ai-toolsMay 19, 2026
Multi-axis Analysis of Image Manipulation Localization
Advanced image editing software enables easy creation of highly convincing image manipulations, which has been made even more accessible in recent years…
Read Full Story
Research & Analysis
Research & Analysis
In-depth research papers, case studies, surveys, and academic insights on finance and technology
Articles
472
Updated
May 19, 2026
Category
RESEARCH
Top Stories
View Allai-tools12:00 AM
Long-term Power Grid Planning via Answer Set Programming
The Power grid is a critical infrastructure underpinning all aspects of modern society and its services. Maintaining its effectiveness requires…
ai-tools12:00 AM
HaorFloodAlert: Deseasonalized ML Ensemble for 72-Hour Flood Prediction in Bangladesh Haor Wetlands
Flash floods in Bangladesh's haor wetlands show up with almost no warning. They wreck the annual boro rice harvest. Current setups, built for riverine…
ai-tools12:00 AM
Atoms of Thought: Universal EEG Representation Learning with Microstates
Learning universal representations from electroencephalogram (EEG) signals is a cutting-edge approach in the field of neuroinformatics and brain-computer…
ai-tools12:00 AM
A Methodology for Selecting and Composing Runtime Architecture Patterns for Production LLM Agents
Production LLM agents combine stochastic model outputs with deterministic software systems, yet the boundary between the two is rarely treated as a…
More Stories
ai-tools
May 19Multi-axis Analysis of Image Manipulation Localization
ai-tools
May 19Long-term Power Grid Planning via Answer Set Programming
ai-tools
May 19HaorFloodAlert: Deseasonalized ML Ensemble for 72-Hour Flood Prediction in Bangladesh Haor Wetlands
ai-tools
May 19Atoms of Thought: Universal EEG Representation Learning with Microstates
ai-tools
May 19A Methodology for Selecting and Composing Runtime Architecture Patterns for Production LLM Agents
ai-tools
May 14VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Prediction
ai-tools
May 14RefDecoder: Enhancing Visual Generation with Conditional Video Decoding
ai-tools
May 14FutureSim: Replaying World Events to Evaluate Adaptive Agents
ai-tools
May 14EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation
ai-tools
May 14ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both
ai-tools
May 14VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Prediction
ai-tools
May 14RefDecoder: Enhancing Visual Generation with Conditional Video Decoding
ai-tools
May 14FutureSim: Replaying World Events to Evaluate Adaptive Agents
ai-tools
May 14EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation
ai-tools
May 14ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both
ai-tools
May 12Task-Adaptive Embedding Refinement via Test-time LLM Guidance
ai-tools
May 12Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation
ai-tools
May 12Learning, Fast and Slow: Towards LLMs That Adapt Continually
ai-tools
May 12Elastic Attention Cores for Scalable Vision Transformers
ai-tools
May 12AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward
ai-tools
May 12Task-Adaptive Embedding Refinement via Test-time LLM Guidance
ai-tools
May 12Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation
ai-tools
May 12Learning, Fast and Slow: Towards LLMs That Adapt Continually
ai-tools
May 12Elastic Attention Cores for Scalable Vision Transformers
ai-tools
May 12AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward
news
May 11Variational Inference for Lévy Process-Driven SDEs via Neural Tilting
news
May 11ELF: Embedded Language Flows
news
May 11DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices
news
May 11Variational Inference for Lévy Process-Driven SDEs via Neural Tilting
news
May 11ELF: Embedded Language Flows
news
May 11DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices
news
May 7Why Global LLM Leaderboards Are Misleading: Small Portfolios for Heterogeneous Supervised ML
news
May 7Verifier-Backed Hard Problem Generation for Mathematical Reasoning
news
May 7UniPool: A Globally Shared Expert Pool for Mixture-of-Experts
news
May 7BAMI: Training-Free Bias Mitigation in GUI Grounding
news
May 7ActCam: Zero-Shot Joint Camera and 3D Motion Control for Video Generation
news
May 7Why Global LLM Leaderboards Are Misleading: Small Portfolios for Heterogeneous Supervised ML
news
May 7Verifier-Backed Hard Problem Generation for Mathematical Reasoning
news
May 7UniPool: A Globally Shared Expert Pool for Mixture-of-Experts
news
May 7BAMI: Training-Free Bias Mitigation in GUI Grounding
news
May 7ActCam: Zero-Shot Joint Camera and 3D Motion Control for Video Generation
news
May 6Taming Outlier Tokens in Diffusion Transformers
news
May 6Sharp Capacity Thresholds in Linear Associative Memory: From Winner-Take-All to Listwise Retrieval
news
May 6LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents
news
May 6Grokability in five inequalities
news
May 6Almost-Orthogonality in Lp Spaces: A Case Study with Grok
news
May 6Taming Outlier Tokens in Diffusion Transformers
news
May 6Sharp Capacity Thresholds in Linear Associative Memory: From Winner-Take-All to Listwise Retrieval
