전문분석자료 인텔리전스 허브

ConstitutionGPT: An AI-Powered Multilingual Legal Assistance System for Indian Citizens

SCOTUStoday: Sotomayor criticizes Kavanaugh

Final 2 days to save up to $500 on your TechCrunch Disrupt 2026 ticket

AI Copyright Infringement: Navigating the Legal Risks of AI-Generated Content

A Severity-Based Curriculum Learning Strategy for Arabic Medical Text Generation

Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook

LLM-Augmented Knowledge Base Construction For Root Cause Analysis

When Does Context Help? A Systematic Study of Target-Conditional Molecular Property Prediction

The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment

Efficient Quantization of Mixture-of-Experts with Theoretical Generalization Guarantees

Final 2 days to save up to $500 on your TechCrunch Disrupt 2026 ticket

AI Copyright Infringement: Navigating the Legal Risks of AI-Generated Content

Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook

LLM-Augmented Knowledge Base Construction For Root Cause Analysis

When Does Context Help? A Systematic Study of Target-Conditional Molecular Property Prediction

$S^3$: Stratified Scaling Search for Test-Time in Diffusion Language Models

Fine-tuning Whisper for Pashto ASR: strategies and scale

Spectral Edge Dynamics Reveal Functional Modes of Learning

The Illusion of Stochasticity in LLMs

Weighted Bayesian Conformal Prediction

Improving Clinical Trial Recruitment using Clinical Narratives and Large Language Models

General Explicit Network (GEN): A novel deep learning architecture for solving partial differential equations

Towards the AI Historian: Agentic Information Extraction from Primary Sources

Episode 42: Russia, Imperial Continuities and Histories of International Law - EJIL: The Podcast!

Position: Science of AI Evaluation Requires Item-level Benchmark Data

Improving Model Performance by Adapting the KGE Metric to Account for System Non-Stationarity

More Human, More Efficient: Aligning Annotations with Quantized SLMs

Ontology-Constrained Neural Reasoning in Enterprise Agentic Systems: A Neurosymbolic Architecture for Domain-Grounded AI Agents

As more Americans adopt AI tools, fewer say they can trust the results

Understanding the Challenges in Iterative Generative Optimization with LLMs

Efficient Quantization of Mixture-of-Experts with Theoretical Generalization Guarantees

Weighted Bayesian Conformal Prediction

FLeX: Fourier-based Low-rank EXpansion for multilingual transfer

FMI@SU ToxHabits: Evaluating LLMs Performance on Toxic Habit Extraction in Spanish Clinical Texts

Context-Aware Dialectal Arabic Machine Translation with Interactive Region and Register Selection

The Illusion of Superposition? A Principled Analysis of Latent Thinking in Language Models

Emergent decentralized regulation in a purely synthetic society

SubFLOT: Submodel Extraction for Efficient and Personalized Federated Learning via Optimal Transport

Bi-Lipschitz Autoencoder With Injectivity Guarantee

Stochastic Gradient Descent in the Saddle-to-Saddle Regime of Deep Linear Networks

Legislative history lives on – in secret

LLM-Augmented Knowledge Base Construction For Root Cause Analysis

When Does Context Help? A Systematic Study of Target-Conditional Molecular Property Prediction

TwinLoop: Simulation-in-the-Loop Digital Twins for Online Multi-Agent Reinforcement Learning

SensorPersona: An LLM-Empowered System for Continual Persona Extraction from Longitudinal Mobile Sensor Streams

TelcoAgent-Bench: A Multilingual Benchmark for Telecom AI Agents

FLeX: Fourier-based Low-rank EXpansion for multilingual transfer

State-of-the-Art Arabic Language Modeling with Sparse MoE Fine-Tuning and Chain-of-Thought Distillation

TalkLoRA: Communication-Aware Mixture of Low-Rank Adaptation for Large Language Models

STDec: Spatio-Temporal Stability Guided Decoding for dLLMs

Detecting Neurovascular Instability from Multimodal Physiological Signals Using Wearable-Compatible Edge AI: A Responsible Computational Framework

FastODT: A tree-based framework for efficient continual learning

When Right Meets Wrong: Bilateral Context Conditioning with Reward-Confidence Correction for GRPO

Cross-Domain Uncertainty Quantification for Selective Prediction: A Comprehensive Bound Ablation with Transfer-Informed Betting

Elenchus: Generating Knowledge Bases from Prover-Skeptic Dialogues

Enhancing Consistency of Werewolf AI through Dialogue Summarization and Persona Information

A Comparative Study of Undue Influence and Unfair Conduct in Contract Law Using NLP and Knowledge Graphs: Bridging Common Law and Chinese Legal Systems Through Computational Legal Intelligence

Pessimistic Auxiliary Policy for Offline Reinforcement Learning

Fintech Regulation 2026: Navigating the New Compliance Landscape

Global Trade Realignment: How Geopolitical Shifts Are Reshaping International Commerce

When Does Context Help? A Systematic Study of Target-Conditional Molecular Property Prediction

Quality-preserving Model for Electronics Production Quality Tests Reduction

State-of-the-Art Arabic Language Modeling with Sparse MoE Fine-Tuning and Chain-of-Thought Distillation

Improving Robustness In Sparse Autoencoders via Masked Regularization

Emergent decentralized regulation in a purely synthetic society

GraphWalker: Graph-Guided In-Context Learning for Clinical Reasoning on Electronic Health Records

