Tyler LaBonte

@tmlabonte

Senior Researcher @MSFTResearch @ms_aifrontiers working on future capabilities of multimodal agents. ML PhD @GeorgiaTech, Math BS @USC.

Atlanta, GA

tyler-labonte.com

Replies Reposts Media

Pinned
Tyler LaBonte
@tmlabonte
Jun 23
Overdue update: I've defended my dissertation and graduated from @GeorgiaTech! Next, I've joined @MSFTResearch @ms_aifrontiers as a Senior Researcher working on future capabilities of multimodal agents 🚀
8
Tyler LaBonte
@tmlabonte
Jun 30
New paper — the last and best from my PhD! We show the first end-to-end feature learning analysis of how neural networks overfit to spurious correlations. Our theory implies phase transitions in SGD learning dynamics that match empirical results. Paper: arxiv.org/abs/2606.30444
5
Tyler LaBonte
@tmlabonte
Jun 25
Very cool work from new colleagues at @ms_aifrontiers: most LLM benchmarks are redundant!
Microsoft AI Frontiers
@ms_aifrontiers
Jun 25
Most LLM benchmark scores are predictable before you ever run them. New from the MS AI Frontiers team: BenchPress. The 84-model × 133-benchmark score matrix turns out to be effectively rank-2, so matrix completion fills in the rest. 5 probes recover a model's whole profile.
00:00
Tyler LaBonte
@tmlabonte
Jun 21
I like the characterization of AI as an "alien collaborator" for math. We have a forthcoming theory paper where AI was invaluable for optimizing delicate technical conditions -- but only humans could translate ideas and goals into self-contained math questions the AI could parse
Tony Feng
@tonylfeng
Jun 20
Recently, I have started getting appreciable value from AI for my own mathematics research. While model improvements were necessary for this to happen, I think another key factor was reflecting on recent success cases, in order to build a better mental model for the comparative
Tyler LaBonte
@tmlabonte
May 24
The updated version of this paper has been accepted at @TmlrOrg 🚨🚀 Very excited about implications of our results for SOTA robustness algorithms & understanding spurious correlations more generally. Journal version link: openreview.net/pdf?id=h81ztbr…
Tyler LaBonte
@tmlabonte
Apr 23, 2025
Heading to #ICLR2025 to present our SCSL workshop paper on understanding how last-layer retraining methods mitigate spurious correlations! openreview.net/pdf?id=B2W51aq… Stop by on Monday, April 28 to chat and learn more 🙂
1