Saibo-Creator (@saibogeng) 's Twitter Profile
Saibo-Creator

@saibogeng

PhD @EPFL | Reliable Robust LLM Generation | intern @MSFTResearch

ID: 3229795705

linkhttps://saibo-creator.github.io/ calendar_today29-05-2015 13:02:04

144 Tweet

191 Followers

196 Following

Saibo-Creator (@saibogeng) 's Twitter Profile Photo

#ACL2024 I'll be giving an oral presentation at 17:15 in World Ballroom B on my previous work about how to indirectly apply constraining to Blackbox LLM. arxiv.org/abs/2401.09967 I’d love to chat about LLM inference, constrained decoding, or any interesting ideas :)

Saibo-Creator (@saibogeng) 's Twitter Profile Photo

Holy shit, I mis-typed " stirct " instead of "strict" and when I tab, copilot generate " # typo here " in comment ! wow ! I like it !

Holy shit, I mis-typed " stirct " instead of "strict" and when I tab, copilot generate " # typo here " in comment !  wow ! I like it !
Logan Kilpatrick (@officiallogank) 's Twitter Profile Photo

We just shipped Structured Outputs, JSON schema mode, for Gemini 1.5 Flash, available via API and AI Studio right now (I love shipping on Fridays)! 🏗️ ai.google.dev/gemini-api/doc…

Akhil Arora (@akhilarora.bsky.social) (@aroraakhilcs) 's Twitter Profile Photo

Disappointed to not be at #EMNLP owing to a dislocated shoulder 😢 Debjit Paul will present our poster on Multilingual Entity Insertion (cf. arxiv.org/pdf/2410.04254). Swing by our poster in session #6 on Wed 13@10:30 EST 🚀 PS: I am hiring PhD students Computer Science at Aarhus University #LLM #GNNs #CSS

Disappointed to not be at #EMNLP owing to a dislocated shoulder 😢
<a href="/DebjitPaul2/">Debjit Paul</a>  will present our poster on Multilingual Entity Insertion (cf. arxiv.org/pdf/2410.04254). Swing by our poster in session #6 on Wed 13@10:30 EST

🚀 PS: I am hiring PhD students <a href="/csaudk/">Computer Science at Aarhus University</a> 
#LLM #GNNs #CSS
Julian Minder (@jkminder) 's Twitter Profile Photo

Can we understand and control how language models balance context and prior knowledge? Our latest paper shows it’s all about a 1D knob! 🎛️ arxiv.org/abs/2411.07404 Co-led with Kevin Du, as well as Niklas Stoehr, Giovanni Monea, Chris Wendler, Bob West & Ryan Cotterell.

Chris Wendler (@wendlerch) 's Twitter Profile Photo

R1 is exciting and provides unique challenges from a mechanistic interpretability point of view. Come join us at ARBOR — an open research collective aimed at collaboratively reverse engineering LLM based reasoning models.

Luca Beurer-Kellner (@lbeurerkellner) 's Twitter Profile Photo

🔴 New MCP attack leaks WhatsApp messages via MCP, side-stepping WhatsApp security. 1/n We show a new MCP attack that leaks your WhatsApp messages if you are connected via WhatsApp MCP. Our attack uses a sleeper design, circumventing the need for user approval. More 👇

🔴 New MCP attack leaks WhatsApp messages via MCP, side-stepping WhatsApp security. 1/n

We show a new MCP attack that leaks your WhatsApp messages if you are connected via WhatsApp MCP.

Our attack uses a sleeper design, circumventing the need for user approval.

More 👇
Saibo-Creator (@saibogeng) 's Twitter Profile Photo

It feels quite unreal that after I return from my holiday, the company I'm interning got acquired! CRAZY TIMES !!!😎 Congrats again to the cofounders!!!