficient Post-Training Token Pruning for Visual State Space ModelsEfficient LLM inference and serving → Token pruning and merging for ViTs
Advancing Reliable Test-Time Adaptation of Vision-Language Models under Visual VariationsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
GLIMPSE: Do Large Vision-Language Models Truly Think With Videos or Just Glimpse at Them?LLM reasoning → Multimodal reasoning +1
HMID-Net: An Exploration of Masked Image Modeling and Knowledge Distillation in Hyperbolic SpaceKnowledge distillation → General knowledge distillation methods
Evaluating LLMs on Sequential API Call Through Automated Test GenerationLLM agents and tool use → Tool learning and function calling
Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMsLLM reasoning → Knowledge- and tool-augmented reasoning +2
RectifiedHR: High-Resolution Diffusion via Energy Profiling and Adaptive Guidance SchedulingDiffusion models → Diffusion foundations and sampling
Visuo-Acoustic Hand Pose and Contact Estimation
Adversarial Demonstration Learning for Low-resource NER Using Dual Similarity
From Cell Towers to Satellites: A 2040 Blueprint for Urban-Grade Direct-to-Device Mobile Networks
AI-Based Impedance Encoding-Decoding Method for Online Impedance Network Construction of Wind Farms
A Disentangled Representation Learning Framework for Low-altitude Network Coverage Prediction
Latent Sensor Fusion: Multimedia Learning of Physiological Signals for Resource-Constrained Devices
Physics-guided impact localisation and force estimation in composite plates with uncertainty quantification
The AI Ethical Resonance Hypothesis: The Possibility of Discovering Moral Meta-Patterns in AI Systems
Landmark Detection for Medical Images using a General-purpose Segmentation Model
Deformable Dynamic Convolution for Accurate yet Efficient Spatio-Temporal Traffic Prediction
A Memory-Efficient Framework for Deformable Transformer with Neural Architecture Search
LLMs Meet Cross-Modal Time Series Analytics: Overview and Directions
Compute Requirements for Algorithmic Innovation in Frontier AI Models
Fine-tuning Large Language Model for Automated Algorithm Design
Sub-Scaling Laws: On the Role of Data Density and Training Strategies in LLMs
FedGSCA: Medical Federated Learning with Global Sample Selector and Client Adaptive Adjuster under Label Noise
A Feed-Forward Artificial Intelligence Pipeline for Sustainable Desalination under Climate Uncertainties: UAE Insights
The Shape of Deceit: Behavioral Consistency and Fragility in Money Laundering Patterns
Neural Expectation Operators
DALI-PD: Diffusion-based Synthetic Layout Heatmap Generation for ML in Physical Design
RedOne: Revealing Domain-specific LLM Post-Training in Social Networking Services
Generative Cognitive Diagnosis
Hierarchical Abstraction Enables Human-Like 3D Object Recognition in Deep Learning Models
Regret Analysis of Posterior Sampling-Based Expected Improvement for Bayesian Optimization
Bridging Neural Networks and Dynamic Time Warping for Adaptive Time Series Classification
Nesterov Finds GRAAL: Optimal and Adaptive Gradient Method for Convex Optimization
Compressed Computation: Dense Circuits in a Toy Model of the Universal-AND Problem
VRU-Accident: A Vision-Language Benchmark for Video Question Answering and Dense Captioning for Accident Scene Understanding
Federated Learning with Graph-Based Aggregation for Traffic Forecasting
Technical Requirements for Halting Dangerous AI Activities
A Scalable and Efficient Signal Integration System for Job Matching
CADmium: Fine-Tuning Code Language Models for Text-Driven Sequential CAD Design
Prompting for Performance: Exploring LLMs for Configuring Software
TinyTroupe: An LLM-powered Multiagent Persona Simulation Toolkit
Physics-informed neural networks for high-dimensional solutions and snaking bifurcations in nonlinear lattices
BitParticle: Partializing Sparse Dual-Factors to Build Quasi-Synchronizing MAC Arrays for Energy-efficient DNNs
Te Ahorr'e Un Click: A Revised Definition of Clickbait and Detection in Spanish News
Pairwise Alignment & Compatibility for Arbitrarily Irregular Image Fragments
Toward accurate RUL and SoH estimation using reinforced graph-based physics-informed neural networks enhanced with dynamic weights
EventHunter: Dynamic Clustering and Ranking of Security Events from Hacker Forum Discussions
AI-Enhanced Pediatric Pneumonia Detection: A CNN-Based Approach Using Data Augmentation and Generative Adversarial Networks (GANs)
Your Pretrained Model Tells the Difficulty Itself: A Self-Adaptive Curriculum Learning Paradigm for Natural Language Understanding
Energy Dissipation Rate Guided Adaptive Sampling for Physics-Informed Neural Networks: Resolving Surface-Bulk Dynamics in Allen-Cahn Systems
Do we need equivariant models for molecule generation?
MB-RIRs: a Synthetic Room Impulse Response Dataset with Frequency-Dependent Absorption Coefficients
Causality-informed Anomaly Detection in Partially Observable Sensor Networks: Moving beyond Correlations
Discovering Governing Equations in the Presence of Uncertainty
Continental-scale habitat distribution modelling with multimodal earth observation foundation models
Pre-trained Under Noise: A Framework for Robust Bone Fracture Detection in Medical Imaging
Visual Homing in Outdoor Robots Using Mushroom Body Circuits and Learning Walks
Signed Graph Learning: Algorithms and Theory
Phase transition of the Sinkhorn-Knopp algorithm
EPT-2 Technical Report
MCEval: A Dynamic Framework for Fair Multilingual Cultural Evaluation of LLMs
Frequency-aware Surrogate Modeling With SMT Kernels For Advanced Data Forecasting
ExpStar: Towards Automatic Commentary Generation for Multi-discipline Scientific Experiments
Post-Training Quantization of Generative and Discriminative LSTM Text Classifiers: A Study of Calibration, Class Balance, and Robustness
Symptom-Driven Personalized Proton Pump Inhibitors Therapy Using Bayesian Neural Networks and Model Predictive Control
Networked Information Aggregation via Machine Learning
OrQstrator: An AI-Powered Framework for Advanced Quantum Circuit Optimization
Seamless High-Resolution Terrain Reconstruction: A Prior-Based Vision Transformer Approach
Conformal Prediction for Privacy-Preserving Machine Learning

All 162