Sign in

Aishik Ghosh

@aishikghosh.bsky.social
272 followers 99 following 76 posts

Assistant Professor in School of Physics @ GT Physics ∩ AI AI Policy

PostsRepliesMedia
Aishik Ghosh @aishikghosh.bsky.social · 11h
A point on attribution worth highlighting: since our LLMs connect ideas from past scientific work, we explicitly cite the papers that inspired their contributions.
000
Aishik Ghosh @aishikghosh.bsky.social · 01/10/2026
This one could be a thesis! Probing dark matter signatures with an RL agent that sets the stage for swarms of LLMs. The framework connects software from across particle physics & cosmology, proposes interesting observables! Paper led by Ibrahim Elsharkawy, with Victoria Knapp-Perez and Wahid Bhimji.
130
Aishik Ghosh @aishikghosh.bsky.social · 30/09/2026
Ever wanted high-dim NSBI analyses with the robustness of histogram methods? New paper on hybrid NSBI for robust applications and limited-budget scenarios, with Sean Benevedes, Mani Dehghan, and Tae Park. arxiv.org/abs/2609.36044
120
Reposted by Aishik Ghosh
Lukas Heinrich @lukasheinrich.com · 03/09/2026
Postdoc Fellowship 🚨 (Sept 30) We're hiring a postdoc on our ORIGINS Data Science Lab fellowship. The position allows researchers in particle physics to pursue their independent data-science / AI-related research vision in the context of our Excellence Cluster. inspirehep.net/jobs/3199251
inspirehep.net
INSPIRE
044
Aishik Ghosh @aishikghosh.bsky.social · 02/09/2026
As our Physics-AI research area continues to grow, @gtsciences.bsky.social is looking for a new faculty in physics! www.apsphysicsjobs. om/job/32794/open-rank-tenured-tenure-track-position-in-physics-artificial-intelligence-machine-learning/
apsphysicsjobs.com
Open-Rank, Tenured/Tenure Track Position in Physics - Artificial Intelligence/Machine Learning job with Georgia Institute of Technology - School of Physics | 32794
Open-rank tenured/tenure-track faculty position at the interface between machine learning and physics.
001
Aishik Ghosh @aishikghosh.bsky.social · 25/08/2026
New paper: An RL algorithm that incorporates 𝗮𝘂𝘁𝗼𝗺𝗮𝘁𝗲𝗱 𝗿𝗲𝗮𝘀𝗼𝗻𝗶𝗻𝗴 concepts to leverage rich feedback from physics software! A fun collaboration with Vijay Ganesh, led by Piyush Jha, together with Jake, Victoria, and Max from AMBer. arxiv.org/abs/2608.20686
120
Reposted by Aishik Ghosh
Virginia Gewin @virginiagewin.bsky.social · 08/07/2026
For my latest @nature.com piece, I talked to Ryan Rising, who is trying to build a prison-to-academia pipeline, informed by his own experience in incarceration. "At the core of my work is a simple idea: the people who are most affected by a problem are the ones closest to its solution."
nature.com
I want to see a prison-to-PhD pipeline
Ryan Rising creates programmes that help people who have been incarcerated to access academic opportunities.
1187
Aishik Ghosh @aishikghosh.bsky.social · 13/06/2026
Went on a four-hour bike ride today on the new section of the @atlantabeltline.org. Patches of pristine nature, followed by lively neighbourhoods. Wonder how the city will evolve around it in the next years.
010
Aishik Ghosh @aishikghosh.bsky.social · 03/06/2026
Could Christiano and Messi get along? Dennis and Melissa sure can, in an ATLAS-CMS collaborative effort to explain anomaly detection ;)
000
Aishik Ghosh @aishikghosh.bsky.social · 03/06/2026
Today Sofia Palacios Schweitzer introduces GANs as 'early attempts' in her generative models lecture ...👴
020
Aishik Ghosh @aishikghosh.bsky.social · 01/06/2026
And we're off! The Machine Learning for Fundamental Physics School 2026 starts at @gtsciences.bsky.social. Melissa Quinnan introduces foundational concepts to a room full of eager learners
031
Aishik Ghosh @aishikghosh.bsky.social · 11/05/2026
Such fun stories, from understanding sheep brain damage to searching for dark matter. My favourite was reading about moments when you find out something that the rest of the world doesn't know yet.
