🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

NEW PAPER ALERT: Generating visual narratives to illustrate textual stories remains an open challenge, due to the lack of knowledge to constrain faithful and self-consistent generations. Our #CVPR2025 paper proposes a new benchmark, VinaBench, to address this challenge.

🚨 AI is in legal hot water. Lawsuits over copyrighted training data are mounting — and content owners are pulling out fast. Top opt-outs? 📰 News & Media 🔬 Science & Tech 🏥 Health Info But here’s the thing: How much do those datasets actually matter for model performance? 🧵👇

We are pleased to invite you to NUS (NUS)-Swiss AI Workshop on Wed April 23 (a day before ICLR 2026 #ICLR2025 in Singapore). Register for the workshop here (seats are limited!!!): forms.office.com/pages/response… This workshop is co-organized with the Swiss AI Initiative, a

The following 3 events at NUS are part of the Singapore AI Research Week (smartnation.gov.sg/singapore-ai-r…) that is held in parallel with ICLR 2026 #ICLR2025. 23 Apr (Wed) 2-6pm ~ NUS-Swiss AI Workshop featuring Antoine Bosselut Antoine Bosselut (EPFL), Annie Hartley Mary-Anne Hartley (Annie)

I am attending NAACL this week to present our paper. Come check out our poster at 14:00, Apr 30 in Hall 3 . Hale Sirin Defne Circi will also be there to answer your questions!

Excited to be at #NAACL2025 in Albuquerque! I’ll be presenting our paper “The LLM Language Network” as an Oral tomorrow at 2:00 PM in Ballroom C, hope to see you there! Grateful to my co-authors Greta Tuckute, Antoine Bosselut, Martin Schrimpf — looking forward to the discussions!🧠

EPFL researchers have discovered key ‘units’ in large AI models that seem to be important for language, mirroring the brain’s language system. When these specific units were turned off, the models got much worse at language tasks. #EPFL #AI #brain #communication #neuroscience

Many AI models speak dozens of languages, but do they grasp cultural context? 🗣️🌍 The INCLUDE benchmark from EPFL's NLP Lab and Cohere Labs reveal that there is still a gap... 👉 Find out how benchmarks like INCLUDE can help make AI more inclusive: actu.epfl.ch/news/beyond-tr…

Got ideas for making LLMs more inclusive and culturally aware? 🌍✨ Submit to #MELT Workshop 2025! We’re all about multilingual, multicultural, and equitable LLMs; come share your work! 🧠💬 📅 Oct 10, 2025 | Co-located with Conference on Language Modeling 🔗 melt-workshop.github.io

Global MMLU is revolutionizing multilingual AI. 🌍 Recognized by Stanford HAI and adopted by top labs, it's the benchmark for fair evaluation across 42 languages. Looking forward to sharing this work at ACL in Vienna next month. 🇦🇹

Check out Badr's work on specializing experts in MoE-style models to individually represent the operation of different brain networks.

What makes some jailbreak suffixes stronger than others? We looked into the inner workings of GCG-like attacks and found a cool hijacking mechanism that strong attacks heavily rely on. This also lets us enhance attacks and defenses against them. Check out Matan Ben-Tov 's thread 👇

Check out Silin Gao 's paper done in collaboration with on reinforcing abstract thinking in #Reasoning traces!

We open-sourced the codebase of Flextok. Flextok is an image tokenizer that produces flexible-length token sequences and represents image content in a compressed coarse-to-fine way. Like in PCA: the 1st token captures the most compressed representation of the image, the 2nd

We benchmarked leading multimodal foundation models (GPT-4o, Claude 3.5 Sonnet, Gemini, Llama, etc.) on standard computer vision tasks—from segmentation to surface normal estimation—using standard datasets like COCO and ImageNet. These models have made remarkable progress;

Huge thanks to my incredible coauthors for making this possible 🙏 Ted Sumers, Badr AlKhamissi, @abosselut, Griffiths Computational Cognitive Science Lab Check out the updated paper here: arxiv.org/abs/2410.05563

🗒️Can we meta-learn test-time learning to solve long-context reasoning? Our latest work, PERK, learns to encode long contexts through gradient updates to a memory scratchpad at test time, achieving long-context reasoning robust to complexity and length extrapolation while

🚀 Big time! We can finally do LLM RL fine-tuning with rewards and leverage offline/off-policy data! ❌ You want rewards, but GRPO only works online? ❌ You want offline, but DPO is limited to preferences? ✅ QRPO can do both! 🧵Here's how we do it: