@riedelcastro

Researcher in NLP/ML @deepmind, @ucl_nlp, @riedelcastro@sigmoid.social on Mastodon

 London, England
riedelcastro.org/
Joined September 2009
  • Tweets1.9K
  • Following453
  • Followers16.2K
33Media
Interested in language, knowledge and reasoning? Come to work with me and others at @DeepMind and its language group as a research scientist! Apply here: boards.greenhouse.io/deepmin…
4
45
2
257
🚨 New Paper 🧵 How effectively do reasoning models reevaluate their thought? We find that: - Models excel at identifying unhelpful thoughts but struggle to recover from them - Smaller models can be more robust - Self-reevaluation ability is far from true meta-cognitive awareness
3
28
3
129
10,425
Want to build on the new @Google Multimodal Live API with Gemini 2.0? My teammates @hapticdata + @tinaz0ne + @trudypainter made open-source starter demos! 🧵 Here's a React.js boilerplate console you can start with. Code here: github.com/google-gemini/mul…
2
19
5
123
25,062
The Gemini 2.0 era begins with 2.0 Flash Experimental release ⚡️ 📈2.0 Flash beats 1.5 Pro across factuality, reasoning, coding, math. 📳 More modalities - image and audio out (in EAP) 🔧 Native tool use for Google Search, code execution and 3P functions 🆕 a new multimodal, realtime API experience 🎬 3 new cool starter apps - spatial understanding, video analyzer and map explorer
Google AI Developers
@googleaidevs11 Dec 2024
We just released Gemini 2.0 Flash Experimental ⚡ Available in the Gemini API and Google AI Studio for testing, it allows developers to build interactive experiences with better performance and multimodal capabilities. goo.gle/3BriaXd

Google for Developers Blog - News about Web, Mobile, AI and Cloud

developers.googleblog.com
6
14
181
13,832
I am hiring for RS/RE positions! If you are interested in language-flavored multimodal learning, evaluation, or post-training apply here 🦎 boards.greenhouse.io/deepmin… I will also be #NeurIPS2024 so come say hi! (Please email me to find time to chat)
4
41
4
209
61,214
Sohee (@soheeyang_) in the house! 🚀🚀🚀🚀
6
24
2,056
It's paper review day (every day) - since I discovered that DeepMind already knows everything let's look at their latest Paper arxiv.org/pdf/2411.16679
Lisan al Gaib
@scaling0129 Nov 2024
Replying to @scaling01
bro how is it always DeepMind I might just need to go through all DeepMind papers chronologically to build AGI
5
37
3
615
113,427
🚨 New Paper 🚨 Can LLMs perform latent multi-hop reasoning without exploiting shortcuts? We find the answer is yes – they can recall and compose facts not seen together in training or guessing the answer, but success greatly depends on the type of the bridge entity (80%+ for country, 6% for year)! 1/N
7
51
8
205
47,490
Frontier models can do this stuff, but also not! Opinions differ on how much we even want this (CC @geoffreyirving), but understanding the patterns will be critical regardless. Been a pleasure to work with Latent Reasoning Dream Team @soheeyang_ @megamor2 @KassnerNora!
Sohee Yang@soheeyang_27 Nov 2024
🚨 New Paper 🚨 Can LLMs perform latent multi-hop reasoning without exploiting shortcuts? We find the answer is yes – they can recall and compose facts not seen together in training or guessing the answer, but success greatly depends on the type of the bridge entity (80%+ for country, 6% for year)! 1/N
7
29
7,253
The team @jhamrick and I co-lead is hiring a research engineer. If you are interested in improving the capabilities of LLMs in the planning and reasoning space, and building generally capable agents, please apply! boards.greenhouse.io/deepmin…
1
13
57
7,362
Excited to share our prompt tuning playbook! (Not an official product. Just authors tips & tricks for better prompting). I'm most excited about first half on mental models for post-training & prompting. Feedback/forks welcome! #LLM #PromptEngineering github.com/varungodbole/prom…
13
127
20
595
116,711
I am hiring for a research engineering role in NYC, focused on Gemini post training. If you are interested, please apply here. Deadline is just in two weeks. boards.greenhouse.io/deepmin…
4
57
4
365
68,496
I am looking for a Research Scientist intern for 2025. If you have already published work that involves understanding behaviours of AI models looking at their parameters and activations, I would like to hear from you. metacareers.com/jobs/5560633…
5
46
318
45,128
Amazing progress @YuxiangJWu and @zhengyaojiang, and great to see the impact of "agent scaffolding" given a base model.
Weco AI
@WecoAI10 Oct 2024
Excited to see OpenAI's recent project, MLE-bench, is based on our open-source effort, AIDE. In their independent evaluation, AIDE surpasses other MLE agents by a large margin!
4
15
3,907
We are launching Design Your Own Avatar (DYOA)! With our latest innovations in multimodal generation at @Creatify_AI , you can now create ultra realistic AI avatars from text description and bring it to life! This unblocks a whole new level of possibilities. Check it out: buff.ly/4dsvt6x
Creatify AI
@Creatify_AI27 Sep 2024
THE FUTURE IS HERE! For the first time ever, you can now create your own 100% AI avatar from scratch. Simply describe your ideal representative, from their appearance to their surroundings, and our technology will bring your vision to life! Available now at: buff.ly/4dsvt6x (examples in thread) [No real people were filmed in the making of this video.]
8
5
31
9,381
🚨NEW BENCHMARK🚨 Are LLMs good at linguistic reasoning if we minimize the chance of prior language memorization? We introduce Linguini🍝, a benchmark for linguistic reasoning in which SOTA models perform below 25%. w/ @b_alastruey, @artetxem, @costajussamarta et al. 🧵(1/n)
https://arxiv.org/pdf/2409.12126

