Wish Suharitdamrong

Phd in AI at University of Surrey

[Wish Suharitdamrong @peterwisu]

@benno_krojer Great work, looking forward to have a chat with you at the conf

[Wish Suharitdamrong @peterwisu]

@tan51616 Sure!

[Wish Suharitdamrong @peterwisu]

While I’m in Seoul for #ICML2026, where’s the best place to watch World Cup matches? ⚽ Any local tips appreciated! 🙏

[Wish Suharitdamrong @peterwisu]

Heading to Seoul for #ICML2026! 🇰🇷

I’ll be presenting CoLA, our work on cross-modal low-rank adaptation 🎧👁️📝

Paper : https://t.co/EF84l9R6Bp

Working on MLLMs for audio & vision? Let’s grab coffee and chat! ☕

[Gabriele Berton @gabriberton]

4 personal thoughts about AI

1) AI/DL/LLMs have nothing in common with the brain. Deep Learning is based on backprop, the brain isn't

2) Anything with backprop is a dead end for understanding the brain. Don't let "brain-inspired" works like JEPA / HRM fool you [1/2]

[Dr. Theophano Mitsa ☦️🇬🇷🇺🇸 @theomitsa]

Move over Plato. Aristotle is better for LLMs.
https://t.co/PnHsNmjqn7

[Sasha Malysheva @aimalysheva]

New ICML 2026 paper challenges the Platonic Representation Hypothesis: model width and depth mechanically inflate similarity scores, creating a misleading global convergence trend which disappears after that bias correction.

What survives is local neighborhood alignment across image, text, and video models (similar things stay near each other even across very different architectures). They call it the Aristotelian Representation Hypothesis :)

So while two models may not share the same representation space in any strong global sense, they can still agree on local neighborhoods (what is similar to what). That is probably the part we actually use in retrieval, transfer, and multimodal systems, and which could be transferred between learned approximations of different models.

https://t.co/sNU3eRtmHd

[Paul Gavrikov @PaulGavrikov]

Made me laugh way to hard #CVPR2026

[Wish Suharitdamrong @peterwisu]

@j_dekoninck What about reproducibility of the result?

[Wish Suharitdamrong @peterwisu]

@leon_chlon @icmlconf Hope you having good time in Thailand

[Hanchen Li @lihanc02]

Best Poster Award at ICLR 2026?

Come to Pavilion 3 #708 to find out! 😃
Mamba 3 is just on the opposite side btw.

[Han Xiao ✈️ ICML 2026 @hxiao]

bro goes casual mode at ICLR

[Yann LeCun @ylecun]

Dario is wrong.
He knows absolutely nothing about the effects of technological revolutions on the labor market.
Don't listen to him, Sam, Yoshua, Geoff, or me on this topic.
Listen to economists who have spent their career studying this, like @Ph_Aghion , @erikbryn , @DAcemogluMIT , @amcafee , @davidautor

[Khaosod English @KhaosodEnglish]

“When you crash the car and are too scared to go home because of your dad… Strait of Hormuz.”

An X account of the Iranian Embassy in South Africa posted a photo showing Thai crew members from the cargo ship Mayuree Naree evacuating after the vessel was attacked near the Strait of Hormuz, accompanied by the caption: “When you crash the car and are too scared to go home because of your dad… Strait of Hormuz.”

The post has drawn widespread criticism from Thai netizens, many of whom said the message was inappropriate and appeared to mock the situation.

[Andrew Ng @AndrewYNg]

Releasing a new "Agentic Reviewer" for research papers. I started coding this as a weekend project, and @jyx_su made it much better.

I was inspired by a student who had a paper rejected 6 times over 3 years. Their feedback loop -- waiting ~6 months for feedback each time -- was painfully slow. We wanted to see if an agentic workflow can help researchers iterate faster.

When we trained the system on ICLR 2025 reviews and measured Spearman correlation (higher is better) on the test set:
- Correlation between two human reviewers: 0.41
- Correlation between AI and a human reviewer: 0.42

This suggests agentic reviewing is approaching human-level performance.

