Palette: teaching a small model to build decks in your design language
• 21
AI & ML interests
Enterprise AI and ML, Foundation Models, Responsible AI
Recent Activity
View all activity
Papers
DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training
DataKernelBench: Can LLMs Optimize Database Queries on GPUs?
Articles
Pretrained graph networks that predict QAOA parameters for max-cut.
Enterprise agent ecosystem featuring AssetOpsBench (industrial) and ITBench (SRE, FinOps, CISO), CUGA to accelerate AI Automation
-
CUGA Apps
🚀61Explore and use multiple web tools from a single dashboard
-
AssetOpsBench
🚀24Run a quick benchmark of web asset performance
-
CUGA Agent
🤖105Configurable Generalist Agent, leader in AppWorld Benchmark
-
MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments
Paper • 2605.09131 • Published • 59
REAL-MM-RAG-Bench is a benchmark designed to evaluate multi-modal retrieval models under realistic and challenging conditions.
Datasets and models of the Otter-Knowledge project
GGUF-formatted versions of IBM Granite 3.2 models. Licensed under the Apache 2.0 license.
-
ibm-research/granite-3.2-2b-instruct-GGUF
Text Generation • 3B • Updated • 838 • 13 -
ibm-research/granite-3.2-8b-instruct-GGUF
Text Generation • 8B • Updated • 1.12k • 11 -
ibm-research/granite-vision-3.2-2b-GGUF
3B • Updated • 1.34k • 16 -
ibm-research/granite-guardian-3.2-3b-a800m-GGUF
Text Generation • 3B • Updated • 669 • 5
A collection of time series models trained by IBM
-
ibm-research/ttm-research-r2
Time Series Forecasting • 855k • Updated • 11.6k • 9 -
ibm-research/ttm-r3
Time Series Forecasting • 1.41M • Updated • 1.63k • 9 -
ibm-research/flowstate
Time Series Forecasting • 9.07M • Updated • 57.2k • 13 -
ibm-research/patchtst-fm-r1
Time Series Forecasting • 0.3B • Updated • 29.6k • 10
An evaluation suite created for benchmarking of retrieval models on Table+Text retrieval datasets.
This category highlights the collective efforts of the AI Automation team in advancing Industry 4.0 applications and exploring innovations beyond it.
-
AssetOpsBench: Benchmarking AI Agents for Task Automation in Industrial Asset Operations and Maintenance
Paper • 2506.03828 • Published • 20 -
FailureSensorIQ: A Multi-Choice QA Dataset for Understanding Sensor Relationships and Failure Modes
Paper • 2506.03278 • Published • 7 -
ibm-research/AssetOpsBench
Viewer • Updated • 467 • 1.18k • 51 -
AssetOpsBench
📉4Evaluating Autonomous AI Agents for Industry 4.0 Tasks
REAL-MM-RAG-Bench is a benchmark designed to evaluate multi-modal retrieval models under realistic and challenging conditions.
Welcome to IBM’s multi-modal foundation model for materials, FM4M, designed to support and advance research in materials science and chemistry.
Pretrained graph networks that predict QAOA parameters for max-cut.
A collection of time series models trained by IBM
-
ibm-research/ttm-research-r2
Time Series Forecasting • 855k • Updated • 11.6k • 9 -
ibm-research/ttm-r3
Time Series Forecasting • 1.41M • Updated • 1.63k • 9 -
ibm-research/flowstate
Time Series Forecasting • 9.07M • Updated • 57.2k • 13 -
ibm-research/patchtst-fm-r1
Time Series Forecasting • 0.3B • Updated • 29.6k • 10
Enterprise agent ecosystem featuring AssetOpsBench (industrial) and ITBench (SRE, FinOps, CISO), CUGA to accelerate AI Automation
-
CUGA Apps
🚀61Explore and use multiple web tools from a single dashboard
-
AssetOpsBench
🚀24Run a quick benchmark of web asset performance
-
CUGA Agent
🤖105Configurable Generalist Agent, leader in AppWorld Benchmark
-
MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments
Paper • 2605.09131 • Published • 59
An evaluation suite created for benchmarking of retrieval models on Table+Text retrieval datasets.
REAL-MM-RAG-Bench is a benchmark designed to evaluate multi-modal retrieval models under realistic and challenging conditions.
This category highlights the collective efforts of the AI Automation team in advancing Industry 4.0 applications and exploring innovations beyond it.
-
AssetOpsBench: Benchmarking AI Agents for Task Automation in Industrial Asset Operations and Maintenance
Paper • 2506.03828 • Published • 20 -
FailureSensorIQ: A Multi-Choice QA Dataset for Understanding Sensor Relationships and Failure Modes
Paper • 2506.03278 • Published • 7 -
ibm-research/AssetOpsBench
Viewer • Updated • 467 • 1.18k • 51 -
AssetOpsBench
📉4Evaluating Autonomous AI Agents for Industry 4.0 Tasks
Datasets and models of the Otter-Knowledge project
REAL-MM-RAG-Bench is a benchmark designed to evaluate multi-modal retrieval models under realistic and challenging conditions.
GGUF-formatted versions of IBM Granite 3.2 models. Licensed under the Apache 2.0 license.
-
ibm-research/granite-3.2-2b-instruct-GGUF
Text Generation • 3B • Updated • 838 • 13 -
ibm-research/granite-3.2-8b-instruct-GGUF
Text Generation • 8B • Updated • 1.12k • 11 -
ibm-research/granite-vision-3.2-2b-GGUF
3B • Updated • 1.34k • 16 -
ibm-research/granite-guardian-3.2-3b-a800m-GGUF
Text Generation • 3B • Updated • 669 • 5
Welcome to IBM’s multi-modal foundation model for materials, FM4M, designed to support and advance research in materials science and chemistry.