@dzyan01

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

david-yan1.github.io
Joined March 2025
  • Tweets161
  • Following439
  • Followers661
24Media
david yan retweeted
Yinfei Yang
@yinfeiyOct 16
I spent a decade building foundation models at Google and Apple. But what our small team at Elorian accomplished with just a few hundred GPUs might be the most exciting leap yet. Meet Glimpse -- Our frontier-level multimodal model at platform.elorian.ai 🚀🚀🚀 @ElorianAI 🚀🚀🚀

Elorian Platform

Try Glimpse, Elorian's frontier visual reasoning model.

platform.elorian.ai
Andrew M. Dai
@AndrewDaiOct 16
Spent years watching models ace a single image and completely whiff on anything that moves or changes angle. Today we’re fixing that. Try Glimpse now, our first visual thinking model with competitive frontier performance compared to Astra on key public visual reasoning benchmarks.
23
18
2
208
12,047
david yan retweeted
Elorian AI
@ElorianAIOct 16
Today we're thrilled to announce the release of our first frontier visual reasoning model
56
120
58
1,769
118,106
david yan retweeted
Dustin Tran
@dustinvtranOct 16
On results, Glimpse is competitive on the frontier across multimodal benchmarks and dominates Flash-sized models.
12
14
7
71
18,681
david yan retweeted
Andrew M. Dai
@AndrewDaiOct 16
Spent years watching models ace a single image and completely whiff on anything that moves or changes angle. Today we’re fixing that. Try Glimpse now, our first visual thinking model with competitive frontier performance compared to Astra on key public visual reasoning benchmarks.
396
616
417
5,859
4,148,720
1/ I’m excited to share our work on “Depth as Time in One-Step Generative Models”! alphaxiv.org/abs/2610.03626 TL;DR: We ask, when a model learns to generate an image in one forward pass, what happens to the denoising process? We observe that process unfolding over depth!
5
38
4
271
12,985
david yan retweeted
Scale Labs
@ScaleAILabsOct 7
We’re introducing Humanity’s Sixth Sense, a new benchmark testing the intuitive visual reasoning people rely on every day. Across 522 open-ended tasks spanning images and video, HSS tests everything from spatial and causal reasoning to social understanding. The gap is significant. Humans score 93.1%, while the strongest model, GPT-6-astra, reaches 53.6%. The median model scores just 30.9%.
85
148
93
2,243
207,203
The most profound paper of my PhD so far. We truly did something special to make LMs play/explain chess, needing both architectural & algorithmic innovation (natural-language analogue of the Alphazero algorithm) + applicable to many other domains. Please read on and share! 1/10
61
174
28
1,550
110,158
david yan retweeted
samrat@samratsahoo_Oct 2
Task and motion planning (TAMP) excels at multi-step, semantic, and geometric reasoning. VLAs excel at deformable object manipulation, which TAMP can't do. Can one VLA do both? DATAFARM fine-tunes VLAs on TAMP demos aligned to the pre-training distribution. (1/9)
3
27
5
91
15,938
david yan retweeted
Vahe Taamazyan
@vahetaSep 1
Placing a risky bet and watching it pay off is one of the best feelings in life. A year ago, we set out to achieve SoTA in stereo 3D reconstruction. Instead of building a complex model, we did the opposite: we stripped it down to a simple ViT. Introducing NBS 🧵👇
20
21
3
207
13,896
Researchers are actively improving memory for LLMs/VLMs. But are we measuring it right? A system can score 100% by rereading the input for each question. If a human did that, we’d call it terrible memory! We test beyond accuracy with ECC: Efficiency, Compression, Calibration. 🧵
4
7
22
1,005
david yan retweeted
Erich Liang@ErichLiangSep 1
Dynamic camera intrinsics often appear in robotics and 3D vision—yet training and evaluation data for predicting them from RGB is surprisingly rare. Introducing InFlux++: our new real-world benchmark and synthetic training dataset for dynamic intrinsics prediction. 🧵1/6
1
18
2
131
10,849
david yan retweeted
Elorian AI
@ElorianAIAug 19
We’re growing the team at Elorian! Our mission: teach machines to truly understand the visual world. Small, focused team, no friction between idea and execution. If solving visual thinking excites you, check out our open roles: elorian.ai
3
9
88
10,648
david yan retweeted
sudarsh
@sudarshk_Jul 30
wow,, larp is life
Ziqian Zhong
@fjzzq2002Jul 30
New blog: Why does Kimi identify as Claude and Sonnet 4.6 as DeepSeek? We find that this can come from a subliminal-learning-like effect: If you speak like Claude, you become Claude.
1
8
974
david yan retweeted
Tom Silver@tomssilverJul 20
New blog post: tomsilver.github.io/blog/202… This is the second in a "series" of posts about how to define and work on research problems. (The first post was 3 years ago...) This one addresses the agentic elephant in the room.

Now What? A Recipe for After the Problem Setting (in the Agentic Age)

The research recipe I follow after defining a problem setting, with a new step for the agentic age: implement the pure agent baseline.

tomsilver.github.io
15
1
124
6,231
1/ We've released Infinigen 2.0! Currently in preview. It creates indoor 3D scene files in 1min CPU time, and includes new and better materials --- all still fully procedural. Our new 2.0 design is highly efficient and allows easy control and recombination via Python APIs.
13
43
4
358
32,917
I've joined @AnthropicAI to work on alignment and character. I'll still teach at @nyuniversity; I'm on leave from @UTAustin.
89
45
41
1,173
441,796
david yan retweeted
Ankit Goyal
@imankitgoyalJul 2
Thrilled to share that I'll be joining the University of Michigan as an Assistant Professor in Fall 2027! My lab will work on Robot Learning, Dexterous Manipulation, Robot Foundation Models & 3D Perception. I'm looking for students to join me. Please apply and reach out. (1/2)
54
23
1
463
30,157
david yan retweeted
Andrew M. Dai
@AndrewDaiJun 17
Incredibly excited to welcome @dustinvtran to @ElorianAI as our new Chief Reasoning Architect! 🚀 We had an amazing time working together at Google Brain, and after seeing his incredible work leading post-training at xAI, I couldn't be more thrilled to be teaming up again. Let’s build something special! Welcome to the team, Dustin!
Dustin Tran
@dustinvtranJun 17
personal news: i've joined Elorian as Chief Reasoning Architect. multimodal AGI is the most critical frontier as we move from the era of chatbots to coding agents to models that reason and act over the physical world. i'm really excited to design natively visual models across thinking, agents, architectures, and the systems stack with the amazing team at Elorian. i wish the best to everyone at xAI & SpaceX — driving posttraining was a unique experience with so many memorable stories. all the best to the team, and to Elon.
10
7
1
109
26,844
david yan retweeted
Dustin Tran
@dustinvtranJun 17
personal news: i've joined Elorian as Chief Reasoning Architect. multimodal AGI is the most critical frontier as we move from the era of chatbots to coding agents to models that reason and act over the physical world. i'm really excited to design natively visual models across thinking, agents, architectures, and the systems stack with the amazing team at Elorian. i wish the best to everyone at xAI & SpaceX — driving posttraining was a unique experience with so many memorable stories. all the best to the team, and to Elon.
51
19
10
383
91,628
david yan retweeted
Raj Ghugare
@GhugareRajJun 16
Does classical computation theory help explain the success of inference time compute in RL? We study this question in our #ICML2026 oral We prove that policies with higher inference compute solve and generalize to a larger set of tasks. Empirically, we show that such policies can outperform 5x larger ResNets. Website - rajghugare19.github.io/compu… 🧵👇
2
8
3
41
14,844
Load more