031
Reposted by Aishik Ghosh
Daniel Whiteson @danielwhiteson.bsky.social · 01/05/2026
Science communication people! Come tell us about your experience at the APS DPF meeting! Submit your abstract by the May 11 deadline: indico.fnal.gov/event/72820/...
063
Aishik Ghosh @aishikghosh.bsky.social · 19/03/2026
The Machine Learning for Fundamental Physics School is back! This time bigger and in a new location: Georgia Institute of Technology (@gtsciences.bsky.social)! We can cover the domestic travel and accommodation of most students and ECRs participating. Apply soon! indico.global/event/17000/
indico.global
Machine Learning for Fundamental Physics School (ML4FP) 2026
The Machine Learning for Fundamental Physics School (ML4FP) 2026 will be held at the Georgia Institute of Technology from June 1 to June 5, 2026. The event is organized with support from Oak Ridge Nat...
042
Aishik Ghosh @aishikghosh.bsky.social · 18/11/2025
Our two new research areas are now live!
020
Aishik Ghosh @aishikghosh.bsky.social · 11/11/2025
📢 𝐆𝐫𝐚𝐝 𝐚𝐝𝐦𝐢𝐬𝐬𝐢𝐨𝐧𝐬 𝐨𝐩𝐞𝐧, 𝐞𝐚𝐫𝐥𝐢𝐞𝐫 𝐝𝐞𝐚𝐝𝐥𝐢𝐧𝐞 𝐭𝐡𝐢𝐬 𝐲𝐞𝐚𝐫!
 Physics at 𝐆𝐞𝐨𝐫𝐠𝐢𝐚 𝐓𝐞𝐜𝐡 is accepting applications. 𝐌𝐲 𝐠𝐫𝐨𝐮𝐩 𝐨𝐧 𝐀𝐈 ∩ 𝐩𝐡𝐲𝐬𝐢𝐜𝐬 𝐢𝐬 𝐠𝐫𝐨𝐰𝐢𝐧𝐠! So if you know students interested in 𝐟𝐮𝐧𝐝𝐚𝐦𝐞𝐧𝐭𝐚𝐥 𝐩𝐡𝐲𝐬𝐢𝐜𝐬 𝐨𝐫 𝐚𝐬𝐭𝐫𝐨, please share this.
 🗓️ Deadline: 𝐃𝐞𝐜𝐞𝐦𝐛𝐞𝐫 𝟏𝟓
 
🔗 physics.gatech.edu/academics/gr...
physics.gatech.edu
Admissions Information
Prospective physics graduate students are welcome to contact faculty members to inquire about their research program. However, individual faculty members cannot accept students into the graduate progr...
032
Aishik Ghosh @aishikghosh.bsky.social · 10/11/2025
📢𝐉𝐨𝐛 𝐚𝐥𝐞𝐫𝐭: Postdoc position(s) in 𝐀𝐈 𝐟𝐨𝐫 𝐟𝐮𝐧𝐝𝐚𝐦𝐞𝐧𝐭𝐚𝐥 𝐩𝐡𝐲𝐬𝐢𝐜𝐬 focusing on either 𝐬𝐭𝐚𝐭𝐢𝐬𝐭𝐢𝐜𝐚𝐥 𝐢𝐧𝐟𝐞𝐫𝐞𝐧𝐜𝐞 or 𝐀𝐈-𝐚𝐬𝐬𝐢𝐬𝐭𝐞𝐝 𝐭𝐡𝐞𝐨𝐫𝐲. 🏙️Join my new group at 𝐆𝐞𝐨𝐫𝐠𝐢𝐚 𝐓𝐞𝐜𝐡, based in 𝐰𝐨𝐧𝐝𝐞𝐫𝐟𝐮𝐥 𝐌𝐢𝐝𝐭𝐨𝐰𝐧 𝐀𝐭𝐥𝐚𝐧𝐭𝐚! 🗓️ Reviews begin sooner, deadline: 𝟓𝐭𝐡 𝐃𝐞𝐜𝐞𝐦𝐛𝐞𝐫 💬 Questions: Reach out! 🔗 inspirehep.net/jobs/2962185
inspirehep.net
INSPIRE
042
Reposted by Aishik Ghosh
Lukas Heinrich @lukasheinrich.com · 31/10/2025
🚨 Job Alert We're hiring our first Postdoc to work with us on our @erc.europa.eu Project on Generative AI for Particle Physics. Check out the details below and don't hesitate to get in touch or spread the word! Deadline: Nov 30th inspirehep.net/jobs/3075448
lnkd.in
LinkedIn
This link will take you to a page that’s not on LinkedIn
0119
Aishik Ghosh @aishikghosh.bsky.social · 16/10/2025
Setting up my research group Slack workspace (free version). Has anyone considered Discord / Zulip / something else? @marielpettee.bsky.social @lukasheinrich.com
200
Reposted by Aishik Ghosh
Yvette Cendes @whereisyvette.bsky.social · 08/10/2025
Yeah, even crazier- last year for my postdoc ad a full half of the applications legit never made reference to anything my lab does and how my research would connect to theirs. You are literally in the top half of applicants for just TRYING to draw a connection in a sentence in the cover letter!
