#emnlp2025 search results
I had a great #EMNLP2025 experience in Suzhou 🇨🇳! ✔️ (Main) Poster Presentation ✔️ (Wordplay Workshop) Outstanding Paper Award ✔️ (Wordplay Workshop) Keynote talk Thanks to my incredible collaborators and all people I had the pleasure of meeting ✨!
What an inspiring week at #EMNLP2025 in Suzhou🇨🇳! Huge thanks to the organizers and everyone who stopped by our poster/talk!
Come check out Agent Laboratory at #EMNLP2025! We will discuss how LLM Agents can help accelerate scientific discovery. I'll be presenting on Nov 5 @ 8:00. Looking forward to the discussions!
🧐Are values in LLMs aligned with humans? 1️⃣ And if they are — do LLMs stay honest to those values, or sometimes say one thing but act another? 2️⃣ ✨ We explore these questions in two papers presented at #EMNLP2025: 1️⃣ ValueCompass: hua-shen.org/assets/files/a… (WiNLP Workshop)…
🎉 Congratulations to all #EMNLP2025 award winners 🎉 Starting with the ✨Best Paper award ✨: "Infini-gram mini: Exact n-gram Search at the Internet Scale with FM-Index" by Hao Xu, Jiacheng Liu, Yejin Choi, Noah A. Smith, and Hannaneh Hajishirzi aclanthology.org/2025.emnlp-mai… 1/n
I also got another paper in #EMNLP2025 from my collaboration with @seacrowd_ai! We will present Entropy2Vec at #EMNLP2025 @mrl_workshop, a fully unsupervised, data-driven language representation construction method leveraging uncertainty between language interactions. (1/3)
I'm grateful to receive an Outstanding Reviewer Award at #EMNLP2025! The award also comes with free registration to a *ACL conference in the next year. I'm hopeful that incentives like this will greatly improve review quality 🙏
Continuing our IMO-gold journey, I’m delighted to share our #EMNLP2025 paper “Towards Robust Mathematical Reasoning”, which tells some of the key stories behind the success of our advanced Gemini #DeepThink at this year IMO. Finding the right north-star metrics was highly…
Very excited to share that an advanced version of Gemini Deep Think is the first to have achieved gold-medal level in the International Mathematical Olympiad! 🏆, solving five out of six problems perfectly, as verified by the IMO organizers! It’s been a wild run to lead this…
Heading home tired but very happy after a fantastic #EMNLP2025 (and some well-deserved vacation 😎). We were super busy presenting 5 papers! It was fantastic catching up with colleagues, exchanging ideas, and seeing all the amazing work in the #NLProc community! (1/6)
Ready for day 3 of #EMNLP2025 🎉🎉 I've been on the lookout for memorization, unlearning, interp, memory module papers & more, chat w me if these topics fascinate you too😻 Looking forward to more of Suzhou, the conf & my BlackboxNLP keynote Sunday 1.45PM! blackboxnlp.github.io/2025/
🚨 New Paper! 🚨 We want ~helpful~ LLMs, and RLHF-ing them with user preferences and reward models will get us there, right? WRONG! 🙅❌⛔️ Our #EMNLP2025 paper finds a major helpfulness-preferences gap: user/LLM judgments + agent simulations can totally miss what helps users
Finally taking a moment to post after #EMNLP2025 in Suzhou, China! Had a wonderful time presenting our TACL paper on using structured recombination to push LLMs toward more creative and diverse idea generation 🍳✨ What an amazing experience to conclude my PhD journey! :)
The Sahara AI crew has landed in Suzhou for #EMNLP2025! Visit us at Hall C3, Booth #5 to see why leading enterprises partner with us for high-quality data annotation and collection to power the next generation of AI systems.👋
Really cool work! Reliable AI reviewing is exactly what the community needs right now. Our recent #EMNLP2025 paper (arxiv.org/abs/2509.18658) explores quantifying uncertainty in LLM judges, which might be a good way to further enhance the system's reliability. 😀
What an inspiring week at #EMNLP2025 in Suzhou🇨🇳! Huge thanks to the organizers and everyone who stopped by our poster/talk!
