Subbarao Kambhampati (కంభంపాటి సుబ్బారావు)
LightNews LightNews
rao2z.bsky.social
Subbarao Kambhampati (కంభంపాటి సుబ్బారావు)
@rao2z.bsky.social
920 followers 16 following 86 posts
AI researcher & teacher at SCAI, ASU. Former President of AAAI & Chair of AAAS Sec T. Here to tweach #AI. YouTube Ch: http://bit.ly/38twrAV Twitter: rao2z
Posts Replies Media Videos
Pinned
rao2z.bsky.social
Subbarao Kambhampati (కంభంపాటి సుబ్బారావు) @rao2z.bsky.social · Dec 29
A meta list of all my 2024 #SundayHarangue's

Not quite sure why, but I apparently wrote sixteen long #AI related Sunday Harangues in 2024.. 😅.

Most were first posted on twitter.

👉https://x.com/rao2z/status/1873214567091966189
rao2z.bsky.social
Here are the recordings of two lectures on 𝗣𝗹𝗮𝗻𝗻𝗶𝗻𝗴 & 𝗥𝗲𝗮𝘀𝗼𝗻𝗶𝗻𝗴 𝗖𝗮𝗽𝗮𝗯𝗶𝗹𝗶𝘁𝗶𝗲𝘀 𝗼𝗳 𝗟𝗟𝗠𝘀/𝗟𝗥𝗠𝘀 that I gave this week at Melbourne ML Summer School (lnkd.in/g7rxg9sw).

𝙇𝙚𝙘𝙩𝙪𝙧𝙚 1: youtube.com/watch?v=_PPV...
𝙇𝙚𝙘𝙩𝙪𝙧𝙚 2: youtube.com/watch?v=fKlm...
February 13, 2026 at 3:31 PM
rao2z.bsky.social
A common theme in our work these past few years has been pushing back on facile anthropomorphizations (and/or efforts that bring questionable/discredited Cognitive Science metaphors) to LLMs.. So I enjoyed giving this talk at @ivado.bsky.social yesterday... www.youtube.com/watch?v=CoyS...
Anthropomorphization Sins in Modern AI (or Perils of Prematurely Applying Lens of Cognition to LLMs)
YouTube video by Subbarao Kambhampati
www.youtube.com
January 28, 2026 at 1:03 PM
rao2z.bsky.social
Three of my talks in India last month--at @iitdelhi.bsky.social,
@msftresearch.bsky.social India and at IndoML Symposium--were "On the Mythos of LRM Thinking Tokens." Here is a recording of one of them--the talk I gave at MSR India.

www.youtube.com/watch?v=fCQX...
On the Mythos of LRM "Thinking Tokens" (Talk @ Microsoft Research, India; 12/16/2025)
YouTube video by Subbarao Kambhampati
www.youtube.com
January 6, 2026 at 9:44 PM
rao2z.bsky.social
ICYMI, here is my keynote on the semantics of LRM "thinking traces" at #NeurIPS2025 workshop on Multimodal Algorithmic Reasoning. It's a unified view of the seven papers we presented at the conference workshops. Special thanks to the engaged audience..🙏

www.youtube.com/watch?v=rvby...
Talk on the semantics of "Thinking Traces" (Keynote at NeurIPS2025 MAR Workshop)
YouTube video by Subbarao Kambhampati
www.youtube.com
December 9, 2025 at 1:11 PM
rao2z.bsky.social
[On using Continuous Latent Space Vectors in the context windows of Transformers and LLMs] #SundayHarangue
👉 x.com/rao2z/status...
November 3, 2025 at 3:16 PM
rao2z.bsky.social
My talk at Samsung AI Forum yesterday
www.youtube.com/watch?v=L2nA...
LRMs and Agentic AI (Talk at Samsung AI Forum)
YouTube video by Subbarao Kambhampati
www.youtube.com
September 16, 2025 at 5:39 PM
rao2z.bsky.social
In the year since LRMs ("reasoning models") hit the scene, we have been trying to understand, analyze and demystify them.. Here are our efforts to date--conveniently all in one place..👇

