• Are your Visual Programs Right for the Wrong Reasons?

  ViUniT, Making AI visual reasoning reliable, one unit test at a time.

  5 min read   ·   April 17, 2025

  2025   ·   multimodal-ai   ·   research

• Introducing TACO - Salesforce AI Research's Family of Multimodal Action Models - Salesforce

  We present TACO, a family of multi-modal large action models designed to improve performance on complex questions that require multiple capabilities and demand multi-step solutions. 

  7 min read   ·   January 16, 2025   ·   salesforce.com

  2025   ·   multimodal-ai   agents   ·   research

• A World of Multi-AI-Agents

  Single-agent and multi-agent architectures

  5 min read   ·   December 09, 2024

  2024   ·   agents   ·   ai-salon

• Hey assistant, don't let me forget my card at the ATM!

  A new benchmark for video understanding.

  4 min read   ·   December 06, 2024

  2024   ·   multimodal-ai   ·   research

• xLAM: A Family of Large Action Models for AI Agents - Salesforce

  Huan Wang, Shelby Heinecke, Juan Carlos Niebles, Caiming Xiong TL;DR: We release xLAM, a series of LLMs optimized for function calling and AI Agents. It offers several variants designed to serve different application…

  7 min read   ·   September 06, 2024   ·   salesforce.com

  2024   ·   agents   ·   research