Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic
• 86
AI & ML interests
Enterprise AI and ML, Foundation Models, Responsible AI
Recent Activity
View all activity
Papers
Evoflux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents
Flash-GMM: A Memory-Efficient Kernel for Scalable Soft Clustering
Articles
Time Series Models
A collection of time series models trained by IBM
Table + Text IR Evaluation
An evaluation suite created for benchmarking of retrieval models on Table+Text retrieval datasets.
AI-Agent-4-Industry-4.0
This category highlights the collective efforts of the AI Automation team in advancing Industry 4.0 applications and exploring innovations beyond it.
REAL-MM-RAG-Bench
REAL-MM-RAG-Bench is a benchmark designed to evaluate multi-modal retrieval models under realistic and challenging conditions.
Materials
Welcome to IBM’s multi-modal foundation model for materials, FM4M, designed to support and advance research in materials science and chemistry.
Enterprise Agents and Benchmarks
Enterprise agent ecosystem featuring AssetOpsBench (industrial) and ITBench (SRE, FinOps, CISO), CUGA to accelerate AI Automation
REAL-MM-RAG-Bench_BEIR
REAL-MM-RAG-Bench is a benchmark designed to evaluate multi-modal retrieval models under realistic and challenging conditions.
Otter-Knowledge
Datasets and models of the Otter-Knowledge project
Granite 3.2 Models (GGUF)
GGUF-formatted versions of IBM Granite 3.2 models. Licensed under the Apache 2.0 license.
Time Series Models
A collection of time series models trained by IBM
Enterprise Agents and Benchmarks
Enterprise agent ecosystem featuring AssetOpsBench (industrial) and ITBench (SRE, FinOps, CISO), CUGA to accelerate AI Automation
Table + Text IR Evaluation
An evaluation suite created for benchmarking of retrieval models on Table+Text retrieval datasets.
REAL-MM-RAG-Bench_BEIR
REAL-MM-RAG-Bench is a benchmark designed to evaluate multi-modal retrieval models under realistic and challenging conditions.
AI-Agent-4-Industry-4.0
This category highlights the collective efforts of the AI Automation team in advancing Industry 4.0 applications and exploring innovations beyond it.
Otter-Knowledge
Datasets and models of the Otter-Knowledge project
REAL-MM-RAG-Bench
REAL-MM-RAG-Bench is a benchmark designed to evaluate multi-modal retrieval models under realistic and challenging conditions.
Granite 3.2 Models (GGUF)
GGUF-formatted versions of IBM Granite 3.2 models. Licensed under the Apache 2.0 license.
Materials
Welcome to IBM’s multi-modal foundation model for materials, FM4M, designed to support and advance research in materials science and chemistry.