news
May 6LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents
news
May 6Grokability in five inequalities
news
May 6Almost-Orthogonality in Lp Spaces: A Case Study with Grok
news
May 5Safety and accuracy follow different scaling laws in clinical large language models
news
May 5Redefining AI Red Teaming in the Agentic Era: From Weeks to Hours
news
May 5OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories
news
May 5Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures
news
May 5A Closed-Form Adaptive-Landmark Kernel for Certified Point-Cloud and Graph Classification
news
May 5Safety and accuracy follow different scaling laws in clinical large language models
news
May 5Redefining AI Red Teaming in the Agentic Era: From Weeks to Hours
news
May 5OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories
news
May 5Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures
news
May 5A Closed-Form Adaptive-Landmark Kernel for Certified Point-Cloud and Graph Classification
news
May 4Unsupervised Machine Learning for Detecting Structural Anomalies in European Regional Statistics
news
May 4Standing on the Shoulders of Giants: Stabilized Knowledge Distillation for Cross--Language Code Clone Detection
news
May 4SpecKV: Adaptive Speculative Decoding with Compression-Aware Gamma Selection
news
May 4Multi-fidelity surrogates for mechanics of composites: from co-kriging to multi-fidelity neural networks
news
May 4Enhancing RL Generalizability in Robotics through SHAP Analysis of Algorithms and Hyperparameters
news
May 4Unsupervised Machine Learning for Detecting Structural Anomalies in European Regional Statistics
news
May 4Standing on the Shoulders of Giants: Stabilized Knowledge Distillation for Cross--Language Code Clone Detection
news
May 4SpecKV: Adaptive Speculative Decoding with Compression-Aware Gamma Selection
news
May 4Multi-fidelity surrogates for mechanics of composites: from co-kriging to multi-fidelity neural networks
news
May 4Enhancing RL Generalizability in Robotics through SHAP Analysis of Algorithms and Hyperparameters
news
Apr 30Synthetic Computers at Scale for Long-Horizon Productivity Simulation
news
Apr 30LLM as Clinical Graph Structure Refiner: Enhancing Representation Learning in EEG Seizure Diagnosis
news
Apr 30Exploration Hacking: Can LLMs Learn to Resist RL Training?
news
Apr 30Computing Equilibrium beyond Unilateral Deviation
news
Apr 30An adaptive wavelet-based PINN for problems with localized high-magnitude source
news
Apr 30Synthetic Computers at Scale for Long-Horizon Productivity Simulation
news
Apr 30LLM as Clinical Graph Structure Refiner: Enhancing Representation Learning in EEG Seizure Diagnosis
news
Apr 30Exploration Hacking: Can LLMs Learn to Resist RL Training?
news
Apr 30Computing Equilibrium beyond Unilateral Deviation
news
Apr 30An adaptive wavelet-based PINN for problems with localized high-magnitude source
news
Apr 29Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models
news
Apr 29On the Learning Curves of Revenue Maximization
news
Apr 29Learning Over-Relaxation Policies for ADMM with Convergence Guarantees
news
Apr 29Hyper Input Convex Neural Networks for Shape Constrained Learning and Optimal Transport
news
Apr 29A Note on How to Remove the $\ln\ln T$ Term from the Squint Bound
news
Apr 29Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models
news
Apr 29On the Learning Curves of Revenue Maximization
news
Apr 29Learning Over-Relaxation Policies for ADMM with Convergence Guarantees
news
Apr 29Hyper Input Convex Neural Networks for Shape Constrained Learning and Optimal Transport
news
Apr 29A Note on How to Remove the $\ln\ln T$ Term from the Squint Bound
news
Apr 28Toward a Functional Geometric Algebra for Natural Language Semantics
news
Apr 28Teacher Forcing as Generalized Bayes: Optimization Geometry Mismatch in Switching Surrogates for Chaotic Dynamics
news
Apr 28Recursive Multi-Agent Systems
news
Apr 28How Fast Should a Model Commit to Supervision? Training Reasoning Models on the Tsallis Loss Continuum
news
Apr 28Carbon-Taxed Transformers: A Green Compression Pipeline for Overgrown Language Models
news
Apr 28Toward a Functional Geometric Algebra for Natural Language Semantics
news
Apr 28Teacher Forcing as Generalized Bayes: Optimization Geometry Mismatch in Switching Surrogates for Chaotic Dynamics
news
Apr 28Recursive Multi-Agent Systems
news
Apr 28How Fast Should a Model Commit to Supervision? Training Reasoning Models on the Tsallis Loss Continuum
news
Apr 28Carbon-Taxed Transformers: A Green Compression Pipeline for Overgrown Language Models
news
Apr 27The Optimal Sample Complexity of Multiclass and List Learning
news
Apr 27SpecRLBench: A Benchmark for Generalization in Specification-Guided Reinforcement Learning
news
Apr 27Personalized Worked Example Generation from Student Code Submissions using Pattern-based Knowledge Components
news
Apr 27Learning to Think from Multiple Thinkers
news
Apr 27Conflict-Aware Harmonized Rotational Gradient for Multiscale Kinetic Regimes
news
Apr 27The Optimal Sample Complexity of Multiclass and List Learning
news
