Siddharth Suresh @siddsuresh97

ML Research Intern @NetflixResearch | PhD student @UWMadison | Human-AI Alignment | Prev Applied Scientist Intern @AmazonAGI, Intern @BrownCLPS scholar.google.com/citations?user… Madison, WI Joined October 2016

Tweets

172
Followers

421
Following

2K
Likes

1K

Apurva Ratan Murty @apurvaratan

2 months ago

Excited for this workshop at #CCN2025! Come listen to me talk about TopoNets: Topographic models across vision, language and audition. Look forward to seeing old friends and making new ones!

Martin Schrimpf @martin_schrimpf

2 months ago

Excited for this workshop at #CCN2025! Come listen to me talk about TopoNets: Topographic models across vision, language and audition. Look forward to seeing old friends and making new ones!

0 7 32 3K 5

0 2 20 1K 0

Kushin Mukherjee @kushin_m

2 months ago

Happening now at Salon 3!!

Kushin Mukherjee @kushin_m

2 months ago

Happening now at Salon 3!!

1 7 29 5K 9

Download Image

0 1 2 245 0

Siddharth Suresh @siddsuresh97

2 months ago

Come watch our talk (@kushin_m) in Salon-3 today at 2:15PM at CogSci. #cogsci2025

Siddharth Suresh @siddsuresh97

2 months ago

Come watch our talk (@kushin_m) in Salon-3 today at 2:15PM at CogSci. #cogsci2025

0 0 0 178 0

Download Image

0 0 0 140 0

Cameron R. Wolfe, Ph.D. @cwolferesearch

2 months ago

Direct Preference Optimization (DPO) is simple to implement but complex to understand, which creates misconceptions about how it actually works… LLM Training Stages: LLMs are typically trained in four stages: 1. Pretraining 2. Supervised Finetuning (SFT) 3. Reinforcement…

2 39 178 11K 139

Download Image

lalit @stochasticlalit

2 months ago

It was amazing to be part of this effort. Huge shout out to the team, and all the incredible pre-training and post-training efforts that ensure Gemini is the leading frontier model! deepmind.google/discover/blog/…

2 8 29 4K 2

Nicholas Roberts @nick11roberts

3 months ago

🎉 Excited to share that our paper "Pretrained Hybrids with MAD Skills" was accepted to @COLM_conf 2025! We introduce Manticore - a framework for automatically creating hybrid LMs from pretrained models without training from scratch. 🧵[1/n]

1 18 44 6K 3

Download Gif

Thomas Fel @Napoolar

3 months ago

🧠 Submit to CogInterp @ NeurIPS 2025! Bridging AI & cognitive science to understand how models think, reason & represent. CFP + details 👉 coginterp.github.io/neurips2025/

CogInterp Workshop @ NeurIPS 2025 @CogInterp

3 months ago

🧠 Submit to CogInterp @ NeurIPS 2025! Bridging AI & cognitive science to understand how models think, reason & represent. CFP + details 👉 coginterp.github.io/neurips2025/

1 20 71 14K 20

0 8 32 3K 4

Jifan Zhang @jifan_zhang

3 months ago

Releasing HumorBench today. Grok 4 is🥇 on this uncontaminated, non-STEM humor reasoning benchmark. 🫡🫡@xai Here are couple things I find surprising👇 1. this benchmark yields an almost perfect rank correlation with ARC-AGI. Yet the task of reasoning about New Yorker style…

Reuben Narad @ReubenNarad

3 months ago

2 5 11 4K 2

Download Image

0 3 12 2K 1

Fenil Doshi @fenildoshi009

3 months ago

🧵 What if two images have the same local parts but represent different global shapes purely through part arrangement? Humans can spot the difference instantly! The question is can vision models do the same? 1/15

5 122 607 72K 430

Download Gif

Qihong Lu | 吕其鸿 @Qihong_Lu

5 months ago

I’m thrilled to announce that I will start as a presidential assistant professor in Neuroscience at the City U of Hong Kong in Jan 2026! I have RA, PhD, and postdoc positions available! Come work with me on neural network models/experiments on human memory! RT appreciated! (1/5)

13 24 125 12K 15

Andrew Lampinen @AndrewLampinen

5 months ago

How do language models generalize from information they learn in-context vs. via finetuning? We show that in-context learning can generalize more flexibly, illustrating key differences in the inductive biases of these modes of learning — and ways to improve finetuning. Thread: 1/

8 153 770 99K 691

Download Image

Ben Lonnqvist @lonnqvistben

5 months ago

Now accepted at #icml2025 !

Ben Lonnqvist @lonnqvistben

5 months ago

Now accepted at #icml2025 !

10 45 338 37K 258

Download Image

0 1 24 1K 1

Andrew Lampinen @AndrewLampinen

5 months ago

Had fun talking at the @SCSLWorkshop at ICLR! One example I brought up, which I think provides an uncommon perspective: a case where spurious shortcuts can improve generalization... even to out-of-distribution sets where the spurious feature doesn't generalize! Thread:

3 7 55 10K 18

Dimitris Papailiopoulos @DimitrisPapail

5 months ago

Do you want to do RL for coding and agentic workflows? Do you want to do science, and figure out when RL kicks in? What is the right algorithm (it's not GRPO)? how much reasoning you need in your base (you def need some! but is it a lot or A LOT)? Do you want to figure out how…

Dimitris Papailiopoulos @DimitrisPapail

5 months ago

36 237 1K 436K 796

Download Image

6 23 204 28K 130

Computational Auditory Perception Group @CompAudition

5 months ago

We are recruiting postdocs! Want to grow your own social networks to study creativity, cultural evolution & decision-making? We are hiring a funded postdoc at Cornell in collaboration with UC Davis, CUNY, & Princeton. Apply here: academicjobsonline.org/ajo/jobs/28959