ALT https://arxiv.org/pdf/2409.12126

3
21
4
115
22,788
The popular science series 10 Things You Should Know by @SevenDialsBooks @orionbooks has a new member: Artificial Intelligence! Out September 26th. You can pre-order it at geni.us/ArtificialIntelligen…
7
12
2
92
13,828
Super proud to have been able to work with you @PSH_Lewis! Does this improve my Bacon number?
Sebastian Riedel (@[email protected])@riedelcastro6 Sep 2024
Replying to @PSH_Lewis
@PSH_Lewis
1
16
3,415
I'll be presenting our TACL paper "Improving Probability-based Prompt Selection Through Unified Evaluation and Analysis" at #ACL2024! 📍 Oral: Mon 12:00 (Machine Learning for NLP I, World Ballroom B) 📍 Poster: Tue 16:00 (Conv. Center A1) Please drop by if you are interested!
Sohee Yang@soheeyang_24 May 2023
1/9 Excited to share "Improving Probability-based Prompt Selection Through Unified Evaluation and Analysis". We've performed a unified evaluation & analysis on probability-based prompt selection methods, increasing the effectiveness from 87.79% to 99.44%! soheeyang.github.io/publicat…
6
26
3,896
Our paper "Do Large Language Models Latently Perform Multi-Hop Reasoning?" will be presented at #ACL2024 today. 📍 Mon 14:00-15:30 Poster Session 2 (Conv. Center A1) Please visit our poster if you are interested, and catch me to chat about the latent reasoning ability of LLMs!
Sohee Yang@soheeyang_28 Feb 2024
🚨 New Paper 🚨 LLMs excel at storing facts & in-context reasoning like CoT. But do they latently💭 reason over their parametric knowledge without answering step-by-step? We found positive evidence 👀 But it varies for different relation types, and scaling doesn't help much! 1/N
2
14
104
13,438
Google presents Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More? Long-context LM: - Often rivals SotA retrieval and RAG systems - But still struggles with areas like compositional reasoning repo: github.com/google-deepmind/l… abs: arxiv.org/abs/2406.13121
3
81
4
323
33,060
Load more