Apr 27SpecRLBench: A Benchmark for Generalization in Specification-Guided Reinforcement Learning
news
Apr 27Personalized Worked Example Generation from Student Code Submissions using Pattern-based Knowledge Components
news
Apr 27Learning to Think from Multiple Thinkers
news
Apr 27Conflict-Aware Harmonized Rotational Gradient for Multiscale Kinetic Regimes
news
Apr 23When Prompts Override Vision: Prompt-Induced Hallucinations in LVLMs
news
Apr 23The Sample Complexity of Multicalibration
news
Apr 23Temporal Taskification in Streaming Continual Learning: A Source of Evaluation Instability
news
Apr 23Seeing Fast and Slow: Learning the Flow of Time in Videos
news
Apr 23Fine-Tuning Regimes Define Distinct Continual Learning Problems
news
Apr 23When Prompts Override Vision: Prompt-Induced Hallucinations in LVLMs
news
Apr 23The Sample Complexity of Multicalibration
news
Apr 23Temporal Taskification in Streaming Continual Learning: A Source of Evaluation Instability
news
Apr 23Seeing Fast and Slow: Learning the Flow of Time in Videos
news
Apr 23Fine-Tuning Regimes Define Distinct Continual Learning Problems
news
Apr 22SpeechParaling-Bench: A Comprehensive Benchmark for Paralinguistic-Aware Speech Generation
news
Apr 22Global Offshore Wind Infrastructure: Deployment and Operational Dynamics from Dense Sentinel-1 Time Series
news
Apr 22FedSIR: Spectral Client Identification and Relabeling for Federated Learning with Noisy Labels
news
Apr 22Closing the Domain Gap in Biomedical Imaging by In-Context Control Samples
news
Apr 22AVISE: Framework for Evaluating the Security of AI Systems
news
Apr 22SpeechParaling-Bench: A Comprehensive Benchmark for Paralinguistic-Aware Speech Generation
news
Apr 22Global Offshore Wind Infrastructure: Deployment and Operational Dynamics from Dense Sentinel-1 Time Series
news
Apr 22FedSIR: Spectral Client Identification and Relabeling for Federated Learning with Noisy Labels
news
Apr 22Closing the Domain Gap in Biomedical Imaging by In-Context Control Samples
news
Apr 22AVISE: Framework for Evaluating the Security of AI Systems
news
Apr 21UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling
news
Apr 21Safe Continual Reinforcement Learning in Non-stationary Environments
news
Apr 21Phase Transitions in the Fluctuations of Functionals of Random Neural Networks
news
Apr 21Generalization at the Edge of Stability
news
Apr 21FASTER: Value-Guided Sampling for Fast RL
news
Apr 21UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling
news
Apr 21Safe Continual Reinforcement Learning in Non-stationary Environments
news
Apr 21Phase Transitions in the Fluctuations of Functionals of Random Neural Networks
news
Apr 21Generalization at the Edge of Stability
news
Apr 21FASTER: Value-Guided Sampling for Fast RL
news
Apr 20When Can LLMs Learn to Reason with Weak Supervision?
news
Apr 20Sessa: Selective State Space Attention
news
Apr 20MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval
news
Apr 20Bounded Ratio Reinforcement Learning
news
Apr 20Agentic Forecasting using Sequential Bayesian Updating of Linguistic Beliefs
news
Apr 20When Can LLMs Learn to Reason with Weak Supervision?
news
Apr 20Sessa: Selective State Space Attention
news
Apr 20MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval
news
Apr 20Bounded Ratio Reinforcement Learning
news
Apr 20Agentic Forecasting using Sequential Bayesian Updating of Linguistic Beliefs
news
Apr 16MM-WebAgent: A Hierarchical Multimodal Web Agent for Webpage Generation
news
Apr 16How Do LLMs and VLMs Understand Viewpoint Rotation Without Vision? An Interpretability Study
news
Apr 16Generalization in LLM Problem Solving: The Case of the Shortest Path
news
Apr 16Diagnosing LLM Judge Reliability: Conformal Prediction Sets and Transitivity Violations
news
Apr 16Benchmarking Optimizers for MLPs in Tabular Deep Learning
news
Apr 16MM-WebAgent: A Hierarchical Multimodal Web Agent for Webpage Generation
news
Apr 16How Do LLMs and VLMs Understand Viewpoint Rotation Without Vision? An Interpretability Study
news
Apr 16Generalization in LLM Problem Solving: The Case of the Shortest Path
news
Apr 16Diagnosing LLM Judge Reliability: Conformal Prediction Sets and Transitivity Violations
news
Apr 16Benchmarking Optimizers for MLPs in Tabular Deep Learning
news
Apr 15Rhetorical Questions in LLM Representations: A Linear Probing Study
news
Apr 15LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning
news
Apr 15HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System
news
Apr 15From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space
news
Apr 15From Feelings to Metrics: Understanding and Formalizing How Users Vibe-Test LLMs
news
Apr 15Rhetorical Questions in LLM Representations: A Linear Probing Study
news
Apr 15LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning
news
Apr 15HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System
news
Apr 15From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space
news
Apr 15From Feelings to Metrics: Understanding and Formalizing How Users Vibe-Test LLMs
news
Apr 14Visual Preference Optimization with Rubric Rewards
news
Apr 14Representation geometry shapes task performance in vision-language modeling for CT enterography
