Chris Samarinas
@CSamarinas
CS PhD at CIIR @manningcics, founder of @NagetInc. Researcher in NLP & Information Retrieval. Search, nuggets, search.
You might like
📢 New paper on scaling test-time compute for document re-ranking Do you want to know how to train compact 2-3B models that can reach the performance of 70B+ LLMs in reasoning-intensive ranking? 📄Check out the distillation + RL recipe in our paper: arxiv.org/abs/2504.03947
🤖➡️📉 Post-training made LLMs better at chat and reasoning—but worse at distributional alignment, diversity, and sometimes even steering(!) We measure this with our new resource (Spectrum Suite) and introduce Spectrum Tuning (method) to bring them back into our models! 🌈 1/🧵
Excited to release new repo: nanochat! (it's among the most unhinged I've written). Unlike my earlier similar repo nanoGPT which only covered pretraining, nanochat is a minimal, from scratch, full-stack training/inference pipeline of a simple ChatGPT clone in a single,…
This paper is one of the most interesting works in IR the last 5+ years.
Instructions/reasoning are now everywhere in retrieval - we want embeddings to do it all! 🚀 But... is it even possible? 🤔 Turns out, it's not possible for single-vector models 😱 theoretically and empirically! To make it obvious we OSS a simple eval SoTA models flop on! 🧵
I'm sick of glorified API wrappers and Chromium reskins. If you want an early glimpse into agentic browser use, check out and contribute to the open-source nanobrowser Chrome extension: github.com/nanobrowser/na…
comet invites demand gives me the early gmail launch vibes. what an incredible product it was and comet is still not in the same leagues but feels special to have the company build something people really want.
I’ll present our full paper "Bridging the Gap: From Ad-hoc to Proactive Search in Conversations" tomorrow (16 July) at @SIGIRConf #SIGIR2025, in the Conversational IR and Intelligent Agents session, MANTEGNA Platea, Floor 1, 10:30–12:30. Paper: dl.acm.org/doi/10.1145/37…
🔥
🚀 Introducing DeepSeek-V3! Biggest leap forward yet: ⚡ 60 tokens/second (3x faster than V2!) 💪 Enhanced capabilities 🛠 API compatibility intact 🌍 Fully open-source models & papers 🐋 1/n
Come to SIGIR Session M3.2: Conversational IR and Recommendation to hear from @CSamarinas about proactive conversational search! #SIGIR2024
Join me for my presentations at #SIGIR2024 M3.1 RAG session July 15 4pm 1. Towards a Search Engine for Machines: Unified Ranking for Multiple Retrieval-Augmented Large Language Models 2. Optimization Methods for Personalizing Large Language Models through Retrieval Augmentation
If you are attending #SIGIR2024, come to our (@snbruch, @cosimorulli1, @rventurini_) talk in M1.3 on Seismic (efficient approx. sparse retrieval)! @snbruch drafted a nice blog post to describe the algorithm, w/ plenty of context: bruch.io/blog/publicati…
Today, I'll be presenting our #SIGIR2024 paper titled "Ranked List Truncation for Large Language Model-based Re-Ranking" at Session Efficiency for Search (M1.3), which starts at 10:30 am, in Room Federal A. @SIGIRConf Paper: dl.acm.org/doi/10.1145/36… Code: github.com/ChuanMeng/RLT4…
I'm at #SIGIR2024 this week-- very excited to be giving a talk about our long context work at LLMs Day (Tuesday @ 12:15 in the Presidential Ballroom)! And I would love to chat with folks interested in long context, attention mechanisms, or IR perspectives on RAG :)
Amazing to see a conference paper search tool that goes beyond text similarity. Check it out: sigir.naget.com #SIGIR2024
This Monday I'm presenting 'ProCIS: A benchmark for proactive retrieval in conversations' at the #SIGIR2024 session M3.2 Conversational IR and Rec. Let's chat about the future of search engines afterward 💬
Check out our first instruction-based search demo focused on #SIGIR2024. Web-scale release and more coming soon: sigir.naget.com
Excited to release our instruction-based search demo for #SIGIR2024 at sigir.naget.com! 🚀 At Naget, we're building a personal discovery engine to transform online content interaction. Stay tuned for our web-scale release and conversational interface!
United States Trends
- 1. Bama 11.4K posts
- 2. Ty Simpson 2,601 posts
- 3. South Carolina 32.5K posts
- 4. #UFC322 26.9K posts
- 5. Iowa 17.9K posts
- 6. #EubankBenn2 28.7K posts
- 7. Mateer 2,717 posts
- 8. Oklahoma 19.8K posts
- 9. Arbuckle N/A
- 10. Texas A&M 31.9K posts
- 11. Susurkaev 2,174 posts
- 12. Beamer 9,252 posts
- 13. Ryan Williams 1,538 posts
- 14. Talty 1,024 posts
- 15. #FightOn N/A
- 16. Camilo 8,667 posts
- 17. Heisman 9,434 posts
- 18. Georgia Tech 2,256 posts
- 19. Makai Lemon N/A
- 20. #Sooners 1,684 posts
You might like
-
Negar Arabzadeh @CIKM
@NegarEmpr -
Hansi Zeng
@HansiZeng -
Mikel Artetxe
@artetxem -
SIGIR-AP 2025
@ACMSIGIR_AP -
Qingyao Ai
@QingyaoAi -
EMNLP 2025
@emnlpmeeting -
Naomi Saphra
@nsaphra -
Shuo Zhang
@imsure318 -
JHU CLSP
@jhuclsp -
Xi Wang @CIKM2025
@wangxieric -
Jina AI
@JinaAI_ -
Minqian Liu
@minqian_liu -
Luke Zettlemoyer
@LukeZettlemoyer -
Amin Bigdeli
@amin_bigdelii
Something went wrong.
Something went wrong.