We have a new paper up on arXiv! 🥳🪇 The paper tries to improve the robustness of closed-source LLMs fine-tuned on NLI, assuming a realistic training budget of 10k training examples. Here's a 60 second rundown of what we found!

ACL is almost here 🎉 Our Imperial NLP community will be presenting several papers at the conference next week. We look forward to seeing everyone in Vienna!

I’ll be at #acl2025 next week in Vienna🇦🇹 presenting our work. Looking forward to meeting old and new friends! If you like to discuss chatbot, code generation, multi-agents, robustness, hate speech detection, or just life😆, feel free to reach out and I’d love to chat!

We released two open-weight reasoning models—gpt-oss-120b and gpt-oss-20b—under an Apache 2.0 license. Developed with open-source community feedback, these models deliver meaningful advancements in both reasoning capabilities & safety. openai.com/index/introduc…

Summary of GPT-OSS architectural innovations: 1. sliding window attention (ref: arxiv.org/abs/1901.02860) 2. mixture of experts (ref: arxiv.org/abs/2101.03961) 3. RoPE w/ Yarn (ref: arxiv.org/abs/2309.00071) 4. attention sinks (ref: streaming llm arxiv.org/abs/2309.17453)

8 RAG architectures all AI Engineers should know:

This is accepted to EMNLP Main! Looking forward to presenting it in Suzhou 🎉

Life update: I’ve just defended my PhD in Robust NLP 🎓 Huge thanks to my supervisors Lucia Specia Marek Rei and to my examiners Björn Schuller Barbara Plank! I’ll be continuing at Epic Games, building agents and pushing better code generation for game development.

We have released #AgentCoMa, an agentic reasoning benchmark where each task requires a mix of commonsense and math to be solved 🧐 LLM agents performing real-world tasks should be able to combine these different types of reasoning, but are they fit for the job? 🤔 🧵⬇️

We introduce PiCSAR (Probabilistic Confidence Selection And Ranking)💡: A simple training-free method for scoring samples based on probabilistic confidence, selecting a reasoning chain with the highest confidence from multiple sampled responses. ✏️PiCSAR is generalisable across

The Unreal Engine version of the Epic Developer Assistant is now accessible on the Epic Developer Community. The Epic Developer Assistant, which currently supports up to UE 5.6, provides guidance on using Unreal Engine and helps generate C++ Code. Check it out here:

Our Imperial NLP community is ready for #EMNLP2025 ✈️ Check out the papers we’ll be presenting next week in Suzhou and come say hi!

I’ll be attending #EMNLP2025 next week. Super excited to attend a *CL conference in China and looking forward to meeting different researchers and learning from their work! Feel free to reach out if you are also interested in agents, code generation, and AI for game development.

🤯This is super cool!