news
Apr 14PAL: Personal Adaptive Learner
news
Apr 14Classical and Quantum Speedups for Non-Convex Optimization via Energy Conserving Descent
news
Apr 14CLAD: Efficient Log Anomaly Detection Directly on Compressed Representations
news
Apr 14Visual Preference Optimization with Rubric Rewards
news
Apr 14Representation geometry shapes task performance in vision-language modeling for CT enterography
news
Apr 14PAL: Personal Adaptive Learner
news
Apr 14Classical and Quantum Speedups for Non-Convex Optimization via Energy Conserving Descent
news
Apr 14CLAD: Efficient Log Anomaly Detection Directly on Compressed Representations
news
Apr 13Solving Physics Olympiad via Reinforcement Learning on Physics Simulators
news
Apr 13Physics-Informed State Space Models for Reliable Solar Irradiance Forecasting in Off-Grid Systems
news
Apr 13Detecting Safety Violations Across Many Agent Traces
news
Apr 13C-ReD: A Comprehensive Chinese Benchmark for AI-Generated Text Detection Derived from Real-World Prompts
news
Apr 13Budget-Aware Uncertainty for Radiotherapy Segmentation QA Using nnU-Net
news
Apr 13Solving Physics Olympiad via Reinforcement Learning on Physics Simulators
news
Apr 13Physics-Informed State Space Models for Reliable Solar Irradiance Forecasting in Off-Grid Systems
news
Apr 13Detecting Safety Violations Across Many Agent Traces
news
Apr 13C-ReD: A Comprehensive Chinese Benchmark for AI-Generated Text Detection Derived from Real-World Prompts
news
Apr 13Budget-Aware Uncertainty for Radiotherapy Segmentation QA Using nnU-Net
news
Apr 2Steerable Visual Representations
news
Apr 2Grounded Token Initialization for New Vocabulary in LMs for Generative Recommendation
news
Apr 2Beyond the Assistant Turn: User Turn Generation as a Probe of Interaction Awareness in Language Models
news
Apr 2Batched Contextual Reinforcement: A Task-Scaling Law for Efficient Reasoning
news
Apr 2ActionParty: Multi-Subject Action Binding in Generative Video Games
news
Apr 2Steerable Visual Representations
news
Apr 2Grounded Token Initialization for New Vocabulary in LMs for Generative Recommendation
news
Apr 2Beyond the Assistant Turn: User Turn Generation as a Probe of Interaction Awareness in Language Models
news
Apr 2Batched Contextual Reinforcement: A Task-Scaling Law for Efficient Reasoning
news
Apr 2ActionParty: Multi-Subject Action Binding in Generative Video Games
news
Apr 1The Recipe Matters More Than the Kitchen:Mathematical Foundations of the AI Weather Prediction Pipeline
news
Apr 1$\texttt{YC-Bench}$: Benchmarking AI Agents for Long-Term Planning and Consistent Execution
news
Apr 1Multimodal Analysis of State-Funded News Coverage of the Israel-Hamas War on YouTube Shorts
news
Apr 1LAtent Phase Inference from Short time sequences using SHallow REcurrent Decoders (LAPIS-SHRED)
news
Apr 1HippoCamp: Benchmarking Contextual Agents on Personal Computers
news
Apr 1Focal plane wavefront control with model-based reinforcement learning
news
Apr 1Dual Optimal: Make Your LLM Peer-like with Dignity
news
Apr 1Do Phone-Use Agents Respect Your Privacy?
news
Apr 1CliffSearch: Structured Agentic Co-Evolution over Theory and Code for Scientific Algorithm Discovery
news
Apr 1Bridging Structured Knowledge and Data: A Unified Framework with Finance Applications
news
Apr 1The Recipe Matters More Than the Kitchen:Mathematical Foundations of the AI Weather Prediction Pipeline
news
Apr 1$\texttt{YC-Bench}$: Benchmarking AI Agents for Long-Term Planning and Consistent Execution
news
Apr 1Multimodal Analysis of State-Funded News Coverage of the Israel-Hamas War on YouTube Shorts
news
Apr 1LAtent Phase Inference from Short time sequences using SHallow REcurrent Decoders (LAPIS-SHRED)
news
Apr 1HippoCamp: Benchmarking Contextual Agents on Personal Computers
news
Apr 1Focal plane wavefront control with model-based reinforcement learning
news
Apr 1Dual Optimal: Make Your LLM Peer-like with Dignity
news
Apr 1Do Phone-Use Agents Respect Your Privacy?
news
Apr 1CliffSearch: Structured Agentic Co-Evolution over Theory and Code for Scientific Algorithm Discovery
news
Apr 1Bridging Structured Knowledge and Data: A Unified Framework with Finance Applications
news
Mar 31Tucker Attention: A generalization of approximate attention mechanisms
news
Mar 31The Triadic Cognitive Architecture: Bounding Autonomous Action via Spatio-Temporal and Epistemic Friction
news
Mar 31Reward-Based Online LLM Routing via NeuralUCB
news
Mar 31Automatic Identification of Parallelizable Loops Using Transformer-Based Source Code Representations
news
Mar 31Aligned, Orthogonal or In-conflict: When can we safely optimize Chain-of-Thought?
news
Mar 31Tucker Attention: A generalization of approximate attention mechanisms
news
Mar 31The Triadic Cognitive Architecture: Bounding Autonomous Action via Spatio-Temporal and Epistemic Friction
news
Mar 31Reward-Based Online LLM Routing via NeuralUCB
news
Mar 31Automatic Identification of Parallelizable Loops Using Transformer-Based Source Code Representations
news
Mar 31Aligned, Orthogonal or In-conflict: When can we safely optimize Chain-of-Thought?