071
Aishik Ghosh @aishikghosh.bsky.social · 25/09/2025
Like AI + Physics, which is a well-developed field but we're still only scratching the surface of what we can do!
010
Aishik Ghosh @aishikghosh.bsky.social · 26/08/2025
At the launch event for ‪@gtsciences.bsky.social‬'s AI4Science Centre: ai4science.ai.gatech.edu. With colleagues from psychology, math, earth sciences and everything in between. Looking forward to all the cross-pollination within the sciences and also with industry!
121
Aishik Ghosh @aishikghosh.bsky.social · 14/08/2025
A little comment like one of these makes my week. Teaching and mentorship is easily the most rewarding aspect of academia. Makes it all worth it. Thanks again to all the students who came to ML4FP and interacted with us for a week. Your positive comments mean the word to us!
100
Aishik Ghosh @aishikghosh.bsky.social · 08/08/2025
Today we have the ATLAS, CMS and Neutrino parallel sessions at the ML4FP School. Julia Gonski give us an overview of ML in ATLAS
100
Aishik Ghosh @aishikghosh.bsky.social · 07/08/2025
GPT5's explanation for FTS is quite impressive, especially where it gives an intuitive explanation that is not just directly lifted from the paper. Makes it easy to learn a new statistics concept. chatgpt.com/s/t_6894ece0...
chatgpt.com
GPT-5 vs GPT-4
010
Aishik Ghosh @aishikghosh.bsky.social · 04/08/2025
And we're off! Yifan Chen welcomes students to the Machine Learning for Fundamental Physics School 2025!
261
Aishik Ghosh @aishikghosh.bsky.social · 28/07/2025
What if you could beat the Likelihood Ratio Test? A fun and potentially transformational phy-statistics paper with Ann Lee, James Carzon, @rafael-izbicki.bsky.social, luca Masserano and @danielwhiteson.bsky.social arxiv.org/abs/2507.17831
arxiv.org
On Focusing Statistical Power for Searches and Measurements in Particle Physics
Particle physics experiments rely on the (generalised) likelihood ratio test (LRT) for searches and measurements, which consist of composite hypothesis tests. However, this test is not guaranteed to b...
152
Reposted by Aishik Ghosh
Oz Amram @ozamram.bsky.social · 14/07/2025
Happy this paper is finally on arxiv! A fun mix of physics (jet substructure) being used to calibrate the performance of ML algorithms (jet taggers) to get proper uncertainties Now a standard CMS tool for interpreting searches for exotic jets, used in multiple analyses
021
Aishik Ghosh @aishikghosh.bsky.social · 04/07/2025
New paper: Constraining the Higgs self-coupling from the off-shell single Higgs with NSBI. Work with Tae Hyoun Park, Maximilian Griese & Ulrich Haisch. arxiv.org/abs/2507.02032 
110
Reposted by Aishik Ghosh
Lukas Heinrich @lukasheinrich.com · 24/06/2025
So happy to see @aishikghosh.bsky.social thrive - he’s been one of the drivers of AI in HEP and I can’t wait to see his lab start up - take note of the postdoc position coming up.
041
Aishik Ghosh @aishikghosh.bsky.social · 23/06/2025
Some happy news — I’ve accepted a tenure-track faculty position in the School of Physics at Georgia Tech! My group will work at the intersection of AI and fundamental physics & astrophysics. GT is making massive investments in these directions, and I’m hiring a postdoc — more soon!
