Vighnesh Subramaniam

PhD student @ MIT EECS + @MIT_CSAIL

[Vighnesh Subramaniam @su1001v]

Excited to announce that I'll be presenting Training the Untrainable at #NeurIPS2025 ! Come say hello :) or DM/email if you want to chat.

https://t.co/vLHEq2dEen

Also keep on the look out for some really exciting new work in the pipeline coming very soon... 👀👀

[Vighnesh Subramaniam @su1001v]

New paper💡!

Certain networks can't perform certain tasks due to lacking the right prior 😢. Can we make these untrainable networks trainable 🤔? We can, by introducing the prior through representational alignment with a trainable network! This approach is called guidance. (1/8)

[Gabrielle Kaili-May Liu (Kaili) @pybeebee]

🔥 New paper alert!! Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs 🔥

Can a model that learns to 𝘫𝘶𝘥𝘨𝘦 𝘪𝘵𝘴𝘦𝘭𝘧 get even better at tasks—and learn to be honest about what it doesn't know? Turns out: yes🤯

Details🧵👇

[Phillip Isola @phillip_isola]

Impromptu NeurIPS meetup: "representational convergence by the beach." We will meet at ballroom 20c (near lunch) 2pm Fri and walk over to Marina. Will chat about platonic reps, fractured reps, or anything else about where all these models are heading.

Anyone is welcome to join!

[Kathy Garcia @NeuroKathyG]

Excited to share that I’m at #NeurIPS2025 this year! 🧠

I’ll be presenting at the UniReps Workshop on my work on Social Tokens with @su1001v and @thisismyhat, where we explore how to inject socially relevant visual features into language models to improve social reasoning and alignment.

Super excited to connect with folks working at the intersection of multimodal models and human cognition.

If you’re around, come say hi! And feel free to DM me for a coffee chat ☕️

[Christopher Wang @czlwang]

Want to scale models on brain datasets recorded with variable sensor layouts?

Population Transformer at #ICLR2025 may be your answer!
🗺️ Fri, Apr 25 | 10am - 12:30pm (poster @ Hall 3 + Hall 2B #58)
🗣️ Fri, Apr 25 | 4:06 pm - 4:18 pm (oral @ Garnet 216-218)

More ⬇️

[Vighnesh Subramaniam @su1001v]

Check out our new #ICLR2025 oral paper! Congrats to the team and in particular, to the first authors, @czlwang and @GeelingC!

[Geeling Chau @ ICML @GeelingC]

🎉Excited to share: My first ML conference paper, Population Transformer 🧠, is an Oral at #ICLR2025! This work has truly evolved since its first appearance as a workshop paper last year. So thankful to have worked with the best advisors + collaborators! 🤗 More soon!

[Vighnesh Subramaniam @su1001v]

Check out our new work for self-improvement of LLMs!

This work uses a multi-agent set up that not only improves performance but preserves diversity over iterations of finetuning.

Website: https://t.co/TNlxCj35BU
Paper: https://t.co/LFoUsHXCGB

[Yilun Du @ ICML @du_yilun]

Introducing multi-agent self-improvement with LLMs!

https://t.co/MRp7URBGyt

Instead of self improving a single LLM, we self-improve a population of LLMs initialized from a base model.

This enables consistent self-improvement over multiple rounds.

[Andrei Barbu @_abarbu_]

Interested in large-scale neuroscience of language and multimodal representations? We have the dataset for you, the Brain Treebank! Come to our oral at NeurIPS. Today at 3:50pm PST, East Meeting room https://t.co/pAaV1ipeQC Now with extra foundation models https://t.co/DfuITDvshV

[Vighnesh Subramaniam @su1001v]

Work done with amazing collaborators @DavidMa53462349, Colin Conwell, Tommy Poggio, Boris Katz, @thisismyhat, and @_abarbu_.

Paper: https://t.co/5VvzuJmuj1
Website: https://t.co/vLHEq2dEen
Code: https://t.co/pXcERwYcRu (8/8)

[Vighnesh Subramaniam @su1001v]

New paper💡!

Certain networks can't perform certain tasks due to lacking the right prior 😢. Can we make these untrainable networks trainable 🤔? We can, by introducing the prior through representational alignment with a trainable network! This approach is called guidance. (1/8)

[Vighnesh Subramaniam @su1001v]

We cover tons of other experiments and settings in the paper such as stopping guidance early and analyzing error consistency of guided networks in the paper.
We hope guidance can be a general tool for improving and understanding neural network design😀! (7/8)

[Vighnesh Subramaniam @su1001v]

Check out our new paper on localizing and characterizing vision-language integration in the brain, now in ICML 2024!

Paper: https://t.co/zmnyyxsTBB
Project Page: https://t.co/4yoQuZYGW2
Dataset: https://t.co/8QPiR1FXsB
Code: https://t.co/6h3UPR0ze5

[Gabriel Kreiman @gkreiman]

Revealing Vision-Language Integration in the Brain with Multimodal Networks. Subramaniam et al, ICML 2024. Download the article here: https://t.co/nApJr74SP6

[Geeling Chau @ ICML @GeelingC]

How can we train models on more brains and sensor layouts?

We present Population Transformer (PopT) which learns population-level interactions on intracranial electrodes, with 🔥decoding and interpretability benefits.

See our poster at #ICML2024 @AI_for_Science 12pm

[Vighnesh Subramaniam @su1001v]

@alfcnz @vighnesh1992 @czlwang Thank you for stopping by! Glad you found the work interesting.