Beyond Facts: Benchmarking Distributional Reading Comprehension in Large Language Models

RAGEN-2: Reasoning Collapse in Agentic RL

Feedback Adaptation for Retrieval-Augmented Generation

Severity-Aware Weighted Loss for Arabic Medical Text Generation

Conversion therapy and professional speech

AI Copyright Infringement: Navigating the Legal Risks of AI-Generated Content

The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment

Efficient Quantization of Mixture-of-Experts with Theoretical Generalization Guarantees

Towards Accurate and Calibrated Classification: Regularizing Cross-Entropy From A Generative Perspective

Spectral Edge Dynamics Reveal Functional Modes of Learning

Distributed Interpretability and Control for Large Language Models

Drifting Fields are not Conservative

Context-Aware Dialectal Arabic Machine Translation with Interactive Region and Register Selection

Improving Robustness In Sparse Autoencoders via Masked Regularization

AI Copyright Infringement: Navigating the Legal Risks of AI-Generated Content

VLMShield: Efficient and Robust Defense of Vision-Language Models against Malicious Prompts

Supreme Court summarily closes the courthouse doors again

The Higher Education Accommodation Mistake

Your Agent is More Brittle Than You Think: Uncovering Indirect Injection Vulnerabilities in Agentic LLMs

Court allows Steve Bannon to move forward on dismissal of criminal charges against him

FactReview: Evidence-Grounded Reviews with Literature Positioning and Execution-Based Claim Verification

LogicPoison: Logical Attacks on Graph Retrieval-Augmented Generation

I must delete the evidence: AI Agents Explicitly Cover up Fraud and Violent Crime

Large Language Models in the Abuse Detection Pipeline

When Does Context Help? A Systematic Study of Target-Conditional Molecular Property Prediction

$S^3$: Stratified Scaling Search for Test-Time in Diffusion Language Models

Towards Accurate and Calibrated Classification: Regularizing Cross-Entropy From A Generative Perspective

Spectral Edge Dynamics Reveal Functional Modes of Learning

TwinLoop: Simulation-in-the-Loop Digital Twins for Online Multi-Agent Reinforcement Learning

Quality-preserving Model for Electronics Production Quality Tests Reduction

SensorPersona: An LLM-Empowered System for Continual Persona Extraction from Longitudinal Mobile Sensor Streams

FLeX: Fourier-based Low-rank EXpansion for multilingual transfer

AE-ViT: Stable Long-Horizon Parametric Partial Differential Equations Modeling

State-of-the-Art Arabic Language Modeling with Sparse MoE Fine-Tuning and Chain-of-Thought Distillation

Legislative history lives on – in secret

SCOTUStoday: Sotomayor criticizes Kavanaugh

Final 2 days to save up to $500 on your TechCrunch Disrupt 2026 ticket

AI Copyright Infringement: Navigating the Legal Risks of AI-Generated Content

Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook

LLM-Augmented Knowledge Base Construction For Root Cause Analysis

When Does Context Help? A Systematic Study of Target-Conditional Molecular Property Prediction

$S^3$: Stratified Scaling Search for Test-Time in Diffusion Language Models

SHAPE: Stage-aware Hierarchical Advantage via Potential Estimation for LLM Reasoning

The Illusion of Stochasticity in LLMs

SCOTUStoday: Sotomayor criticizes Kavanaugh

A Severity-Based Curriculum Learning Strategy for Arabic Medical Text Generation

Efficient Quantization of Mixture-of-Experts with Theoretical Generalization Guarantees

Spectral Edge Dynamics Reveal Functional Modes of Learning

SHAPE: Stage-aware Hierarchical Advantage via Potential Estimation for LLM Reasoning

The Illusion of Stochasticity in LLMs

Asymptotic-Preserving Neural Networks for Viscoelastic Parameter Identification in Multiscale Blood Flow Modeling

Distributed Interpretability and Control for Large Language Models

Databricks co-founder wins prestigious ACM award, says ‘AGI is here already’

State-of-the-Art Arabic Language Modeling with Sparse MoE Fine-Tuning and Chain-of-Thought Distillation

Legislative history lives on – in secret

Conversion therapy and professional speech

SCOTUStoday: Sotomayor criticizes Kavanaugh

Final 2 days to save up to $500 on your TechCrunch Disrupt 2026 ticket

A Severity-Based Curriculum Learning Strategy for Arabic Medical Text Generation

When Does Context Help? A Systematic Study of Target-Conditional Molecular Property Prediction

The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment

$S^3$: Stratified Scaling Search for Test-Time in Diffusion Language Models

Spectral Edge Dynamics Reveal Functional Modes of Learning

TwinLoop: Simulation-in-the-Loop Digital Twins for Online Multi-Agent Reinforcement Learning

LLM-Augmented Knowledge Base Construction For Root Cause Analysis

When Does Context Help? A Systematic Study of Target-Conditional Molecular Property Prediction

Efficient Quantization of Mixture-of-Experts with Theoretical Generalization Guarantees

Fine-tuning Whisper for Pashto ASR: strategies and scale

Spectral Edge Dynamics Reveal Functional Modes of Learning

Quality-preserving Model for Electronics Production Quality Tests Reduction

Weighted Bayesian Conformal Prediction

Distributed Interpretability and Control for Large Language Models

AE-ViT: Stable Long-Horizon Parametric Partial Differential Equations Modeling

Attention Flows: Tracing LLM Conceptual Engagement via Story Summaries