Aswin RRV

376 posts

Aswin RRV banner
Aswin RRV

Aswin RRV

@aswinrrv

NLP Researcher @ASU Astrophile ✨ “Separatedness is an illusion. We were all part of the same Celestial Dust!” MSCS, Fall'23. 22' CS, CEG, Anna University.

Chennai, Tamilnadu, India Katılım Şubat 2022
179 Takip Edilen50 Takipçiler
Aswin RRV
Aswin RRV@aswinrrv·
I think, crowd-review system (like whats happening in twitter/X) is better than these conferences. Some issues I have seen: Reviewer Sabotage (Like internationally asking for orthogonal experiments in the last day of the rebuttal) Unresponsive ones Unjustified Rejections and so on and on
English
1
0
3
454
Xiuyu Li
Xiuyu Li@sheriyuo·
I’ve already seen dozens of papers just like 544 and 5444 get rejected, and I’m honestly confused. Feels like something’s off with the review process lately. 😕
Thibaut Vidal@vidalthi

Happy to announce that our paper was rejected as a spotlight (5/5/4) at #ICML2026. If the methodology was complex enough to confuse the metareviewer, perhaps it may still be of broader interest to you 🙂. Happy to discuss the work if you are into optimal counterfactual maps that permit explanations in milliseconds, or into the occasional ups and downs of academic publishing 🚣

English
4
0
51
10.3K
Prithviraj (Raj) Ammanabrolu
Prithviraj (Raj) Ammanabrolu@rajammanabrolu·
My lab and collaborators had 4 papers on everything from multi objective alignment, reasoning during mid training, multimodal synthetic data, and generating RL tasks accepted to #ICML2026! Come hang out with us in Seoul and we can talk about the exciting follow-ups!
English
2
2
36
2.3K
Azmine Wasi @ICML
Azmine Wasi @ICML@AzmineWasi·
@icmlconf ICML Position Paper decisions seems out, indirectly 👀 Public-release or In-person presentation...?
English
3
0
2
2.5K
Aswin RRV
Aswin RRV@aswinrrv·
@giffmana I think this is not something surprising right? Well, consider a mode collapsed RL model trained on math and you evaluate it on say Code task, you can see some style transfer happening.
English
0
0
0
1.3K
Xiuyu Li
Xiuyu Li@sheriyuo·
When you’re running RL experiments with verl Me: Damn, I can run GRPO and GSPO but not DAPO > Spent a day or two debugging with the infra guy, then realized upgrading vllm to 0.18.0 fixes it, but now my verl needs to be updated Me: Let the Code Agent handle the migration Agent: I spent an hour writing a bunch of garbage code for you Me: wtf, so I rewrote everything myself in an hour and finally got DAPO running > One day later Me: wtf, why does it only work for dense models, why is MoE broken again > xxxxx tons of error logs (random order from Ray) Me: feed it to DeepSeek -> DeepSeek edits -> ... -> ten turns later DeepSeek: you should downgrade vllm to 0.17.0 Me: f**k verl
English
7
0
78
6.6K
Aswin RRV retweetledi
Himanshu Gupta
Himanshu Gupta@himanshu_gup14·
Training giant Mixture-of-Experts (MoE) models from scratch is incredibly expensive. What if we could grow their capacity mid-training without increasing inference costs? Introducing Expert Upcycling! A new compute-efficient recipe for scaling MoEs that saves ~32% in GPU hours. 🚀👇 Full paper: huggingface.co/papers/2604.19… code here: github.com/amazon-science…
Himanshu Gupta tweet media
English
1
7
10
266
Aswin RRV retweetledi
TVK Party HQ
TVK Party HQ@TVKPartyHQ·
TVK Party HQ tweet mediaTVK Party HQ tweet media
ZXX
365
7.5K
18.7K
690.2K
λux
λux@novasarc01·
i am seeing that similar to mood swings researchers have policy swings (jumping from on-policy to off-policy and vice-versa). when training is unstable everyone becomes deeply on-policy. when rollouts get expensive everyone rediscovers off-policy like it is a forgotten religion/ancient sacred thing.
English
3
2
25
2.4K
Aswin RRV retweetledi
Andrei Tarkhov, PhD
Andrei Tarkhov, PhD@Andrei_Tarkhov·
A novel argument to do a PhD in 2026 is to expand the training set of AI models by a unique 100-pager. Before, only a few experts in the world would read it — now, every single model can do so & benefit from reusing it in unexpected contexts. It all happened so fast…
English
6
16
282
19.8K
Aswin RRV retweetledi
Rajinikanth
Rajinikanth@rajinikanth·
ஜனநாயகன் திரைப்படம் இணையத்தில் யாராலோ வெளியிடப்பட்டிருப்பது அதிர்ச்சியையும்,வேதனையையும் அளிக்கிறது. திரை அமைப்புகள் இதற்கு எதிராகக் குரல் எழுப்பி, அரசு இதைச் செய்தவர்களைக் கண்டுபிடித்து கடுமையான தண்டனை அளிக்க வேண்டும். இது போன்ற குற்றம் இனியும் தொடரக்கூடாது.
தமிழ்
1.7K
11.1K
55.3K
2.3M
Aswin RRV retweetledi
Kamal Haasan
Kamal Haasan@ikamalhaasan·
The leak of #Jananayagan is not an accident - it is the result of systemic failure. Had due process been timely, we would not be here. Inordinate delays in certification created fertile ground for piracy. When legal access is stalled, illegitimate channels take over. Piracy is beyond politics; it is an attack on the art and artist itself. It endangers the work of hundreds of artists and technicians, and the investments of honest tax paying producers, exhibitors and theatre owners, all who sustain the cinema we love. Who protects the creator when the system fails? We need accountability, swift certification, strict enforcement, and real-time takedowns. I trust true lovers of cinema will unite and give a befitting response by watching the film legally in theatres, as you stood with me in the past.
English
594
7.6K
41.2K
1.2M
Tanmoy Mukherjee
Tanmoy Mukherjee@langer_han·
@DHolzmueller @icmlconf There is a final justification which is shared with everyone which I am guessing I only got one so far and 3 have ghosted. My concern is the ghosting nature of reviews.
English
2
0
2
435
Tanmoy Mukherjee
Tanmoy Mukherjee@langer_han·
Really bummed that 2 @icmlconf reviewers just decided to ghosts us after putting their questions in rebuttal acknowledgement and not looking at our responses. Come on folks we can do better than this.
English
4
0
29
4.5K
Aswin RRV
Aswin RRV@aswinrrv·
Okay, I am gonna stay out of x today! :)
English
0
0
0
11