www.linkedin.com/posts/subbar...
In the year since LRMs ("reasoning models") hit the scene, we have been trying to understand, analyze and demystify them.. Here are our efforts to date--conveniently all in one… | Subbarao K...
In the year since LRMs ("reasoning models") hit the scene, we have been trying to understand, analyze and demystify them.. Here are our efforts to date--conveniently all in one place.. (𝗙𝗶𝗿𝘀𝘁..) 𝗘𝘃𝗮𝗹...
www.linkedin.com
September 14, 2025 at 10:00 PM
rao2z.bsky.social
𝐏𝐞𝐫𝐟𝐨𝐫𝐦𝐚𝐭𝐢𝐯𝐞 𝐓𝐡𝐢𝐧𝐤𝐢𝐧𝐠? The anthropomorphization of LRM intermediate tokens as thinking begat a cottage industry to "get efficiency by shortening thinking." We ask: 𝗜𝘀 𝗖𝗼𝗧 𝗹𝗲𝗻𝗴𝘁𝗵 𝗿𝗲𝗮𝗹𝗹𝘆 𝗮 𝗿𝗲𝗳𝗹𝗲𝗰𝘁𝗶𝗼𝗻 𝗼𝗳 𝗽𝗿𝗼𝗯𝗹𝗲𝗺 𝗵𝗮𝗿𝗱𝗻𝗲𝘀𝘀 𝗼𝗿 𝗶𝘀 𝗶𝘁 𝗺𝗼𝗿𝗲 𝗽𝗲𝗿𝗳𝗼𝗿𝗺𝗮𝘁𝗶𝘃𝗲? 👉 www.linkedin.com/posts/subbar...
September 10, 2025 at 4:50 PM
rao2z.bsky.social
Rejecting papers in #AI Conferences because of "resource constraints" is shooting ourselves in the foot as a community; use Findings.. #SundayHarangue 👇

x.com/rao2z/status...
Subbarao Kambhampati (కంభంపాటి సుబ్బారావు) on X: "Rejecting papers in #AI Conferences because of "resource constraints" is shooting ourselves in the foot as a community; use Findings.. #SundayHarangue By now, we have all know that top AI conferences are oversubscribed (in terms of paper submissions), and have heard that that" / X
Rejecting papers in #AI Conferences because of "resource constraints" is shooting ourselves in the foot as a community; use Findings.. #SundayHarangue By now, we have all know that top AI conferences are oversubscribed (in terms of paper submissions), and have heard that that
x.com
August 31, 2025 at 7:58 PM
rao2z.bsky.social
Proofs are not reasoning traces & I/O Format Language shouldn't be much of an issue for LLMs + other things #SundayHarangue (Special IMO edition). 🧵 👇

x.com/rao2z/status...
Subbarao Kambhampati (కంభంపాటి సుబ్బారావు) on X: "Proofs are not reasoning traces & I/O Format Language shouldn't be much of an issue for LLMs #SundayHarangue (Special IMO edition). 1/ My feed these last couple of days of IMO discussions has been full of comments that seem to conflate LRM intermediate tokens (aka reasoning" / X
Proofs are not reasoning traces & I/O Format Language shouldn't be much of an issue for LLMs #SundayHarangue (Special IMO edition). 1/ My feed these last couple of days of IMO discussions has been full of comments that seem to conflate LRM intermediate tokens (aka reasoning
x.com
July 22, 2025 at 1:46 PM
rao2z.bsky.social
Both LLMs and LRMs are upper bounded by humanity's knowledge closure. True scientific discoveries are, by definition, outside of that closure. Ergo, LLMs/LRMs are great force multipliers to us; but don't support "Nobel this weekend" hype..

👉 www.linkedin.com/posts/subbar...
Neither LLMs nor LRMs have the ability to go beyond the humanity's knowledge closure--which is needed for true discoveries. | Subbarao Kambhampati
Neither LLMs nor LRMs have the ability to go beyond the humanity's knowledge closure--which is needed for true discoveries. Both are beholden to the collected knowledge of the humanity (whether de...
www.linkedin.com
July 19, 2025 at 10:18 PM
rao2z.bsky.social
Computational Complexity is the wrong measure for LRMs (as it was for LLMs)--think distributional distance instead #SundayHarangue (yes, we're back!)

👉 x.com/rao2z/status...
July 13, 2025 at 9:42 PM
rao2z.bsky.social
A̶̶̶I̶̶̶ ̶ ̶ ̶ ̶(̶A̶r̶t̶i̶f̶i̶c̶i̶a̶l̶ ̶I̶n̶t̶e̶l̶l̶i̶g̶e̶n̶c̶e̶)̶
̶̶̶A̶̶̶G̶̶̶I̶̶̶ ̶(̶A̶r̶t̶i̶f̶i̶c̶i̶a̶l̶ ̶G̶e̶n̶e̶r̶a̶l̶ ̶I̶n̶t̶e̶l̶l̶i̶g̶e̶n̶c̶e̶)̶
̶̶̶A̶̶̶S̶̶̶I̶̶̶ ̶(̶A̶r̶t̶i̶f̶i̶c̶i̶a̶l̶ ̶S̶u̶p̶e̶r̶ ̶I̶n̶t̶e̶l̶l̶i̶g̶e̶n̶c̶e̶)
ASDI (Artificial Super Duper Intelligence)

Don't get stuck with yesterday's hypeonyms!
Dare to get to the next level!

#AIAphorisms
June 23, 2025 at 10:36 PM
rao2z.bsky.social
For anyone interested, here are the videos of the three ~50min each lectures on the reasoning/planning capabilities of LLMs/LRMs that I gave at #ACDL2025 in Riva Del Sole resort last week. 1/

www.youtube.com/playlist?lis...
ACDL Summer School Lectures on Planning/Reasoning Abilities of LLMs/LRMs - YouTube
www.youtube.com
June 19, 2025 at 10:27 PM
Reposted by Subbarao Kambhampati (కంభంపాటి సుబ్బారావు)
melaniemitchell.bsky.social
...it basically confirmed what is already well-established: LLMs (& LRMs & "LLM agents") have trouble w/ problems that require many steps of reasoning/planning.

