Lilian Ngweta

lilianngweta's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted an article 14 days ago

view article

Article

Model Routing Is Simple. Until It Isn’t.

• 

ibm-research

•

14 days ago

• 65

upvoted an article 28 days ago

view article

Article

ScarfBench: Benchmarking AI Agents for Enterprise Java Framework Migration

• 

ibm-research

•

29 days ago

• 26

upvoted an article about 1 month ago

view article

Article

Build real agentic apps using CUGA: two dozen working examples on a lightweight harness

• 

ibm-research

•

Jun 23

• 38

upvoted an article about 2 months ago

view article

Article

Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic

• 

ibm-research

•

Jun 1

• 89

upvoted a paper 3 months ago

MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments

Paper • 2605.09131 • Published May 9 • 60

upvoted an article 4 months ago

view article

Article

ALTK‑Evolve: On‑the‑Job Learning for AI Agents

• 

ibm-research

•

Apr 8

• 29

liked a Space 4 months ago

Running

19

VAKRA Leaderboard

🏆

19

Explore AI agent benchmark and submit results

liked a dataset 4 months ago

ibm-research/VAKRA

Viewer • Updated Mar 31 • 1.33k • 675 • 46

updated a dataset almost 2 years ago

lilianngweta/aligners-datasets

Viewer • Updated Sep 27, 2024 • 557k • 16

updated a model almost 2 years ago

lilianngweta/ethical-aligner-7B

7B • Updated Sep 27, 2024 • 2

authored 2 papers over 2 years ago

Aligners: Decoupling LLMs and Alignment

Paper • 2403.04224 • Published Mar 7, 2024

Simple Disentanglement of Style and Content in Visual Representations

Paper • 2302.09795 • Published Feb 20, 2023 • 1