The protocol uses a Teacher-Orchestrator-Student structure to generate evolving problems, with the Orchestrator increasing problem validity from 4.30 to 4.85 and approval rates from 38.14% to 87.14%.
The method corrects posterior probabilities at test time without retraining, maintaining performance on balanced data while fixing recall collapse in imbalanced scenarios.
The method, presented at ICML 2026, generates observation and action models via LLMs to reconfigure the agent-environment interface, outperforming human-designed baselines in locomotion and manipulation tasks.
Sim-GEAR achieves a 91.1% computational speedup and 62.6% memory reduction compared to GEAR by replacing curvature matching with metric matching.
The study reveals how TokenGT models reconstruct graph incidence through node-ID matching to solve tasks like degree calculation and shortest-path distance.
The study elucidates the principle of local structure restoration via attention heads in basic graph tasks such as degree calculation.
LG AI Research has developed 'MCFlow,' a single model capable of performing multiple crystal generation tasks—including composition, structure, and atom generation—and has been accepted to ICML 2026.
LG AI Research has developed MCFlow, an integrated model for inorganic material generation capable of element substitution, which has been accepted to ICML 2026.
LG AI Research has released EXAONE Tabular, a lightweight tabular foundation model pre-trained without real data.
LG AI Research has released 'EXAONE Tabular', a foundation model for tabular data pre-trained exclusively on synthetic data without using any real-world data.
LG AI Research has released an autonomous vision inspection framework that leverages VLM and Agentic AI to automate the entire process from data labeling to deployment.
LG AI Research has unveiled an autonomous vision inspection framework that combines VLM and Agentic AI to eliminate human intervention from labeling to deployment.
LG AI Research announced ReSQL, which utilizes execution errors as learning signals to improve Text-to-SQL performance in lightweight models.
LG AI Research has released ReSQL, which recycles SQL errors from lightweight models for training to outperform GPT-4.
LG AI Research proposed a method that assigns topics at the segment level rather than the document level to resolve distortion issues in existing topic modeling.
LG AI Research proposed the **SBTA** technique, which assigns topics to sentence-level segments instead of documents to resolve topic contamination.
LG AI Research summarized the World Model research trends and EDA application potential from CVPR 2026.
LG AI Research and LG U+ evolved ixi-O into on-device agentic AI by leveraging the EXAONE model.
LG AI Research and LG Uplus leveraged EXAONE to build an on-device agentic AI service that maximizes both security and efficiency.
LG AI Research has unveiled VinQA, a study that generates answers by strategically combining text and visual elements.
LG AI Research has unveiled 'VinQA,' a multimodal document QA study that generates long-form answers by appropriately placing text and visual elements together.
LG AI Research proposed ASER, a continual learning algorithm that minimizes forgetting by evaluating the importance of data.
LG AI Research proposed the ASER algorithm, which learns new data while preserving existing knowledge by leveraging KNN-SV, a data valuation model.
LG AI Research has developed SISE, a new image recognition explanation technology that overcomes the limitations of existing XAI models.
AI Briefing