david yan (@dzyan01) profile picture

phd student @PrincetonVL, research intern @elorianai. formerly: bse @princetoncs

Joined March 2025
On BrickVision, existing models vary widely in performance! 6/7
2
1
165
Because many existing VQA benchmarks are solvable with simple textual references, we introduce BrickVision, a challenging benchmark designed to measure a model's capability to reason with undescribable visual references. 5/7
1
2
130
To explain these results, we demonstrate that grounded reasoning provides advantages on tasks that require undescribable references, but not when objects are describable in language. 4/7
1
1
143
We also find that, when compared to text reasoning, grounded reasoning is not particularly helpful for general VQA, but improves counting performance! 3/7
1
1
227
We introduce a new technique to measure grounding usage in existing reasoning models and find that many open models don't actually rely on their generated coordinates when reasoning. 2/7
1
1
381
Grounded reasoning is a popular thinking strategy for VLMs. But do models even use their grounding? (spoiler: not always!) In our @ElorianAI paper, we dig into the grounded reasoning recipe and release BrickVision, a benchmark that’s challenging to solve without grounding. 1/7
1
6
1
48
4,210
Random thought on "why do a (ml/ai) phd?" I believe AI has shortened one's optimization horizon, due to high future uncertainty. As such, you should be confident that you will get positive short-term value, instead of indexing on the eventual delayed reward from finishing.
8
5
1
101
8,362
Excited to announce a major performance update for Infinigen! We've overhauled various assets and systems, focusing on efficiency. Our `--performance` config reduces the average generation time of nature scenes by 8x without sacrificing any visual fidelity! 1/3
8
15
2
120
9,483
some things never change! from HN thread on CycleGAN in 2017.
2
22
3,158
great prescience from dario here
2
3
34
1,153
goodbye yellow-theme wandb 😢
3
246
good charts are parsimonious
straight lines on graphs. you can’t even see where ai happened!
1
332
found a guy on ebay who sells career fair quant merch and loose barebells
9
3
3
464
55,362
fable should be kinder to the subagents
9
492
i aspire to become a sota larper
19
1,875
Noticing a trend where zoomer founders advertise their high lol/valorant ranks. Alas, my only notable gaming accomplishment is hitting masters elo in 2018 town of salem.
8
520
Replying to @itsandrewgao
Hasn't shown up in degree data; this is based off what current sophomores are declaring. dailyprincetonian.com/articl…
5
650