#ProudMoment 🙌🏻 Four papers were presented at #EMNLP2025 in Suzhou, China 🇨🇳covering code-mixing, toxicity detection, content moderation, and multilingual model interpretability! ✨ Huge congrats to the teams! 🎉 Read more: lingo.iitgn.ac.in @cse_iitgn @iitgn #NLP #AI
Image search... without the images? 🤔Excited to share our new #RAIDO paper from @QMUL , "Vision-Free Retrieval," presented at #EMNLP2025! We challenge standard VLMs (like CLIP) by ditching the vision encoder. Read it here: zenodo.org/records/176000… #EMNLP2025 #RAIDOProject
With MCP, your agent has access to more tools. Great. But that doesn't mean it knows how to use those tools. Tool access ≠ Tool use ability That's why we created MCPEval (#EMNLP2025), a new framework for evaluating agent performance given access to any MCP servers. Links to…
📸Great to share a photo from #EMNLP2025 w/ Huteng Dai, Xueyang Huang, Emilio Villa Cueva @evllcv and to celebrate the incredible work of our #AI researchers. Get an overview of the papers presented by our faculty and students: cse.engin.umich.edu/stories/eighte…
New paper out at #EMNLP2025: CausalTalk, a benchmark combining causal detection, explicit/implicit classification, span extraction, and gist annotation inspired by fuzzy-trace theory in social psychology. Led by @_XH_Ding_ 📝 arxiv.org/abs/2509.16722 💾 github.com/xding2/CausalT…
Great summary of our recent work on LLM agent failure modes in pentesting presented in #EMNLP2025 As we found, success is less about the model architecture and more about the embodiment of functional capabilities. Thanks for the feature @AISecHub!
Evaluating Key Functional Properties of LLM Architectures in Penetration Testing LLM-based agents show strong potential in automating core penetration testing tasks such as reconnaissance and credential exploitation, but remain brittle on complex, multi-phase workflows. Common…
📜🎉 Congratulation on the Poster presentation by Piotr Przybyła, Attacking Misinformation Detection Using Adversarial Examples Generated by Language Models - Piotr Przybyła, Euan McGill, @h_saggion aclanthology.org/2025.emnlp-mai… at #EMNLP2025 @talnupf #NLProc #AI
📜🎉Congratulations to the @talnupf and UOL teams for the second position in the TSAR 2025 Shared Task on Automatic Text simplification! @h_saggion @idem_EU aclanthology.org/2025.tsar-1.16/ #TextSimplificarion #LLMs #EMNLP2025
At a time of increased focus on "government efficiency", this #EMNLP2025 accepted paper shows how LLMs can empower civil servants rather than replace them, keeping humans in the loop while reducing time spent on redundant and menial tasks. See more at reglab.stanford.edu!
Heading home tired but very happy after a fantastic #EMNLP2025 (and some well-deserved vacation 😎). We were super busy presenting 5 papers! It was fantastic catching up with colleagues, exchanging ideas, and seeing all the amazing work in the #NLProc community! (1/6)
Structural problem #EMNLP2025 #ai conferneces: We reward paper volume over durable science. Less leaderboard theatre. More reproducibility, real-world evals, and honest ablations.
Vibe: Restless and repetitive. #EMNLP2025 looked a lot like every other LLM conference. Lots of demos, fewer durable ideas.
I went to #EMNLP2025 . Here’s what actually mattered. Short version: smaller/faster models, better retrieval, less agent hype, and a field that needs a cleanup.
During #EMNLP2025 in Suzhou,China, @WebAgentLab hosted the first GUI Agent Night. and The event was fully packed, with nearly 200 people signing up in just two days. However, due to space limitations, only fewer than 100 could be accommodated. Researchers, founders, and…
Our computer scientists presented fascinating #NLP research at @emnlpmeeting last week—check out some of their work in this thread! 🧵 (1/7) #EMNLP2025
What an inspiring week at #EMNLP2025 in Suzhou🇨🇳! Huge thanks to the organizers and everyone who stopped by our poster/talk!
Heading home tired but very happy after a fantastic #EMNLP2025 (and some well-deserved vacation 😎). We were super busy presenting 5 papers! It was fantastic catching up with colleagues, exchanging ideas, and seeing all the amazing work in the #NLProc community! (1/6)
With MCP, your agent has access to more tools. Great. But that doesn't mean it knows how to use those tools. Tool access ≠ Tool use ability That's why we created MCPEval (#EMNLP2025), a new framework for evaluating agent performance given access to any MCP servers. Links to…
📜🎉Congratulations to the @talnupf and UOL teams for the second position in the TSAR 2025 Shared Task on Automatic Text simplification! @h_saggion @idem_EU aclanthology.org/2025.tsar-1.16/ #TextSimplificarion #LLMs #EMNLP2025
Something went wrong.
Something went wrong.
United States Trends
- 1. Araujo 85.7K posts
- 2. Ferran 49.8K posts
- 3. Chelsea 386K posts
- 4. Barca 150K posts
- 5. Rashford 19.5K posts
- 6. Barcelona 288K posts
- 7. Sonny Gray 8,332 posts
- 8. Rush Hour 4 14.7K posts
- 9. Kounde 21.3K posts
- 10. Godzilla 22.1K posts
- 11. #AskTems 3,253 posts
- 12. Cucurella 30.8K posts
- 13. #CHEBAR 7,725 posts
- 14. Enzo 41.2K posts
- 15. Happy Thanksgiving 22.3K posts
- 16. Flick 23.7K posts
- 17. Raising Arizona 1,227 posts
- 18. National Treasure 6,263 posts
- 19. Balde 7,474 posts
- 20. Chalobah 6,316 posts