António Góis

77 posts

António Góis

@AntGois

PhD student @Mila_Quebec; Interested in performative prediction, causality, evolution of cooperation,NLProc; prev @deep_spin @Unbabel HotClubeJazz @istecnico

Katılım Haziran 2013

511 Takip Edilen406 Takipçiler

António Góis retweetledi

Jose Gallego-Posada@JGallegoPosada·2 Tem

Meet Cooper — a PyTorch library for constrained optimization in deep learning. 🚀 Cooper makes constraints as easy to use as losses! @juan43ramirez @meraj_hashemi_ @SimonLacosteJ @Mila_Quebec 💻github.com/cooper-org/coo… 🧵👇

English

1.8K

António Góis retweetledi

Krikamol (Hiring Postdoc)@krikamol·20 May

🥳 Just managed to finish the first draft of this work after almost four years of work 😅 (Im)possibility of Collective Intelligence arxiv.org/abs/2206.02786 Any feedback is highly appreciated 🙏

English

164

9.4K

António Góis@AntGois·4 May

Check our poster tomorrow 3-6pm! @aistats_conf

Simon Lacoste-Julien@SimonLacosteJ

Check out this first paper on performative prediction with collective games at #AISTATS2025!

English

182

António Góis retweetledi

Juan Ramirez@juan43ramirez·3 May

Interested in NNs with improved tail performance? Our #AISTATS2025 paper introduces Feasible Learning, a sample-centric learning paradigm that bounds per-sample losses! @nachohounie @juaaan_e @JGallegoPosada @meraj_hashemi_ A. Ribeiro @SimonLacosteJ arxiv.org/abs/2501.14912 🧵

English

António Góis retweetledi

ELLIS Unit Lisbon@Lisbon_ELLIS·28 Nis

🚨Today is the last day to apply to the Lisbon Machine Learning School! Hear from top speakers in the field and get to meet new people during a fantastic week in Lisbon. ‼️Apply today: tinyurl.com/mre5as8f

ELLIS Unit Lisbon@Lisbon_ELLIS

📢 Applications to the 15th Lisbon Machine Learning School 2025 are open! Covering #ML topics such as neural networks, transformers, causality, vision & language. 📅 Dates: 19th - 25th of July 🔗 more info: lxmls.it.pt/2025/index.html 🔗 apply here: tinyurl.com/mre5as8f

English

419

António Góis@AntGois·27 Nis

Thank you to the HAIC organizers @iclr_conf ! Very friendly environment and interesting discussions today @Mila_Quebec

António Góis@AntGois

Happy to announce "Performative Prediction on Games and Mechanism Design" was accepted at @aistats_conf 2025, and got spotlight at HAIC(@iclr_conf workshop) with @mhrnz_m @fernandopsantos @gauthier_gidel @SimonLacosteJ (Mila and UvA) arxiv.org/abs/2408.05146 Details below 1/9🧵

English

1.5K

António Góis@AntGois·26 Nis

Tomorrow Sunday, 14h45! At @iclr_conf 2025 Workshop on Human-AI Coevolution (HAIC) @Mila_Quebec

António Góis@AntGois

English

233

António Góis retweetledi

Milad Aghajohari@MAghajohari·25 Nis

Multi-Agent RL fails in real life. Agents cooperating to solve tasks remains a utopia. -No scalable algorithms for general-sum games. -In a simple apple-harvesting game, PPO agents overharvest and ruin bushes. Advantage Alignment (ICLR 2025 Oral📢) is a huge step forward. 1/n

English

8.8K

António Góis@AntGois·12 Nis

Feel free to reach out to chat about this work — either online or in-person at @iclr_conf and @aistats_conf 9/9🧵

English

121

António Góis@AntGois·12 Nis

This connects to open questions in 𝗽𝗵𝗶𝗹𝗼𝘀𝗼𝗽𝗵𝘆 with practical relevance — how to evaluate performative models? Aiming for prosocial outcomes (appraisal view) undesirably injects moral values, endogenizing causes of adaptation (mitigation view) has side effects 8/9🧵

English

116

António Góis@AntGois·12 Nis