news
Mar 30Temporal Credit Is Free
news
Mar 30Stop Probing, Start Coding: Why Linear Probes and Sparse Autoencoders Fail at Compositional Generalisation
news
Mar 30Rethinking Language Model Scaling under Transferable Hypersphere Optimization
news
Mar 30On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers
news
Mar 30Geometry-aware similarity metrics for neural representations on Riemannian and statistical manifolds
news
Mar 30Temporal Credit Is Free
news
Mar 30Stop Probing, Start Coding: Why Linear Probes and Sparse Autoencoders Fail at Compositional Generalisation
news
Mar 30Rethinking Language Model Scaling under Transferable Hypersphere Optimization
news
Mar 30On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers
news
Mar 30Geometry-aware similarity metrics for neural representations on Riemannian and statistical manifolds
news
Mar 26Vega: Learning to Drive with Natural Language Instructions
news
Mar 26Training the Knowledge Base through Evidence Distillation and Write-Back Enrichment
news
Mar 26PixelSmile: Toward Fine-Grained Facial Expression Editing
news
Mar 26PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference
news
Mar 26Drive My Way: Preference Alignment of Vision-Language-Action Model for Personalized Driving
news
Mar 26Vega: Learning to Drive with Natural Language Instructions
news
Mar 26Training the Knowledge Base through Evidence Distillation and Write-Back Enrichment
news
Mar 26PixelSmile: Toward Fine-Grained Facial Expression Editing
news
Mar 26PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference
news
Mar 26Drive My Way: Preference Alignment of Vision-Language-Action Model for Personalized Driving
news
Mar 25The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
news
Mar 25Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
news
Mar 25Polynomial Speedup in Diffusion Models with the Multilevel Euler-Maruyama Method
news
Mar 25EndoVGGT: GNN-Enhanced Depth Estimation for Surgical 3D Reconstruction
news
Mar 25DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Driving
news
Mar 25The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
news
Mar 25Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
news
Mar 25Polynomial Speedup in Diffusion Models with the Multilevel Euler-Maruyama Method
news
Mar 25EndoVGGT: GNN-Enhanced Depth Estimation for Surgical 3D Reconstruction
news
Mar 25DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Driving
news
Mar 24VISion On Request: Enhanced VLLM efficiency with sparse, dynamically selected, vision-language interactions
news
Mar 24ReqFusion: A Multi-Provider Framework for Automated PEGS Analysis Across Software Domains
news
Mar 24MedObvious: Exposing the Medical Moravec's Paradox in VLMs via Clinical Triage
news
Mar 24Failure of contextual invariance in gender inference with large language models
news
Mar 24Estimating Flow Velocity and Vehicle Angle-of-Attack from Non-invasive Piezoelectric Structural Measurements Using Deep Learning
news
Mar 24VISion On Request: Enhanced VLLM efficiency with sparse, dynamically selected, vision-language interactions
news
Mar 24ReqFusion: A Multi-Provider Framework for Automated PEGS Analysis Across Software Domains
news
Mar 24MedObvious: Exposing the Medical Moravec's Paradox in VLMs via Clinical Triage
news
Mar 24Failure of contextual invariance in gender inference with large language models
news
Mar 24Estimating Flow Velocity and Vehicle Angle-of-Attack from Non-invasive Piezoelectric Structural Measurements Using Deep Learning
news
Mar 23WorldCache: Content-Aware Caching for Accelerated Video World Models
news
Mar 23UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generation
news
Mar 23ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model
news
Mar 23End-to-End Training for Unified Tokenization and Latent Denoising
news
Mar 233D-Layout-R1: Structured Reasoning for Language-Instructed Spatial Editing
news
Mar 23WorldCache: Content-Aware Caching for Accelerated Video World Models
news
Mar 23UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generation
news
Mar 23ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model
news
Mar 23End-to-End Training for Unified Tokenization and Latent Denoising
news
Mar 233D-Layout-R1: Structured Reasoning for Language-Instructed Spatial Editing
news
Mar 19Spectrally-Guided Diffusion Noise Schedules
news
Mar 19Online Learning and Equilibrium Computation with Ranking Feedback
news
Mar 19NavTrust: Benchmarking Trustworthiness for Embodied Navigation
news
Mar 19FinTradeBench: A Financial Reasoning Benchmark for LLMs
news
Mar 19F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World
news
Mar 19Spectrally-Guided Diffusion Noise Schedules
news
Mar 19Online Learning and Equilibrium Computation with Ranking Feedback
news
Mar 19NavTrust: Benchmarking Trustworthiness for Embodied Navigation
news
Mar 19FinTradeBench: A Financial Reasoning Benchmark for LLMs
news
Mar 19F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World
news
Mar 18Unified Spatio-Temporal Token Scoring for Efficient Video VLMs
news
Mar 18Toward Scalable Automated Repository-Level Datasets for Software Vulnerability Detection
news
Mar 18LoST: Level of Semantics Tokenization for 3D Shapes