The agent grounds its feedback by searching arXiv, so it works best in fields like AI where research is freely published there. It’s an experimental tool, but I hope it helps you with your research.

Check it out here: https://t.co/n7ctnDilJJ

[Ahmad Beirami ✈️ ICML @abeirami]

Woke up to this email this morning

- Wow, I won a NeurIPS award?!
- …runner-up, but I’ll take it.
- Wait, I didn’t submit a paper.
- Ah, I’m chairing the session and I’m supposed to give the award.

Huge congratulations to the actual winners and runners-up!

[Wish Suharitdamrong @peterwisu]

@tan51616 Same thing happend to my paper, I submitted rebuttal 1 day before they disable review response🥲.

[Jeffrey Li 💙💛 @askerlee]

@nathan_w_henry What the hell is going on

[Lei Yang @diyerxx]

Got burned by an Apple ICLR paper — it was withdrawn after my Public Comment.

So here’s what happened. Earlier this month, a colleague shared an Apple paper on arXiv with me — it was also under review for ICLR 2026.
The benchmark they proposed was perfectly aligned with a project we’re working on.

I got excited after reading it. I immediately stopped my current tasks and started adapting our model to their benchmark.
Pulled a whole weekend crunch session to finish the integration… only to find our model scoring absurdly low.

I was really frustrated. I spent days debugging, checking everything — maybe I used it wrong, maybe there was a hidden bug.
During this process, I actually found a critical bug in their official code:

* When querying the VLM, it only passed in the image path string, not the image content itself.

The most ridiculous part? After I fixed their bug, the model's scores got even lower!

The results were so counterintuitive that I felt forced to do deeper validation. After multiple checks, the conclusion held: fixing the bug actually made the scores worse.

At this point I decided to manually inspect the data. I sampled the first 20 questions our model got wrong, and I was shocked:

* 6 out of 20 had clear GT errors.
* The pattern suggested the “ground truth” was model-generated with extremely poor quality control, leading to tons of hallucinations.
* Based on this quick sample, the GT error rate could be as high as 30%.

I reported the data quality issue in a GitHub issue. After 6 days, the authors replied briefly and then immediately closed the issue.
That annoyed me — I’d already wasted a ton of time, and I didn’t want others in the community to fall into the same trap — so I pushed back. Only then did they reopen the GitHub issue.

Then I went back and checked the examples displayed in the paper itself.
Even there, I found at least three clear GT errors.

It’s hard to believe the authors were unaware of how bad the dataset quality was, especially when the paper claims all samples were reviewed by annotators. Yet even the examples printed in the paper contain blatant hallucinations and mistakes.

When the ICLR reviews came out, I checked the five reviews for this paper.
Not a single reviewer noticed the GT quality issues or the hallucinations in the paper's examples.

So I started preparing a more detailed GT error analysis and wrote a Public Comment on OpenReview to inform the reviewers and the community about the data quality problems.

The next day — the authors withdrew the paper and took down the GitHub repo.

Fortunately, ICLR is an open conference with Public Comment. If this had been a closed-review venue, this kind of shoddy work would have been much harder to expose.

So here’s a small call to the community:
For any paper involving model-assisted dataset construction, reviewers should spend a few minutes checking a few samples manually. We need to prevent irresponsible work from slipping through and misleading everyone.

Looking back, I should have suspected the dataset earlier based on two red flags:

* The paper’s experiments claimed that GPT-5 has been surpassed by a bunch of small open-source models.
* The original code, with a ridiculous bug, produced higher scores than the bug-fixed version.

But because it was a paper from Big Tech, I subconsciously trusted the integrity and quality, which prevented me from spotting the problem sooner.

This whole experience drained a lot of my time, energy, and emotion — especially because accusing others of bad data requires extra caution.
I’m sharing this in hopes that the ML community remains vigilant and pushes back against this kind of sloppy, low-quality, and irresponsible behavior before it misleads people and wastes collective effort.

#ICLR #ICLR2026 #NeurIPS #CVPR #openreview #MachineLearning #LLM #VLM