![Mohammad Hossein Rohban Profile](https://pbs.twimg.com/profile_images/806951430397509633/ol0_n4aB_x96.jpg)
Mohammad Hossein Rohban
@MhRohban
Followers
1K
Following
2K
Statuses
508
Associate Professor in Computer Science @ Sharif University of Technology
Joined March 2013
We are honored to host Prof. Sutton in this week Wednesday at Sharif. Please sign up if you’re interested:
This week, we have the honor of hosting Richard Sutton as our guest speaker. Thank you @RichardSSutton.
0
5
59
RT @TrackingActions: 🔥🙏🏼 #AROS 💍 is accepted to #ICLR2025 @iclr_conf ! So proud of @hsirm96 - what an awesome way to kick off his first gr…
0
5
0
Looking forward to see insightful work submitted to this workshop.
🚨 Workshop on Spurious Correlation & Shortcut Learning at ICLR 2025! 📝 Submission Deadline: 10 February (AoE) 🔗 Submit here: Tracks: - Regular: Up to 6 pages (excl. appendix & refs) - Tiny: 3 pages More details: #ICLR2025
0
5
49
RT @MahdiGhaznavi78: 🎉 The holidays are over—get ready to share your groundbreaking research! 🚨 Submit to the SCSL Workshop: 1️⃣ New spuri…
0
6
0
@yassersouri I agree this has been repeated in the last two decades, but I meant this for foundation models and solving the benchmark in a *single* round and in a short time period.
0
0
1
Referring to this:
Important words from @fchollet: “it is important to note that ARC-AGI is not an acid test for AGI – as we've repeated dozens of times this year. It's a research tool designed to focus attention on the most challenging unsolved problems in AI, a role it has fulfilled well over the past five years. Passing ARC-AGI does not equate to achieving AGI, and, as a matter of fact, I don't think o3 is AGI yet. o3 still fails on some very easy tasks, indicating fundamental differences with human intelligence. Furthermore, early data points suggest that the upcoming ARC-AGI-2 benchmark will still pose a significant challenge to o3, potentially reducing its score to under 30% even at high compute (while a smart human would still be able to score over 95% with no training)”
0
0
2
RT @DavidSKrueger: Looking forward to speaking at this workshop on Spurious Correlationa and Shortcut Learning at ICLR 2025! I was very in…
0
4
0
and to the organizers @MahdiGhaznavi78, @HesamAsdz, @polkirichenko, @MSoleymanib, @paahrsa, @aahladpuli, @Arash_M_O, @ShikaiQiu, @nahalmirzaie. 6/
0
0
10
RT @_philschmid: How we implemented test-time computing for open models to solve complex math problems like @OpenAI o1. 👀 Test-time compu…
0
72
0