news
Mar 18Loc3R-VLM: Language-based Localization and 3D Reasoning with Vision-Language Models
news
Mar 18AgentFactory: A Self-Evolving Framework Through Executable Subagent Accumulation and Reuse
news
Mar 18Unified Spatio-Temporal Token Scoring for Efficient Video VLMs
news
Mar 18Toward Scalable Automated Repository-Level Datasets for Software Vulnerability Detection
news
Mar 18LoST: Level of Semantics Tokenization for 3D Shapes
news
Mar 18Loc3R-VLM: Language-based Localization and 3D Reasoning with Vision-Language Models
news
Mar 18AgentFactory: A Self-Evolving Framework Through Executable Subagent Accumulation and Reuse
news
Mar 17SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation
news
Mar 17MessyKitchens: Contact-rich object-level 3D scene reconstruction
news
Mar 17ManiTwin: Scaling Data-Generation-Ready Digital Object Dataset to 100K
news
Mar 17Efficient Reasoning on the Edge
news
Mar 17Demystifing Video Reasoning
news
Mar 17SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation
news
Mar 17MessyKitchens: Contact-rich object-level 3D scene reconstruction
news
Mar 17ManiTwin: Scaling Data-Generation-Ready Digital Object Dataset to 100K
news
Mar 17Efficient Reasoning on the Edge
news
Mar 17Demystifing Video Reasoning
news
Mar 12The Latent Color Subspace: Emergent Order in High-Dimensional Chaos
news
Mar 12Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training
news
Mar 12SciMDR: Benchmarking and Advancing Scientific Multimodal Document Reasoning
news
Mar 12Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models
news
Mar 12Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Training
news
Mar 12The Latent Color Subspace: Emergent Order in High-Dimensional Chaos
news
Mar 12Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training
news
Mar 12SciMDR: Benchmarking and Advancing Scientific Multimodal Document Reasoning
news
Mar 12Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models
news
Mar 12Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Training
news
Mar 11V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation
news
Mar 11Neural Field Thermal Tomography: A Differentiable Physics Framework for Non-Destructive Evaluation
news
Mar 11LiTo: Surface Light Field Tokenization
news
Mar 11Instruction set for the representation of graphs
news
Mar 11COMIC: Agentic Sketch Comedy Generation
news
Mar 11V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation
news
Mar 11Neural Field Thermal Tomography: A Differentiable Physics Framework for Non-Destructive Evaluation
news
Mar 11LiTo: Surface Light Field Tokenization
news
Mar 11Instruction set for the representation of graphs
news
Mar 11COMIC: Agentic Sketch Comedy Generation
news
Mar 10Understanding the Use of a Large Language Model-Powered Guide to Make Virtual Reality Accessible for Blind and Low Vision People
news
Mar 10Task Aware Modulation Using Representation Learning for Upsaling of Terrestrial Carbon Fluxes
news
Mar 10From Data Statistics to Feature Geometry: How Correlations Shape Superposition
news
Mar 10Emotional Modulation in Swarm Decision Dynamics
news
Mar 10BEACON: Language-Conditioned Navigation Affordance Prediction under Occlusion
news
Mar 10Understanding the Use of a Large Language Model-Powered Guide to Make Virtual Reality Accessible for Blind and Low Vision People
news
Mar 10Task Aware Modulation Using Representation Learning for Upsaling of Terrestrial Carbon Fluxes
news
Mar 10From Data Statistics to Feature Geometry: How Correlations Shape Superposition
news
Mar 10Emotional Modulation in Swarm Decision Dynamics
news
Mar 10BEACON: Language-Conditioned Navigation Affordance Prediction under Occlusion
news
Mar 9Scale Space Diffusion
news
Mar 9Impermanent: A Live Benchmark for Temporal Generalization in Time Series Forecasting
news
Mar 9Evaluating Financial Intelligence in Large Language Models: Benchmarking SuperInvesting AI with LLM Engines
news
Mar 9Agentic Critical Training
news
Mar 9A Multi-Objective Optimization Approach for Sustainable AI-Driven Entrepreneurship in Resilient Economies
news
Mar 9Scale Space Diffusion
news
Mar 9Impermanent: A Live Benchmark for Temporal Generalization in Time Series Forecasting
news
Mar 9Evaluating Financial Intelligence in Large Language Models: Benchmarking SuperInvesting AI with LLM Engines
news
Mar 9Agentic Critical Training
news
Mar 9A Multi-Objective Optimization Approach for Sustainable AI-Driven Entrepreneurship in Resilient Economies
news
Mar 6SUREON: A Benchmark and Vision-Language-Model for Surgical Reasoning
news
Mar 6SCOPE: Scene-Contextualized Incremental Few-Shot 3D Segmentation
news
Mar 6Fly360: Omnidirectional Obstacle Avoidance within Drone View
news
Mar 6BEVLM: Distilling Semantic Knowledge from LLMs into Bird's-Eye View Representations
news
Mar 6A recipe for scalable attention-based MLIPs: unlocking long-range accuracy with all-to-all node attention
news
Mar 6SUREON: A Benchmark and Vision-Language-Model for Surgical Reasoning
news
Mar 6SCOPE: Scene-Contextualized Incremental Few-Shot 3D Segmentation
news
Mar 6Fly360: Omnidirectional Obstacle Avoidance within Drone View
news
Mar 6BEVLM: Distilling Semantic Knowledge from LLMs into Bird's-Eye View Representations
