ICLR | BestHub

DevOps

Apr 9, 2025 · Artificial Intelligence

AI Scientist v2 Generates ICLR Workshop Paper Reviewed and Accepted

An AI‑generated research paper created entirely by Sakana AI’s AI Scientist‑v2 system achieved a 6/7/6 score and passed peer review at an ICLR workshop, demonstrating end‑to‑end hypothesis generation, experiment execution, data analysis, and manuscript writing, while highlighting the system’s capabilities and limitations.

AI ScientistAI-generated researchAgentic Tree Search

0 likes · 8 min read

AI Scientist v2 Generates ICLR Workshop Paper Reviewed and Accepted

JD Tech

Mar 12, 2025 · Artificial Intelligence

From Low‑Resource Large Model Training to Dynamic Margin Selection: A JD Engineer’s Journey

The article recounts a JD retail engineer’s rapid growth through tackling low‑resource large‑model training, developing a margin‑based dynamic data selection method (DynaMS) that earned an ICLR paper, and sharing practical insights on aligning business needs with cutting‑edge AI research.

AI researchICLRLarge Models

0 likes · 11 min read

From Low‑Resource Large Model Training to Dynamic Margin Selection: A JD Engineer’s Journey

JD Retail Technology

Mar 6, 2025 · Artificial Intelligence

Dynamic Margin Selection for Efficient Deep Learning and Low-Resource Large Model Training

Jia Xing’s research introduces Dynamic Margin Selection, a technique that repeatedly refreshes a core set of boundary‑close samples to train large language models efficiently on limited resources, achieving comparable loss to full‑data training, enabling six‑fold model compression, faster inference, and a proposed exponential scaling law for data‑efficient AI.

ICLRLarge Language Modelsdynamic data selection

0 likes · 10 min read

Dynamic Margin Selection for Efficient Deep Learning and Low-Resource Large Model Training

DataFunSummit

Oct 9, 2021 · Artificial Intelligence

Adaptive Universal Generalized PageRank Graph Neural Network (GPR‑GNN): Solving Generality and Over‑Smoothing in Graph Neural Networks

This article presents the Adaptive Universal Generalized PageRank Graph Neural Network (GPR‑GNN), explains the two main limitations of existing GNNs—lack of generality across homophilic and heterophilic graphs and the over‑smoothing problem—and demonstrates through synthetic and real‑world experiments that GPR‑GNN achieves robust node classification while remaining interpretable and parameter‑efficient.

GPR-GNNGraph Neural NetworksICLR

0 likes · 18 min read

Adaptive Universal Generalized PageRank Graph Neural Network (GPR‑GNN): Solving Generality and Over‑Smoothing in Graph Neural Networks