Taylor Berg-Kirkpatrick

@BergKirkpatrick

Assoc Prof at UC San Diego @ucsd_cse, AI researcher

San Diego, CA

Joined December 2017

Taylor Berg-Kirkpatrick
@BergKirkpatrick
Jul 16
🎉 Thrilled to share we had 4 papers accepted to COLM 2026! Huge congrats to Hayden Prairie @hayden_prairie, Ivan Lee @ivn1e (lead on two!), Yasaman Jafari @yasjafarii , Zixian Wang, Cheng Yang @ChengYANG_yc , and Zachary Novack @zacknovack — 🧵 below with all the papers: 1/
arxiv.org
Parcae: Scaling Laws For Stable Looped Language Models
Traditional fixed-depth architectures scale quality by increasing training FLOPs, typically through increased parameterization, at the expense of a higher memory footprint, or data. A potential...
Taylor Berg-Kirkpatrick
@BergKirkpatrick
Apr 15
Exciting new work by amazing students @hayden_prairie and @zacknovack in collab with @realDanFu !! Check it out!
Hayden Prairie
@hayden_prairie
Apr 15
We’ve been thinking a lot about scaling laws, wondering if there is a more effective way to scale FLOPs without increasing parameters. Turns out the answer is YES – by looping blocks of layers during training. We find that predictable scaling laws exist for layer looping,
Taylor Berg-Kirkpatrick
@BergKirkpatrick
Dec 9, 2025
Cool work by amazing students Ivan Lee @ivn1e and Cheng Yang!
Ivan Lee
@ivn1e
Dec 9, 2025
DeepSeek-OCR is a solid OCR model. But the excitement around it has become something bigger—evidence that vision might solve the long context problem. Has the excitement outpaced the evidence? "Optical Context Compression Is Just (Bad) Autoencoding" → arxiv.org/abs/2512.03643
Taylor Berg-Kirkpatrick
@BergKirkpatrick
May 14, 2025
So excited for Niloofar!!! she’s truly a force of nature — honored to have been along for part of the ride!!
Niloofar
@niloofar_mire
May 6, 2025
📣Thrilled to announce I’ll join Carnegie Mellon University (@CMU_EPP & @LTIatCMU) as an Assistant Professor starting Fall 2026! Until then, I’ll be a Research Scientist at @AIatMeta FAIR in SF, working with @kamalikac’s amazing team on privacy, security, and reasoning in LLMs!
Taylor Berg-Kirkpatrick
@BergKirkpatrick
Oct 18, 2024
Together with @EarlenceF and amazing students we demonstrated that obfuscated adversarial prompts can secretly exfiltrate Personally Identifiable Information (PII) from an LLM chat interface via tool misuse.
earlence
@EarlenceF
Oct 17, 2024
We've done some work on hacking AI/LLM Agents by creating obfuscated adversarial prompts. What do you think this prompt does? Would you believe me if I told you it will polish the heck out of that cover or visa application letter?