060
Aishik Ghosh @aishikghosh.bsky.social · 23/06/2025
Delighted to see our work featured in the news! Two key players mentioned but unfortunately not explicitly named: discussions with Kyle Cranmer and Johann Brehmer were crucial in the initial stages. Also Jay, Rafael were central in making it a reality in ATLAS.
092
Reposted by Aishik Ghosh
Gilles Louppe @glouppe.bsky.social · 23/06/2025
Our work on simulation-based inference at the LHC is featured in @arstechnica.com! Well done @aishikghosh.bsky.social @sandesarajay.bsky.social 🙌 arstechnica.com/science/2025...
arstechnica.com
How a grad student got LHC data to play nice with quantum interference
New approach is already having an impact on the experiment’s plans for future work.
0204
Aishik Ghosh @aishikghosh.bsky.social · 11/06/2025
Wondered what it would take for AI agents to design and test new theories for fundamental physics, just like a physicist? We show how, an example in neutrino model building! Paper with Jake, Max, Victoria, Jason leading crucial aspects, also @danielwhiteson.bsky.social . arxiv.org/abs/2506.08080
183
Aishik Ghosh @aishikghosh.bsky.social · 06/04/2025
Breakthrough Prize awarded to LHC experiments for the study of Higgs properties (to which I contributed), rare processes, matter-antimatter asymmetry, and many other areas of research
031
Reposted by Aishik Ghosh
Daniel Whiteson @danielwhiteson.bsky.social · 06/01/2025
New paper! Learning Broken Symmetries with Approximate Invariance Led by HIGH SCHOOL STUDENT Seth Nabat, with Aishik_Ghosh, Ed Witkowski and GregorKasieczka. arxiv.org/abs/2412.18773
arxiv.org
Learning Broken Symmetries with Approximate Invariance
Recognizing symmetries in data allows for significant boosts in neural network training, which is especially important where training data are limited. In many cases, however, the exact underlying sym...
1112
Reposted by Aishik Ghosh
Gregor Kasieczka @kasieczka.bsky.social · 06/01/2025
We show that a hybrid (conserving+breaking) architecture combines the advantages of symmetry-conserving networks (fast learning) and breaking ones (higher maximum performance). Great work by Seth with @aishikghosh.bsky.social, Ed, @danielwhiteson.bsky.social Full paper: arxiv.org/abs/2412.18773
071
Reposted by Aishik Ghosh
Gregor Kasieczka @kasieczka.bsky.social · 06/01/2025
Now(ish) on arxiv: Learning Broken Symmetries with Approximate Invariance Invariances (or, as physicists call them: symmetries) of the data can be baked into a ML model to improve performance or data efficiency. However, in reality, these symmetries are often broken. How to deal with that?
182
Reposted by Aishik Ghosh
UW–Madison Data Science Institute @uwdsi.bsky.social · 19/12/2024
DSI Research Scientist @matthewfeickert.com focuses on data science applications and #opensource software for particle physics. Read his story: ospo.wisc.edu/community/pr...
0102
Reposted by Aishik Ghosh
Lukas Heinrich @lukasheinrich.com · 09/12/2024
It’s a pleasure to host @aishikghosh.bsky.social in Munich, where he he’s sharing the NSBI story that he has pushed in @atlasexperiment.bsky.social for many years and recently came out
Aishik Ghosh giving a seminar at the Max Planck Institute for Physics
292
Aishik Ghosh @aishikghosh.bsky.social · 04/12/2024
The propaganda slide about how the next discovery may be made in particle physics, from my CERN seminar: indico.cern.ch/event/1479992/
051
Reposted by Aishik Ghosh
Gilles Louppe @glouppe.bsky.social · 03/12/2024
Simulation-based inference in ATLAS! 👀 Very proud to have contributed to this project, from its inception 10 years ago, to its publication this morning. NSBI replaces histogram-based analysis with a per-event analysis based likelihood-ratios modeled by NNs. Gains in sensitivity are substantial!
1141
Aishik Ghosh @aishikghosh.bsky.social · 03/12/2024
First post on BlueSky! I'm excited to give a seminar at #CERN tomorrow on 6 years of work developing a complete statistical framework for high-dimensional inference of the Higgs width. Simulation-based inference on actual collision data in ATLAS, profiling all systematic uncertainties!
1152