Future of Data, Agents and Processes (DAP). DAPLab is a group of @Columbia faculty and their PhD students at the forefront of applied research of Agentic AI.

New York, NY
Joined July 2025
DAPLab retweeted
At last week's #VLDB26, I gave keynotes @ NOVAS & DashSys workshops about @DAP__Lab's early work on Agentic Data Environments. Agent use cases are dragging technology behind it & there are research opportunities everywhere! Annotated slides: eugenewu.net/talks/2026-09-a…
2
4
16
1,360
Accepted at #ACL2026 Findings! Check out our paper on how to make agents better reasoners given a budget. See u in San Diego 🏖️!
LLMs can “think longer” and get better answers… but what if you can’t afford long reasoning? In our new paper, we study how LLMs reason under fixed computation budgets, where producing useful partial solutions quickly matters more than exhaustive reasoning. 🧵(1/n) 🔗: arxiv.org/pdf/2601.11038
1
13
999
LLMs can “think longer” and get better answers… but what if you can’t afford long reasoning? In our new paper, we study how LLMs reason under fixed computation budgets, where producing useful partial solutions quickly matters more than exhaustive reasoning. 🧵(1/n) 🔗: arxiv.org/pdf/2601.11038
3
11
2
29
7,287
DAPLab retweeted
i've isolated four recurring agent behaviors behind most vibe-coding failures: 1. skipping steps 2. ignoring conventions and style 3. making wrong assumptions 4. local optimization check out my new blog post for more details! daplab.cs.columbia.edu/gener…
1
3
8
510
A mom uses AI to make her kids' messes look like they're on the news. It worked! 😂
682
3,451
453
34,753
3,161,290
BREAKING: Anthropic just figured out how to control AI personalities with a single vector. Lying, flattery, even evil behavior? Now it’s all tweakable like turning a dial. This changes everything about how we align language models. Here's everything you need to know:
37
197
32
1,382
180,570