Salesforce AI Research

All

57 repositories

LATTE
Public
Python
•
Other
•4•63•4•0•Updated Sep 15, 2025Sep 15, 2025
gift-eval
Public
Jupyter Notebook
•
Apache License 2.0
•38•140•8•2•Updated Sep 14, 2025Sep 14, 2025
MCP-Universe
Public
MCP-Universe is a comprehensive framework designed for developing, testing, and benchmarking AI agents
Python
•
Apache License 2.0
•36•419•2•2•Updated Sep 12, 2025Sep 12, 2025
LoCoBench
Public
Python
•
Apache License 2.0
•0•8•2•0•Updated Sep 11, 2025Sep 11, 2025
MCPEval
Public
MCP-based Agent Deep Evaluation System
Python
•
Apache License 2.0
•12•129•3•1•Updated Sep 10, 2025Sep 10, 2025
pretrain-time-series-cloudops
Public archive
Official code repository for the paper "Pushing the Limits of Pre-training for Time Series Forecasting in the CloudOps Domain"
time-series forecasting cloudops pretrain
Python
•
Apache License 2.0
•4•23•1•0•Updated Sep 9, 2025Sep 9, 2025
CoAct
Public
CoAct-1: Computer-using Agents with Coding as Actions
agents cua
Python
•
Other
•0•4•0•0•Updated Aug 27, 2025Aug 27, 2025
xLAM
Public
xLAM: A Family of Large Action Models to Empower AI Agent Systems
agents xlam llms llm-agent agentstudio actionstudio
Python
•
Apache License 2.0
•46•560•5•0•Updated Aug 21, 2025Aug 21, 2025
strefer
Public
Strefer: Empowering Video LLMs with Space-Time Referring and Reasoning via Synthetic Instruction Data
Jupyter Notebook
•
Other
•0•8•1•0•Updated Aug 18, 2025Aug 18, 2025
uni2ts
Public
Unified Training of Universal Time Series Forecasting Transformers
machine-learning deep-learning time-series transformers forecasting representation-learning time-series-forecasting pre-training pre-trained-models universal-forecasting
Jupyter Notebook
•
Apache License 2.0
•149•1.2k•35•1•Updated Aug 12, 2025Aug 12, 2025
UserBench
Public
Python
•
Apache License 2.0
•2•34•2•0•Updated Aug 5, 2025Aug 5, 2025
promptomatix
Public
An Automatic Prompt Optimization Framework for Large Language Models
Python
•
Apache License 2.0
•11•117•0•0•Updated Aug 1, 2025Aug 1, 2025
benchforce
Public
Python
•
Apache License 2.0
•0•1•0•0•Updated Jul 18, 2025Jul 18, 2025
HERB
Public
Python
•
Other
•1•0•0•0•Updated Jul 17, 2025Jul 17, 2025
MAS-Zero
Public
Designing Multi-Agent Systems with Zero Supervision
multi-agent-systems large-language-models self-evolving inference-time-compute reasoning-language-models zero-supervision
Python
•
Apache License 2.0
•10•99•1•0•Updated Jul 8, 2025Jul 8, 2025
SweRank
Public
Python
•
Other
•4•12•1•0•Updated Jul 4, 2025Jul 4, 2025
CRMArena
Public
Official Repo for CRMArena and CRMArena-Pro
Python
•
Other
•17•114•1•1•Updated Jun 24, 2025Jun 24, 2025
oss-template
Public template
Apache License 2.0
•0•1•0•0•Updated Jun 18, 2025Jun 18, 2025
ReasoningJudgeBench
Public
Python
•
Other
•0•3•0•0•Updated Jun 17, 2025Jun 17, 2025
jetts-benchmark
Public
Code repository for the paper "Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators"
Python
•
Other
•0•4•0•0•Updated Jun 17, 2025Jun 17, 2025
FaithEval
Public
Apache License 2.0
•4•48•1•0•Updated Jun 11, 2025Jun 11, 2025
Elastic-Reasoning
Public
Make reasoning models scalable
scalable reasoning cot llm
Jupyter Notebook
•
Apache License 2.0
•3•46•1•0•Updated May 31, 2025May 31, 2025
Unanswerability_RAGE
Public
Python
•
Apache License 2.0
•0•5•0•0•Updated May 20, 2025May 20, 2025
CogAlign
Public
Why Vision Language Models Struggle with Visual Arithmetic? Towards Enhanced Chart and Geometry Understanding
Jupyter Notebook
•
Other
•0•8•0•0•Updated May 17, 2025May 17, 2025
perfcodegen
Public
Python
•
Apache License 2.0
•2•45•1•0•Updated May 6, 2025May 6, 2025
discrn
Public
Apache License 2.0
•1•1•0•0•Updated Apr 18, 2025Apr 18, 2025
ReGenesis
Public
Python
•
Apache License 2.0
•0•6•0•0•Updated Apr 10, 2025Apr 10, 2025
BingoGuard
Public
Python
•
Apache License 2.0
•0•5•0•0•Updated Apr 10, 2025Apr 10, 2025
SiReRAG
Public
Python
•
Other
•2•12•1•0•Updated Apr 7, 2025Apr 7, 2025
EntroDrop
Public
Python
•
Apache License 2.0
•1•2•1•0•Updated Apr 1, 2025Apr 1, 2025