Sign in

Nikolai Rozanov

@ai-nikolai.bsky.social
535 followers 206 following 18 posts

CS. PhD Candidate in LLM Agents @ImperialCollegeLondon || ex tech-founder nikolairozanov.com

PostsRepliesMedia
Reposted by Nikolai Rozanov
Lisa Alazraki @lisaalaz.bsky.social · 13/02/2025
Do LLMs need rationales for learning from mistakes? 🤔 When LLMs learn from previous incorrect answers, they typically observe corrective feedback in the form of rationales explaining each mistake. In our new preprint, we find these rationales do not help, in fact they hurt performance! 🧵
1219
Reposted by Nikolai Rozanov
Chris Paxton @cpaxton.bsky.social · 22/01/2025
Not that you need another thread on Deepseek's R1, but I really enjoy these models, and it's great to see an *open*, MIT-licensed reasoner that's ~as good as OpenAI o1. A blog post: itcanthink.substack.com/p/deepseek-r... It's really very good at ARC-AGI for example:
2407
Reposted by Nikolai Rozanov
Nathan Lambert @natolambert.bsky.social · 23/01/2025
LLM360 gets way less recognition relative to the quality of their totally open outputs in the last year+. They dropped a 60+ page technical report last week and I don't know if I saw anyone talking about it. Along with OLMo, it's the other up to date open-source LM. Paper: buff.ly/40I6s4d
1455
Reposted by Nikolai Rozanov
Nikolai Rozanov @ai-nikolai.bsky.social · 21/01/2025
#NLP #LLMAgents Community, I have a question: I have been running Webshop with older GPTs, e.g. gpt-3.5-turbo-1106 / -0125 / -instruct). On 5 different code repos (ReAct, Reflexion, ADaPT, StateAct) I am getting scores of 0%, while previously the scores where at ~15%. Any thoughts anyone?
111
Nikolai Rozanov @ai-nikolai.bsky.social · 21/01/2025
#NLP #LLMAgents Community, I have a question: I have been running Webshop with older GPTs, e.g. gpt-3.5-turbo-1106 / -0125 / -instruct). On 5 different code repos (ReAct, Reflexion, ADaPT, StateAct) I am getting scores of 0%, while previously the scores where at ~15%. Any thoughts anyone?
111
Reposted by Nikolai Rozanov
Ian Goodfellow @ian-goodfellow.bsky.social · 24/11/2024
Posting a call for help: does anyone know of a good way to simultaneously treat both POTS and Ménière’s disease? Please contact me if you’re either a clinician with experience doing this or a patient who has found a good solution. Context in thread
1512771
Reposted by Nikolai Rozanov
Ai2 @ai2.bsky.social · 26/11/2024
Meet OLMo 2, the best fully open language model to date, including a family of 7B and 13B models trained up to 5T tokens. OLMo 2 outperforms other fully open models and competes with open-weight models like Llama 3.1 8B — As always, we released our data, code, recipes and more 🎁
The OLMo 2 models sit at the Pareto frontier of training FLOPs vs model average performance.
515235
Nikolai Rozanov @ai-nikolai.bsky.social · 23/11/2024
Pretty cool people are being added to the LLM Agent & LLM Reasoning group. Thanks @lisaalaz.bsky.social for suggesting @jhamrick.bsky.social @gabepsilon.bsky.social and others. Feel free to mention yourself and others. :) go.bsky.app/LUrLWXe #LLMAgents #LLMReasoning
8141
Reposted by Nikolai Rozanov
Peng Qi @qi2peng2.bsky.social · 21/11/2024
#EMNLP2024 was a fun time to reconnect with old friends and meet new ones! Reflecting on the conference program and in-person discussions, I believe we're seeing the "Google Moment" to #IR research play out in #NLProc. 1/n
1153
Reposted by Nikolai Rozanov
Nikolai Rozanov @ai-nikolai.bsky.social · 20/11/2024
I thought to create a Starter Pack for people working on LLM Agents. Please feel free to self-refer as well. go.bsky.app/LUrLWXe #LLMAgents #LLMReasoning
12165
Nikolai Rozanov @ai-nikolai.bsky.social · 20/11/2024
I thought to create a Starter Pack for people working on LLM Agents. Please feel free to self-refer as well. go.bsky.app/LUrLWXe #LLMAgents #LLMReasoning
12165
Reposted by Nikolai Rozanov
Lisa Alazraki @lisaalaz.bsky.social · 20/11/2024
Hi Bluesky, would like to introduce myself 🙂 I am PhD-ing at Imperial College under @marekrei.bsky.social’s supervision. I am broadly interested in LLM/LVLM reasoning & planning 🤖 (here’s our latest work arxiv.org/abs/2411.04535) Do reach out if you are interested in these (or related) topics!
arxiv.org
Meta-Reasoning Improves Tool Use in Large Language Models
External tools help large language models (LLMs) succeed at tasks where they would otherwise typically fail. In existing frameworks, LLMs learn tool use either by in-context demonstrations or via full...
0403
Nikolai Rozanov @ai-nikolai.bsky.social · 20/11/2024
Quick intro to myself. I am a CS PhD in LLM Agents @imperial-nlp.bsky.social with @marekrei.bsky.social. This is our latest work on LLM Agents: StateAct: arxiv.org/abs/2410.02810 (outperforming ReAct by ~10%). Feel free to reach out for collaboration.
arxiv.org
StateAct: State Tracking and Reasoning for Acting and Planning with Large Language Models
Planning and acting to solve `real' tasks using large language models (LLMs) in interactive environments has become a new frontier for AI methods. While recent advances allowed LLMs to interact with o...
092
Reposted by Nikolai Rozanov
Joe Stacey @joestacey.bsky.social · 20/11/2024
Welcome to Bluesky to more of our NLP researchers at Imperial!! Looking forward to following everyone's work on here. To follow us all click 'follow all' in the starter pack below go.bsky.app/Bv5thAb
3207