Tyler LaBonte

ML PhD student @GeorgiaTech, Math BS @USC. Deep learning theory, generalization, robustness.

[Tyler LaBonte @tmlabonte]

Excited to present at the first #AISTATS2025 poster session on May 3!

Ever wondered how LLMs can generalize to new tasks in-context despite only training on token completion? We formalize this phenomenon as "task shift" and investigate a linear version: https://t.co/RoYippuZVi

[Tyler LaBonte @tmlabonte]

@guilhermeotina @TmlrOrg Yep! Most methods which infer group structure use properties of the model representation; we argue feature learning is key for understanding & interpreting them (e.g. Izmailov 2022).

Our TMLR paper is more specific to unbalanced LLR, but feature learning papers are in the works!

[Tyler LaBonte @tmlabonte]

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: https://t.co/XkLMSbw5ua

[Tyler LaBonte @tmlabonte]

Heading to #ICLR2025 to present our SCSL workshop paper on understanding how last-layer retraining methods mitigate spurious correlations! https://t.co/6kQ1HG0WVI

Stop by on Monday, April 28 to chat and learn more 🙂

[Tyler LaBonte @tmlabonte]

@matheusmaldaner @iStaridium @LAHacks Go to Tacos 1986!

[Tyler LaBonte @tmlabonte]

@matheusmaldaner @NSF Congrats!!!

[Tyler LaBonte @tmlabonte]

@etash_guha Killing it Etash!

[Tyler LaBonte @tmlabonte]

Cramér on Lindeberg: "When he was reproached for not being sufficiently active in his scientific work, he said 'Well, I am really a farmer.' And if somebody happened to say that his farm was not properly cultivated, his answer was 'Of course my real job is to be a professor.'"

[Tyler LaBonte @tmlabonte]

@iamwaynechi Can't wait for more games in various shades of red! ("rougelikes"... ok I'll see myself out)

[Microsoft Research @MSFTResearch]

Multimodal reasoning with Phi-4-reasoning-vision, new work on scaling LLM inference, benchmarking AI agents in network operations, cinematic video generation, adaptive evaluation for LLMs, and using AI to improve individual and population health. https://t.co/9Y0SyTlG5W

[Tyler LaBonte @tmlabonte]

Our Phi-4-reasoning-vision-15B technical report is now available on arxiv:

https://t.co/6ZPE7J6kz4

[Tyler LaBonte @tmlabonte]

Some nice coverage on our new model release, highlighting our hybrid approach to multimodal reasoning 🚀

[VentureBeat @VentureBeat]

Microsoft built Phi-4-reasoning-vision-15B to know when to think — and when thinking is a waste of time
https://t.co/exMXVFEss6

[Tyler LaBonte @tmlabonte]

It's been the privilege of my career to help build the newest Phi series model from @MSFTResearch!

Phi-4-reasoning-vision-15B is open-weight & competitive on perf with 10X less compute/tokens.

Read the blog for math and CUA case studies, hybrid reasoning, data insights, & more!

[Microsoft Research @MSFTResearch]

Vision-language models improve multimodal systems, but can make them slower, costlier, and harder to deploy. Learn how Phi-4-reasoning-vision-15B, a compact and fast multimodal reasoning model, blends strengths of different methods while reducing their limits: https://t.co/jP5L3AXRzX

[Tyler LaBonte @tmlabonte]

@bneyshabur Best of luck, Behnam! Looking forward to what comes next!

[Tyler LaBonte @tmlabonte]

Finally, thanks to @Kangwook_Lee's "Tenure Track Simulator" post for inspiring me to make the game public and write this up!

[Tyler LaBonte @tmlabonte]

Over the holidays, I stress-tested the AI coding hype by doing something concrete: I built a college football simulator game from scratch to see if agents actually deliver. Here’s what I learned 👇

[Tyler LaBonte @tmlabonte]

Misc takeaways:
• Copilot + GitHub was far more useful than I expected
• Keeping code style consistent across humans + agents is painful
• Overall: Claude was best for agentic coding; Gemini best for interactive pair-programming