Spandan Madan (@spandan_madan) 's Twitter Profile
Spandan Madan

@spandan_madan

AI + Neuroscience @Harvard

ID: 1285209259701989377

calendar_today20-07-2020 13:45:52

735 Tweet

784 Followers

516 Following

Spandan Madan (@spandan_madan) 's Twitter Profile Photo

Are DNNs good models of the brain? We answer this question in our recent work: openreview.net/forum?id=kD1kp…. Had a lot of fun presenting this at NeurIPS 2024! The associated interview with CBMM can be found here: youtube.com/watch?v=bhXB-d….

Spandan Madan (@spandan_madan) 's Twitter Profile Photo

We all know about adversarial attacks. But is a malicious adversarial agent even necessary to attack these models? Not quite. In our recent #Neurips2024 work, we show networks are highly susceptible to data hiding in plain sight within the training data distribution!

Spandan Madan (@spandan_madan) 's Twitter Profile Photo

Why do vision models struggle to generalize? Our #NeurIPS2024 paper identifies the underlying cause---computer vision models simply need to be trained with data similar to biological vision. We present the Human Visual Diet dataset, and models that can leverage this data.

Spandan Madan (@spandan_madan) 's Twitter Profile Photo

Very proud that our work was covered by CBMM and Harvard SEAS (seas) news! In a nutshell, we explore the perils of Neural Network based models of the brain! cbmm.mit.edu/video/benchmar… seas.harvard.edu/news/2025/01/e…

Spandan Madan (@spandan_madan) 's Twitter Profile Photo

Super proud of the amazing work led by serena bono, which just made it to the homepage of MIT: mit.edu. Associated News: news.mit.edu/2025/new-train… Video Interview explaining the project: youtube.com/watch?v=JEyP1v…

Spandan Madan (@spandan_madan) 's Twitter Profile Photo

Built a new benchmark evaluating OpenAI O3 and Google Gemini 2.5 Pro on cognitive tasks. Google beating OpenAI hands down. Every cognitive task. More to come soon.

Spandan Madan (@spandan_madan) 's Twitter Profile Photo

Going to be honest. I have a PhD in Machine Learning, and I have never ever used Discrete Structures. Make that leap. Skip those stairs.

Ethan Mollick (@emollick) 's Twitter Profile Photo

Huh. Looks like Plato was right. A new paper shows all language models converge on the same "universal geometry" of meaning. Researchers can translate between ANY model's embeddings without seeing the original text. Implications for philosophy and vector databases alike.

Huh. Looks like Plato was right.

A new paper shows all language models converge on the same "universal geometry" of meaning. Researchers can translate between ANY model's embeddings without seeing the original text.

Implications for philosophy and vector databases alike.
Spandan Madan (@spandan_madan) 's Twitter Profile Photo

Interesting problem now that LLMs have memory across chats---Claude 4 copied and replaced line of code from an older file version from a past chat. Took forever to track.

Spandan Madan (@spandan_madan) 's Twitter Profile Photo

The same might be true for code. The skill of thinking "what to code" might get atrophied. Seeing it in younger students already.

Jonathan Gorard (@getjonwithit) 's Twitter Profile Photo

Calling c the "speed of light" completely misses the point. Rather, c is the "spacetime exchange rate": how many units of space you can exchange for one unit of time. In actuality, everything travels at the "speed of light", just not necessarily through space alone... (1/4)

Calling c the "speed of light" completely misses the point. Rather, c is the "spacetime exchange rate": how many units of space you can exchange for one unit of time.

In actuality, everything travels at the "speed of light", just not necessarily through space alone... (1/4)