Keming Zhang

@j_dekoninck Claude Opus scored near bottom on BrokenArXiv, but near top on the Bullshit Benchmark (petergpt.github.io/bullshit-bench…). They appear to test similar skills. Any comments on this?

How often do LLMs claim to prove false mathematical statements? In our latest benchmark, BrokenArXiv, we find they do so very often. The best model, GPT-5.4, only rejects 40% of incorrect statements obtained by perturbing recent ArXiv papers, and other models do much worse.

@TingAstro Very interesting work! I competed at the 8th IOAA in 2014 and recall the gold medal line was 90% of the top 3 scores averaged. Did this change recently?

We tested 5 state-of-the-art LLMs (GPT-5, Gemini-2.5-Pro, OpenAI o3, Claude Opus 4.1, Claude Sonnet 4) on the International Olympiad on Astronomy and Astrophysics (IOAA). arxiv.org/pdf/2510.05016 Theory problems: GPT-5 and Gemini-2.5-Pro ranked top 2 among 200-300 students across 4 years (2022-2025), achieving gold medals. Other models also reached gold level but with lower rankings 🥇 Data analysis problems: GPT-5 ranked top 10, but other models struggled to varying degrees, revealing gaps in multimodal reasoning 📷 AI can excel at physics reasoning but still struggles with spatial visualization and interpreting astronomical data. Great collaboration with the NLP science agent group at OSU @hhsun1 @ShroffNess Yingbin Liang. Led by Lucas Carrit Delgado Pinheiro and @RonZiruChen. Also Bruno Caxeita Piazza.

@david_kipping Good luck! Will you be staying with a university?

Some personal news! Next month I will be moving to the UK for a year for a sabbatical. I plan to do some writing, recharge my batteries, build new connections and make some great videos. Looking forward to seeing many of my long list British colleagues!

I’m excited to share that I’ll be starting as a NHFP Sagan Fellow at @MIT this fall! Look forward to connecting with new/old friends interested in everything Astro and AI.

Check out this NYT story on our planet discovery! H/T @kjb_astro, @jlu_astro, @AgolEric, @bsgaudi, @seankterry, @QuinnKono, et al.

An Earth-mass planet is inferred to have a white dwarf host, suggesting that terrestrial planets in Earth-like orbits may avoid being engulfed during the red-giant phases of their host stars. @AstroKeming, Zang et al.: nature.com/articles/s4155… / rdcu.be/dVa0R @ucsdastro

The coolest paper on @arxiv today has to be this one, on the discovery of an Earth-mass planet and a brown dwarf orbiting a white dwarf. It makes me think about what happens to a planetary system when its star goes red giant (short thread) arxiv.org/abs/2409.02157

Joint work with Weicheng Zang, @kjb_astro, @jlu_astro, Josh Bloom, @AgolEric, @bsgaudi, @seankterry, @QuinnKono, Shude Mao, and Natalie LeBaron

We have discovered a 1.9 Earth-mass planet orbiting a White Dwarf at ~2.1 au, around where you would expect to find planet Earth if it could avoid being engulfed by the Red Giant Sun. Also a bonus brown dwarf at ~30 au. arxiv.org/abs/2409.02157

@PlotAstro I did IAO 2013 and IOAA 2014 😄

Speaking of the Olympiad, did you participate in an Astronomy Olympiad? I did! 🥈😀

@miyazaki_shota Looks fantastic!

GC observed by PRIME! Victory!

@bmac_astro @seankterry @jlu_astro @profjsb GL758 and HR7672

@seankterry @AstroKeming @jlu_astro @profjsb Nice! What were you attempting with the coronagraph?

Amazing observing with Keck laser adaptive optics last night! I guess that means I’m now officially an observer? A big shoutout to @jlu_astro @profjsb @seankterry Natalie and our amazing OA/SA Jim and Rita for your support! Guess what we were looking at? (hint: right image)

@seankterry @jlu_astro @profjsb And also Titan!

@AstroKeming @jlu_astro @profjsb Congrats on a great night Keming! Imaging the new SN, microlensing targets, even (attempting) the coronagraph! lol

@seankterry @jlu_astro @profjsb Guess I’ll learn everything about coronagraphs from @QuinnKono soon!😄

@AstroJacobLi @jlu_astro @profjsb @seankterry bulge it is

@AstroKeming @jlu_astro @profjsb @seankterry Galactic center or bulge?

@AJamesMcCarthy Are the two images taken on the same night? If so, would you mind sharing the time stamp the supernova first became visible in your images? @profjsb

Look in the upper arm of this galaxy- you'll see a star appear to blink in and out of existence. That's a supernova! Very recently discovered in m101: the Pinwheel galaxy (which I happened to be shooting when this happened)

@bsgaudi Thank you very much Scott! I look forward to your visit in July!

Congrats to Keming!

Thank you very much Josh! It has been exciting five years working with you!

@bsgaudi @OSUAstro @NASARoman @NASAWebb Congratulations! Will her thesis/paper be made available online? This sounds super exciting and I’d love to learn more.

Proud to announce that Autumn Stephens, an @OSUAstro undergraduate that I've working for, successfully passed her senior thesis examination today! Her thesis was on the prospects for getting spectra of microlensing host stars of planets detected by @NASARoman with @NASAWebb.