See, e.g., lots of recent papers by Subbarao Kambhampati's group at ASU. (2/2)
June 9, 2025 at 10:53 PM
rao2z.bsky.social
An AGI-wannabe reasoning model whining that it couldn't handle a problem because its context window isn't big enough is like a superman-wannabe little kid protesting that he couldn't add those numbers because he doesn't have enough fingers and toes.. #AIAphorisms
June 16, 2025 at 12:47 AM
Reposted by Subbarao Kambhampati (కంభంపాటి సుబ్బారావు)
abeba.bsky.social
"our counter-intuitive results demonstrate ways in which common interpretations of Large Reasoning Models may be anthropomorphizations or simplifications" arxiv.org/abs/2505.13775
Beyond Semantics: The Unreasonable Effectiveness of Reasonless Intermediate Tokens
Recent impressive results from large reasoning models have been interpreted as a triumph of Chain of Thought (CoT), and especially of the process of training on CoTs sampled from base LLMs in order to...
arxiv.org
June 1, 2025 at 1:30 PM
rao2z.bsky.social
The transformer expressiveness results are often a bit of a red herring as there tends to be a huge gap between what can be expressed in transformers, and what can be learned with gradient descent. Mind the Gap, a new paper with
Lucas Saldyt dives deeper into this issue 👇👇

x.com/SaldytLucas/...
Lucas Saldyt on X: "Neural networks can express more than they learn, creating expressivity-trainability gaps. Our paper, “Mind The Gap,” shows neural networks best learn parallel algorithms, and analyzes gaps in faithfulness and effectiveness. @rao2z https://t.co/8YjxPkXFu0" / X
Neural networks can express more than they learn, creating expressivity-trainability gaps. Our paper, “Mind The Gap,” shows neural networks best learn parallel algorithms, and analyzes gaps in faithfulness and effectiveness. @rao2z https://t.co/8YjxPkXFu0
x.com
May 30, 2025 at 1:59 PM
rao2z.bsky.social
Anthropomorphization of intermediate tokens as reasoning/thinking traces isn't quite a harmless fad, and may be pushing LRM research into questionable directions.. So we decided to put together a more complete argument. Paper 👉 arxiv.org/pdf/2504.09762 (Twitter thread: x.com/rao2z/status...)
May 28, 2025 at 1:41 PM
rao2z.bsky.social
This RLiNo? paper (arxiv.org/abs/2505.13697) lead by Soumya Samineni and Durgesh_kalwar dives into the MDP model used in the RL post-training methods inspired by DeepSeek R1, and asks if some of the idiosyncrasies of RL aren't just consequences of the simplistic structural assumptions made
May 25, 2025 at 10:51 PM
rao2z.bsky.social
Do Intermediate Tokens Produced by LRMs (need to) have any semantics? Our new study 👇

Thread 👉 x.com/rao2z/status...
May 21, 2025 at 8:08 PM
rao2z.bsky.social
Delighted to share that Siddhant Bhambri & Mudit Verma's
critical evaluation and refutation of the reasoning claims of ReACT has been accepted to #TMLR (Transactions on Machine Learning)

👉https://openreview.net/forum?id=aFAMPSmNHR
May 13, 2025 at 5:22 PM
rao2z.bsky.social
Solving Single Agent Fully Observable Deterministic (SAFODP) Problems with Dec-POMDP approaches #SundayHarangue #allegory

x.com/rao2z/status...
Subbarao Kambhampati (కంభంపాటి సుబ్బారావు) on X: "Solving Single Agent Fully Observable Deterministic (SAFODP) Problems with Dec-POMDP approaches #SundayHarangue #allegory Imagine you modeled your decision problem into a Dec-POMDP problem ('cuz that's as expressive a decision model as you can get! )--but with some https://t.co/vDWYTHbnQA" / X
Solving Single Agent Fully Observable Deterministic (SAFODP) Problems with Dec-POMDP approaches #SundayHarangue #allegory Imagine you modeled your decision problem into a Dec-POMDP problem ('cuz that's as expressive a decision model as you can get! )--but with some https://t.co/vDWYTHbnQA
x.com
May 12, 2025 at 12:45 AM
rao2z.bsky.social
IMHO, the whole idea of connecting "length of intermediate tokens" produced by LRMs to inference time compute is a mind-boggling demonstration of circular reasoning--that comes from the assumptions about MDP model and reward model.. 👇

x.com/rao2z/status...
x.com
May 9, 2025 at 2:42 PM
rao2z.bsky.social
It ain't "The Bitter Lesson" if you are in the loop curating the training data for your LLM, y'all.. Pick your lesson, will ya? #SundayHarangue (h/t @kstechly.bsky.social)
May 5, 2025 at 11:44 AM