news
Mar 6A recipe for scalable attention-based MLIPs: unlocking long-range accuracy with all-to-all node attention
news
Mar 5The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks
news
Mar 5RoboPocket: Improve Robot Policies Instantly with Your Phone
news
Mar 5POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation
news
Mar 5Cheap Thrills: Effective Amortized Optimization Using Inexpensive Labels
news
Mar 5Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation
news
Mar 5The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks
news
Mar 5RoboPocket: Improve Robot Policies Instantly with Your Phone
news
Mar 5POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation
news
Mar 5Cheap Thrills: Effective Amortized Optimization Using Inexpensive Labels
news
Mar 5Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation
research
Nov 17Voltage-Based Unsupervised Learning Framework for Bridge Damage Detection in Simultaneous Energy Harvesting and Sensing Systems
research
Nov 17UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity
research
Nov 17Ultrafast propagation of magnon-polaritons
research
Nov 17Tuning for Two Adversaries: Enhancing the Robustness Against Transfer and Query-Based Attacks using Hyperparameter Tuning
research
Nov 17Toward Conversational Hungarian Speech Recognition: Introducing the BEA-Large and BEA-Dialogue Datasets
research
Nov 17The Merkle Mountain Belt
research
Nov 17Sub-Solar Mass Intermediate Mass Ratio Inspirals: Waveform Systematics and Detection Prospects with Gravitational Waves
research
Nov 17Statistical and economic evaluation of forecasts in electricity markets: beyond RMSE and MAE
research
Nov 17ST-ProC: A Graph-Prototypical Framework for Robust Semi-Supervised Travel Mode Identification
research
Nov 17Scaling Spatial Intelligence with Multimodal Foundation Models
research
Nov 17Quantum Machine Learning via Contrastive Training
research
Nov 17Protein Secondary Structure Prediction Using 3D Graphs and Relation-Aware Message Passing Transformers
research
Nov 17Person-AI Bidirectional Fit - A Proof-Of-Concept Case Study Of Augmented Human-Ai Symbiosis In Management Decision-Making Process
research
Nov 17P1: Mastering Physics Olympiads with Reinforcement Learning
research
Nov 17Market-Dependent Communication in Multi-Agent Alpha Generation
research
Nov 17Making Evidence Actionable in Adaptive Learning Closing the Diagnostic Pedagogical Loop
research
Nov 17LinkXplore: A Framework for Affordable High-Quality Blockchain Data
research
Nov 17Learning stochasticity: a nonparametric framework for intrinsic noise estimation
research
Nov 17Infinite-Horizon Optimal Control of Jump-Diffusion Models for Pollution-Dependent Disasters
research
Nov 17In-Situ Growth of Halide Perovskite Single Crystals and Thin Films on Optical Fiber End Facets
research
Nov 17Generalist Foundation Models Are Not Clinical Enough for Hospital Operations
research
Nov 17From Power to Precision: Learning Fine-grained Dexterity for Multi-fingered Robotic Hands
research
Nov 17From Black Box to Insight: Explainable AI for Extreme Event Preparedness
research
Nov 17Fairness-Aware Graph Representation Learning with Limited Demographic Information
research
Nov 17Efficient Reconstruction of Matched-Filter SNR Time Series from Nearby Templates
research
Nov 17CBDC Stress Test in a Dual-Currency Setting
research
Nov 17Block Structure Preserving Model Order Reduction for A-EFIE Integral Equation Method
research
Nov 17Basis Immunity: Isotropy as a Regularizer for Uncertainty
research
Nov 17Automated Construction of Medical Indicator Knowledge Graphs Using Retrieval Augmented Large Language Models
research
Nov 17Artificial Intelligence-driven Intelligent Wearable Systems: A full-stack Integration from Material Design to Personalized Interaction
research
Nov 17Architectural Approaches to Fault-Tolerant Distributed Quantum Computing and Their Entanglement Overheads
research
Nov 17Alpha Divergence Losses for Biometric Verification
research
Nov 17A Lightweight 3D Anomaly Detection Method with Rotationally Invariant Features
research
Nov 17Voltage-Based Unsupervised Learning Framework for Bridge Damage Detection in Simultaneous Energy Harvesting and Sensing Systems
research
Nov 17UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity
research
Nov 17Ultrafast propagation of magnon-polaritons
research
Nov 17Tuning for Two Adversaries: Enhancing the Robustness Against Transfer and Query-Based Attacks using Hyperparameter Tuning
research
Nov 17Toward Conversational Hungarian Speech Recognition: Introducing the BEA-Large and BEA-Dialogue Datasets
research
Nov 17The Merkle Mountain Belt
research
Nov 17Sub-Solar Mass Intermediate Mass Ratio Inspirals: Waveform Systematics and Detection Prospects with Gravitational Waves
research
Nov 17Statistical and economic evaluation of forecasts in electricity markets: beyond RMSE and MAE
research
Nov 17ST-ProC: A Graph-Prototypical Framework for Robust Semi-Supervised Travel Mode Identification
research
Nov 17Scaling Spatial Intelligence with Multimodal Foundation Models
research
Nov 17Quantum Machine Learning via Contrastive Training
research
Nov 17Protein Secondary Structure Prediction Using 3D Graphs and Relation-Aware Message Passing Transformers
