Really enjoyed the SWE-Agent technical paper.

My overall takeaway is the importance of context management for building complex agentic workflows.

There are a lot of key components necessary for LLM-based agents to autonomously complete software engineering tasks. This paper…

500B billion parameters in-house model from Microsoft?

It wouldn't surprise me. I am also eager to see what they do with the Phi model series.

AlphaMath Almost Zero

Enhances LLMs with Monte Carlo Tree Search (MCTS) to improve mathematical reasoning capabilities.

The MCTS framework extends the LLM to achieve a more effective balance between exploration and exploitation.

For this work, the idea is to generate…

Hallucination of Multimodal LLMs

This new paper presents a comprehensive overview of hallucination in multimodal large language models.

Discusses recent advances in detection, evaluation, and mitigation strategies for hallucination. It also summarizes causes, evaluation…

I am getting a lot of requests for educational materials on how to build AI agents.

Here is a FREE 2-hour workshop to learn about complex AI agents.

It's a good opportunity to learn how to apply AI agents for automating tasks in areas like customer support, marketing,…

Hallucination of Multimodal LLMs

This new paper presents a comprehensive overview of hallucination in multimodal large language models.

Discusses recent advances in detection, evaluation, and mitigation strategies for hallucination. It also summarizes causes, evaluation…

The Top ML Papers of the Week (April 29 - May 5):

- Med-Gemini
- When to Retrieve?
- Kolmogorov-Arnold Networks
- Multimodal LLM Hallucinations
- Self-Play Preference Optimization
- In-Context Learning with Long-Context Models
...

The most exciting LLM paper of the week was the one from Gloeckle et al. that aims to train better and faster LLM via multi-token prediction.

It's an impressive research paper so I had lots of thoughts as usual, especially because it attempts to push LLMs forward.

I enjoyed…

An Open Source LM Specialized in Evaluating Other LMs

Open-source Prometheus 2 (7B & 8x7B), state-of-the-art open evaluator LLMs that closely mirror human and GPT-4 judgments.

They support both direct assessments and pair-wise ranking formats grouped with user-defined…

The most exciting LLM paper of the week was the one from Gloeckle et al. that aims to train better and faster LLM via multi-token prediction.

It's an impressive research paper so I had lots of thoughts as usual, especially because it attempts to push LLMs forward.

I enjoyed…