MTS @ Cohere on code. Views not my employer’s.https://bsky.app/profile/tomsherborne.bsky.socialhttps://bsky.app/profile/tomsherborne.bsky.social/post/3liope5spqk2uWe are hiring @cohere.com for an Agent Infrastructure Engineer! If you want to work on building the next generation of agent models for #RAG, #ToolUse #Code, #Reasoning and more then apply here. DM me if you have any Qs. https://jobs.ashbyhq.com/cohere/3f797fee-430a-4fdd-8c06-acf7899de5b821 Feb 2025 11:31 +0000at://did:plc:nrza7tzhisi6o7gxpowajjz2/app.bsky.feed.post/3liope5spqk2uhttps://bsky.app/profile/tomsherborne.bsky.social/post/3lcfwpgv7422uI’ll be at @neuripsconf.bsky.social all next week! Find me mostly at the @cohere.com booth / DM me to talk code / post-training / life at Cohere 🇨🇦03 Dec 2024 15:17 +0000at://did:plc:nrza7tzhisi6o7gxpowajjz2/app.bsky.feed.post/3lcfwpgv7422uhttps://bsky.app/profile/tomsherborne.bsky.social/post/3kkclivavuc23My PhD thesis "Modelling Cross-lingual Transfer For Semantic Parsing" is finally submitted! 🎉🎉🎉31 Jan 2024 21:14 +0000at://did:plc:nrza7tzhisi6o7gxpowajjz2/app.bsky.feed.post/3kkclivavuc23https://bsky.app/profile/tomsherborne.bsky.social/post/3kj4bnbsc4g2fTRAM is accepted to #ICLR2024 as a Spotlight! See you in Vienna 🇦🇹! Thanks to @nsaphra.bsky.social, Pradeep Dasigi, Hao Peng and @ai2.bsky.social Vision experiments, more discussion and visuals coming soon to the camera ready! [contains quote post or other embedded content]16 Jan 2024 15:36 +0000at://did:plc:nrza7tzhisi6o7gxpowajjz2/app.bsky.feed.post/3kj4bnbsc4g2fhttps://bsky.app/profile/tomsherborne.bsky.social/post/3kbhpza55s72t🚨 new paper 🚨 Can we train for flat minima with less catastrophic OOD forgetting? 

We propose Trust Region Aware Minimization for smoothness in parameters+representations. TL;DR representations matter just as much! arxiv.org/abs/2310.03646 w/ @nsaphra.bsky.social Pradeep Dasigi + Hao Peng11 Oct 2023 09:31 +0000at://did:plc:nrza7tzhisi6o7gxpowajjz2/app.bsky.feed.post/3kbhpza55s72t