research
Nov 17Person-AI Bidirectional Fit - A Proof-Of-Concept Case Study Of Augmented Human-Ai Symbiosis In Management Decision-Making Process
research
Nov 17P1: Mastering Physics Olympiads with Reinforcement Learning
research
Nov 17Market-Dependent Communication in Multi-Agent Alpha Generation
research
Nov 17Making Evidence Actionable in Adaptive Learning Closing the Diagnostic Pedagogical Loop
research
Nov 17LinkXplore: A Framework for Affordable High-Quality Blockchain Data
research
Nov 17Learning stochasticity: a nonparametric framework for intrinsic noise estimation
research
Nov 17Infinite-Horizon Optimal Control of Jump-Diffusion Models for Pollution-Dependent Disasters
research
Nov 17In-Situ Growth of Halide Perovskite Single Crystals and Thin Films on Optical Fiber End Facets
research
Nov 17Generalist Foundation Models Are Not Clinical Enough for Hospital Operations
research
Nov 17From Power to Precision: Learning Fine-grained Dexterity for Multi-fingered Robotic Hands
research
Nov 17From Black Box to Insight: Explainable AI for Extreme Event Preparedness
research
Nov 17Fairness-Aware Graph Representation Learning with Limited Demographic Information
research
Nov 17Efficient Reconstruction of Matched-Filter SNR Time Series from Nearby Templates
research
Nov 17CBDC Stress Test in a Dual-Currency Setting
research
Nov 17Block Structure Preserving Model Order Reduction for A-EFIE Integral Equation Method
research
Nov 17Basis Immunity: Isotropy as a Regularizer for Uncertainty
research
Nov 17Automated Construction of Medical Indicator Knowledge Graphs Using Retrieval Augmented Large Language Models
research
Nov 17Artificial Intelligence-driven Intelligent Wearable Systems: A full-stack Integration from Material Design to Personalized Interaction
research
Nov 17Architectural Approaches to Fault-Tolerant Distributed Quantum Computing and Their Entanglement Overheads
research
Nov 17Alpha Divergence Losses for Biometric Verification
research
Nov 17A Lightweight 3D Anomaly Detection Method with Rotationally Invariant Features
research
Nov 16Maximizing the efficiency of human feedback in AI alignment: a comparative analysis
research
Nov 16Maximizing the efficiency of human feedback in AI alignment: a comparative analysis
research
Nov 15Sangam: Chiplet-Based DRAM-PIM Accelerator with CXL Integration for LLM Inferencing
research
Nov 15Open Banking Foundational Model: Learning Language Representations from Few Financial Transactions
research
Nov 15High-Performance N-Queens Solver on GPU: Iterative DFS with Zero Bank Conflicts
research
Nov 15Determinants of financial and digital inclusion in West and Central Africa: Evidence from binary models with cross-validation
research
Nov 15Sangam: Chiplet-Based DRAM-PIM Accelerator with CXL Integration for LLM Inferencing
research
Nov 15Open Banking Foundational Model: Learning Language Representations from Few Financial Transactions
research
Nov 15High-Performance N-Queens Solver on GPU: Iterative DFS with Zero Bank Conflicts
research
Nov 15Determinants of financial and digital inclusion in West and Central Africa: Evidence from binary models with cross-validation
research
Nov 4How FinTech affects financial sustainability: Evidence from Chinese commercial banks using a three-stage network DEA-Malmquist model
research
Nov 4How FinTech affects financial sustainability: Evidence from Chinese commercial banks using a three-stage network DEA-Malmquist model
research
Oct 29ScaleCall -- Agentic Tool Calling at Scale for Fintech: Challenges, Methods, and Deployment Insights
research
Oct 29Retrieval Augmented Generation (RAG) for Fintech: Agentic Design and Evaluation
research
Oct 29ScaleCall -- Agentic Tool Calling at Scale for Fintech: Challenges, Methods, and Deployment Insights
research
Oct 29Retrieval Augmented Generation (RAG) for Fintech: Agentic Design and Evaluation
research
Sep 29Fin-Ally: Pioneering the Development of an Advanced, Commonsense-Embedded Conversational AI for Money Matters
research
Sep 29Fin-Ally: Pioneering the Development of an Advanced, Commonsense-Embedded Conversational AI for Money Matters
research
Sep 16Agentic AI for Financial Crime Compliance
research
Sep 16Agentic AI for Financial Crime Compliance
research
Sep 10When FinTech Meets Privacy: Securing Financial LLMs with Differential Private Fine-Tuning
research
Sep 10When FinTech Meets Privacy: Securing Financial LLMs with Differential Private Fine-Tuning
research
Sep 3Distribution-valued Causal Machine Learning: Implications of Credit on Spending Patterns
research
Sep 3Distribution-valued Causal Machine Learning: Implications of Credit on Spending Patterns
research
Aug 24L-XAIDS: A LIME-based eXplainable AI framework for Intrusion Detection Systems
research
Aug 24L-XAIDS: A LIME-based eXplainable AI framework for Intrusion Detection Systems
research
Aug 5Momentum-integrated Multi-task Stock Recommendation with Converge-based Optimization
research
Aug 5Momentum-integrated Multi-task Stock Recommendation with Converge-based Optimization
research
Aug 4An Efficient and Adaptive Next Edit Suggestion Framework with Zero Human Instructions in IDEs
research
Aug 4