Peter Chen

PhD Student @MIT_CSAIL | Student Researcher @allen_ai | Intern @MSFTResearch

[Peter Chen @peterbailechen]

Research talk on LAG, CONCUR, and ongoing work on AI systems and test-time scaling @ Test-time updates workshop (4/27 Monday)

[Peter Chen @peterbailechen]

Excited to share two papers and ongoing work at #ICLR2026. Feel free to catch me at sessions and chat!

Huge thanks to my collaborators @Wado_Will @WeiyueLi777 @DanRothNLP @samrmadden @jacobandreas @MikeCafarella!

More details in threads below🧵

[Peter Chen @peterbailechen]

CONCUR where we explore lightweight continual model routing to unseen models
- 4/25 Saturday: Poster @ 10:30AM-1PM Pavilion 3 P3-#1413

[Peter Chen @peterbailechen]

Log-augmented generation (LAG) where we explore test-time scaling by reusing computations via KV cache values
- 4/23 Thursday: Poster @ 3:15PM-5:45PM Pavilion 3 P3-#1419
- 4/26 Sunday: Poster @ LLA and RSI workshops
- 4/27 Monday 16:15-16:45: Oral @ MemAgent workshop

[Peter Chen @peterbailechen]

I am excited to present EnrichIndex at #COLM2025 where we explore how to use LLMs to build reusable retrieval indices offline to improve complex retrieval with implicit reasoning! @TomerWolfson @MikeCafarella @DanRothNLP @cogcomp

Come check out our poster @ Poster 3 (11:00 AM)!