The Natural Language Processing Group at the University of Edinburgh.
Edinburgh, Scotland
Joined May 2017
- Tweets1.3K
- Following158
- Followers13.9K
- Likes922
EdinburghNLP retweeted
my amazing collaborators will be presenting a few papers at EMNLP/NeurIPS/LoG -- if you're attending any of these conferences, touch base with them; they're great! 🚀🚀🚀
blog post: neuralnoise.com/2026/emnlp-n…
EdinburghNLP retweeted
VLMs benefit from tool calls as they allow for "thinking with images".
But can a VLM simply internalise the effects of calling correct tools in the latent space and not need to explicitly call them during inference? 🧵
Presenting tomorrow at 11 AM @COLM_conf !
EdinburghNLP retweeted
Did you know training on your own incorrect samples can beat distilling from a much larger teacher?
Traditional RFT only reinforces a narrow set of approaches. Strategically sampling for approach-level diversity gives better pass@k, test-time scaling and RL initialization!
alexgurung.me/diversity/
🧵
EdinburghNLP retweeted
Very happy to see @j0hngou’s work accepted as a NeurIPS oral! I particularly like the broader idea: let models interact richly during training while pressuring them to reduce that interaction. This gives a denser learning signal and leads to more effective one-shot collaboration
Happy to share that our paper "Clarification as Supervision" was accepted as an Oral at #NeurIPS2026 (top ~0.3%). When a text-only reasoner answers from a VLM's caption and gets it wrong, we usually blame the reasoning. Often the caption left out the details the reasoner needed🧵
EdinburghNLP retweeted
Self-play on a massive number of synthetic environments as an endless source of super-human post-training data 🚀🚀🚀 Really happy this is now out — it may be how we achieve AGI/ASI 🙂
📄 arxiv.org/abs/2609.30936
🌐 lormolf.github.io/publicatio…
Work done during my visiting period at the University of Edinburgh with @PMinervini , together with the UniboNLP group
Kudos to all my coauthors!
EdinburghNLP retweeted
Latent reasoning (i.e. recursively decomposing goals into sub-goals in latent space, and extracting symbolic knowledge by decoding goal and sub-goal representations) waaay before it was cool, straight outta ICML’20
EdinburghNLP retweeted
Back in 2021 we managed to get an ICLR Outstanding Paper Award (iclr-conf.medium.com/announc…) with @_kire_kara_’s amazing MSc thesis work, today this looks a bit more tricky to achieve 😬
EdinburghNLP retweeted
Edoardo is amazing, catch this opportunity! 🚀🚀🚀🚀🚀
I am looking for 1 postdoc and 2 fully funded PhDs at Imperial @ICComputing to join my @ERC_Research project AToM ⚛
We aim to build models that learn to compress what they perceive and remember, for permanent memory, longer horizons, and >10x speedups
ducdauge.github.io/atom/
EdinburghNLP retweeted
I am looking for 1 postdoc and 2 fully funded PhDs at Imperial @ICComputing to join my @ERC_Research project AToM ⚛
We aim to build models that learn to compress what they perceive and remember, for permanent memory, longer horizons, and >10x speedups
ducdauge.github.io/atom/
EdinburghNLP retweeted
Fazl and his group are stellar; consider applying!!! 🚀🚀🚀
EdinburghNLP retweeted
Whether a model is faithful (and, e.g., whether it's relying on a cue) depends heavily on environmental factors, and faithfulness/mechinterp/safety research should take that into account! 🚀 Amazing work by @aryopg et al.
EdinburghNLP retweeted
Developing next-generation accelerators requires benchmarking them on realistic and agentic AI workloads.
With @ARIA_research's Scaling Compute programme, we are releasing TEAS 🍵, serving 5 models (4B to ~1T total) on 9 accelerators for 6 workloads.
teasbench.com/
EdinburghNLP retweeted
CoT monitoring assumes reasoning traces record what shapes an answer.
Yet, we found that models are less likely to verbalize a cue in its CoT when the cue comes from a tool return instead of the user message! 👀
🧵
EdinburghNLP retweeted
Scotland is pretty amazing AI-wise! For example, @EdinburghUni folks have been doing AI research since the 60s (informatics.ed.ac.uk/aiai/hi…), and they still have a pretty massive impact (impactrank.org/, informatics.ed.ac.uk/news/la…, etc.).
EdinburghNLP retweeted
We are pleased to announce the winner of the ACL Computational Linguistics Doctoral Dissertation Award (ACL Dissertation Award)! Congratulations Verna Dankers!
@vernadankers #NLproc #CLJournal
EdinburghNLP retweeted
Organisations -- sponsorship opportunities are available for #EACL2027, the flagship European conference in computational linguistics, taking place in Athens in March 2027! Support the #NLP community and connect with researchers and practitioners: 2027.eacl.org/
EdinburghNLP retweeted
Today + tomorrow I'm at @aclmeeting '26, and early this morning, I received the 2026 ACL Computational Linguistics Doctoral Dissertation Award!! 🙀🏆👩🎓It's the icing on the cake of my excellent PhD experience in Edinburgh @Edin_CDT_NLP @EdinburghNLP. (1/3)
Don't forget to attend the "ACL Computational Linguistics Doctoral Dissertation Award 2026" session on Mon Jul 6, 9:009:30 AM (Location: Promenade) in the "Session 8: Oral/Poster Session D" (1/2) #ACL2026NLP
EdinburghNLP retweeted
On-policy self-distillation: the teacher saw the solution; the student didn't. Copy that confidence and you gain in-domain but lose out-of-domain reasoning. GeoSD scales the teacher's pull by overlap and bounds drift - OOD +5.7–8.6 pts, ID largely intact. Led by @chatruncata
Self-distillation gives LLMs dense reasoning feedback without requiring a larger teacher. But ID gains can come at the cost of OOD generalization. New joint work with @iatitov : "Geometric Self-Distillation for Reasoning Generalization" (arxiv.org/abs/2607.06855)
EdinburghNLP retweeted
Self-distillation gives LLMs dense reasoning feedback without requiring a larger teacher. But ID gains can come at the cost of OOD generalization. New joint work with @iatitov : "Geometric Self-Distillation for Reasoning Generalization" (arxiv.org/abs/2607.06855)
