Twitter Beğeni Hilesi

One aspect of AI development that I've come to deeply appreciate is the importance of having reliable evals when building models. This may seem obvious, but the nuances and challenges in creating evals are often underappreciated. The quality of your evals directly impacts your

We introduce Situated Instruction Following (SIF), to appear in ECCV 2024! There is inherent underspecification in instructions when humans act as they speak. SIF is addresses these dynamic, temporally evolving intent of instructions in the context of physical human actions.(1/7)

#ICML2024 #ICML Our new work provides a highly effective and scalable method for enriching deep neural networks to decide whether it has sufficient evidence for reaching a reliable prediction. Paper 📒 : huggingface.co/papers/2406.10… Code 💻: github.com/ifiaposto/Dist… Poster 📸:

How to Map 🗺️ It Anywhere? mapitanywhere.github.io The trick is to flip the script from using principally limited self-collected datasets to using readily available worldwide maps. Head over to our website to generate your own data or see our FPV Mapper in action! 🧵👇 1/n

Due to a series of lucky 7s 🎰 in terms of co-authors, I'll be co-presenting 8 papers at #ICML2024 this year: 4 at the main conference, 4 at the workshops! Please DM if you'd like to talk imitation / inverse RL, RLHF, causal RL, or just give me an excuse for an extra pastry!

#ICML2024 : tomorrow, Thurs 25, 1:30pm, presenting CARTE, our breakthrough toward tabular foundation models Poster 507 figshare.com/articles/poste…

📢Call for Papers: The First NeurIPS Workshop on Time Series in the Age of Large Models📢 We invite submissions to our workshop on "Time Series in the Age of Large Models" at NeurIPS 2024. Further details can be found at neurips-time-series-workshop.github.io. Please help us spread the word!

🎉 Excited to share our preprint: "ECG-FM: An Open Electrocardiogram Foundation Model"! ECG-FM is a transformer-based model, one of the pioneering open foundation models for ECG analysis. The electrocardiogram (ECG) is a widely used, cost-effective diagnostic test with great

More training data isn’t always better! We (joint work w.Deb Raji and Irene Chen) will present our new work: The Data Addition Dilemma, at MLHC 2024 this week! (1/5)

📢 Call For Papers: The First NeurIPS Workshop on Time Series in the Age of Large Models 📢 We invite submissions to the workshop on Time Series in the Age of Large Models @ NeurIPS 2024 in Vancouver, Canada. Less than a month until the deadline. Help us spread the word! 🔊

Part 2 of our panel on time series foundation models is out now! We share our thoughts on the future of time series FMs. 📉📈 What are your thoughts?

Part 2 IIF podcast Forecasting Impact latest "Panel on Foundational Models". Our hosts Mariana Menchero and Faranak Golestaneh, explore foundation models for time series forecasting with azul (she/her) w/nixtla and Mononito Goswami forecasters.org/publications/f… Laurent Ferrara Mahdi Abolghasemi

Can a single neural network policy generalize over poses, objects, obstacles, backgrounds, scene arrangements, in-hand objects, and start/goal states? Introducing Neural MP: A generalist policy for solving motion planning tasks in the real world 🤖 1/N

We just released a PyTorch version of the original timesfm-1.0 model (huggingface.co/google/timesfm…), with more details at github.com/google-researc…

If you're applying to CMU SCS PhD programs and come from a traditionally underrepresented group, current students are here to help! Apply to the Graduate Applicant Support Program (GASP) by Oct. 8, 2024 to receive feedback on your application materials: cs.cmu.edu/~gasp

India rarely if ever gets credit for its phenomenal effort in preserving biodiversity. Considering the million problems that we have it would have been easy to just drop the ball in this. But we didn’t. Hope to see cheetah rewilding succeed followed by more: ostrich, Hippos.