ΑΙhub.org
 

#ICML2025 social media round-up 1


by
16 July 2025



share this:
ICML logo

The 42nd International Conference on Machine Learning (ICML2025) is currently taking place in Vancouver, Canada, running from 13-19 July. As well as five invited talks, the programme boasts oral and poster presentations, affinity events, tutorials, and workshops. Find out what participants have been getting up to during the first couple of days.

✈️ Traveling to #ICML2025. Presenting our paper: Quantifying Prediction Consistency Under Fine-Tuning Multiplicity in Tabular LLMs #TabularLLM #Uncertainty #PredictionConsistency #Robustness
🕟 Wed 16 Jul 4:30 p.m. PDT — 7 p.m. PDT
➡️ East Exhibition Hall A-B E-901
🔗https://arxiv.org/abs/2407.04173

[image or embed]

— Sanghamitra Dutta (@sanghamd.bsky.social) 12 July 2025 at 19:29

On my way to #ICML2025 to present our algorithm that strongly scales with inference compute, in both performance and sample diversity! 🚀

Reach out if you’d like to chat more!

[image or embed]

— Aditi Mavalankar (@aditimavalankar.bsky.social) 13 July 2025 at 13:26

Our ✨spotlight paper✨ "Primal-Dual Neural Algorithmic Reasoning" is coming to #ICML2025!

We bring Neural Algorithmic Reasoning (NAR) to the NP-hard frontier 💥

🗓 Poster session: Tuesday 11:00–13:30
📍 East Exhibition Hall A-B, # E-3003
🔗 openreview.net/pdf?id=iBpkz…

🧵

[image or embed]

— Yu He (@dransyhe.bsky.social) 13 July 2025 at 22:34

🍁Greetings from ICML 2025 in Vancouver!

I'm excited to present our paper: “Adaptive Sample Sharing for Multi-Agent Linear Bandits” Hamza Cherkaoui, Merwan Barlier, Igor Colin
📄 Paper: openreview.net/forum?id=qQB…
💻 Code: github.com/hcherkaoui/c…
#ICML2025 #MachineLearning #Bandits #AI

[image or embed]

— Hamza Cherkaoui (@hamzacherkaoui.bsky.social) 14 July 2025 at 12:15

Re-upping this post for any just landing at #ICML2025!

Some tips on how to make friends and socialize with other researchers at a conference

[image or embed]

— Gautam Kamath (@gautamkamath.com) 14 July 2025 at 16:24

Excited to be chatting about our new paper "Understanding Fixed Predictions via Confined Regions" (joint work with @berkustun.bsky.social, Lily Weng, and Madeleine Udell) at #ICML2025!

🕐 Wed 16 Jul 4:30 p.m. PDT — 7 p.m. PDT
📍East Exhibition Hall A-B #E-1104
🔗 arxiv.org/abs/2502.16380

[image or embed]

— Connor Lawless (@lawlessopt.bsky.social) 14 July 2025 at 17:08

Can diffusion models solve visual Sudoku?

If you are at #ICML2025, come to our poster in the Wednesday morning poster session (Poster Session 3 East, Poster 3412) and find out!

@chriswewer.bsky.social

[image or embed]

— Jan Eric Lenssen (@janericlenssen.bsky.social) 14 July 2025 at 21:41

#ICML2025 Stats

[image or embed]

— Kosta Derpanis (@csprofkgd.bsky.social) 15 July 2025 at 03:04

Second Panel at WiML @ #ICML2025!

The Unsolved Problems of AI: What We’re Still Getting Wrong. Join Ana Lucic, Been Kim, Furong Huang & Meg Risdal as they share what’s missing, what’s broken, and what still needs to change in AI, with Natasha Jaques as moderator.

#WiML

[image or embed]

— Women in Machine Learning (WiML) (@wimlworkshop.bsky.social) 14 July 2025 at 23:29

First #runconference was great! Come by tomorrow at same time (7am) for another great run!
#icml2025

[image or embed]

— Pablo Samuel Castro (@pcastr.bsky.social) 16 July 2025 at 04:45



tags: , ,


Lucy Smith is Senior Managing Editor for AIhub.
Lucy Smith is Senior Managing Editor for AIhub.




            AIhub is supported by:



Related posts :



New AI technique sounding out audio deepfakes

  21 Nov 2025
Researchers discover a smarter way to detect audio deepfakes that is more accurate and adaptable to keep pace with evolving threats.

Learning robust controllers that work across many partially observable environments

  20 Nov 2025
Exploring designing controllers that perform reliably even when the environment may not be precisely known.

ACM SIGAI Autonomous Agents Award 2026 open for nominations

  19 Nov 2025
Nominations are solicited for the 2026 ACM SIGAI Autonomous Agents Research Award.

Interview with Mario Mirabile: trust in multi-agent systems

  18 Nov 2025
We meet ECAI Doctoral Consortium participant, Mario, to find out more about his research.

Review of “Exploring metaphors of AI: visualisations, narratives and perception”

and   17 Nov 2025
A curated research session at the Hype Studies Conference, “(Don’t) Believe the Hype?!” 10-12 September 2025, Barcelona.

Designing value-aligned autonomous vehicles: from moral dilemmas to conflict-sensitive design

  13 Nov 2025
Autonomous systems increasingly face value-laden choices. This blog post introduces the idea of designing “conflict-sensitive” autonomous traffic agents that explicitly recognise, reason about, and act upon competing ethical, legal, and social values.

Learning from failure to tackle extremely hard problems

  12 Nov 2025
This blog post is based on the work "BaNEL: Exploration posteriors for generative modeling using only negative rewards".



 

AIhub is supported by:






 












©2025.05 - Association for the Understanding of Artificial Intelligence