📢 Come to our @NeurIPSConf tutorial on Advances in Bayesian Optimization Dec 5, Mon, 11am to 1:30pm PST bayesopt-tutorial.github.io/ Speakers: @VGAglietti, Jake Gardner, me Panelists: @StefanieJegelka, @jmhernandez233, Roman Garnett, @eytan, @syrineblk Post your questions below.

Congratulations to Kaiming and ResNet. ResNet is 10 years old but Kaiming remains as young and brilliant as ever! We are deeply grateful for you and for everything you have done for computer vision, Kaiming (though he refuses to be on social media)

Avi Wigderson is the only person in history to have won both a Turing Award (computer science) and Abel Prize (math). I interviewed him all about his field. We discussed: • His intuition on a proof of P vs NP • Why we use SAT solvers for most NP problems • Zero knowledge proofs and their impact • Quantum computation and implications • Math and computer science's relationship Where to watch: • YouTube: youtu.be/5GUcvSAJcJw • Spotify: open.spotify.com/episode/4JZ… • Apple Podcasts: podcasts.apple.com/us/podcas… • Transcript: developing.dev/p/turing-awar… Thank you to this episode's sponsors for supporting my work: • WorkOS: makes your app Enterprise Ready with easy to use APIs to add SSO, SCIM, RBAC, and more in just a few lines of code, check them out at workos.com/ Timestamps: 00:00 - Intro 01:08 - P vs NP 14:51 - What if you relaxed correctness 25:38 - Why NP complete problems are equivalent 30:33 - Space vs time complexity 43:06 - Why people use SAT solvers 45:53 - Randomness is a resource 55:48 - Randomness depends on computational power 01:21:20 - Zero knowledge proofs and their significance 01:38:30 - Quantum computation and why it matters 01:56:24 - Math vs computer science 02:08:16 - Major breakthroughs and his experience 02:12:31 - Advice for his younger self 02:14:48 - Outro

Attention @arxiv authors: Our Code of Conduct states that by signing your name as an author of a paper, each author takes full responsibility for all its contents, irrespective of how the contents were generated. 1/

Excited to see my student’s work on Flux Matching out. It turns out you can learn a much broader class of vector fields with the data distribution as stationary (not just the score). This lets you enforce useful properties like fast mixing, and it already works on high-dimensional image datasets!

Ten years in academia and the best part has not been what many value most ie freedom to pursue your ideas. It’s experiencing your students grow and go on to incredible trajectories. What I’ve come to know about myself is that I value permanence, presence, and people. And for all the illusions that institutions, titles, awards etc offer, none at all come close to this: watching a human absorb, even in tiny amounts, the care and effort you’ve put into trying your best to just be there for them.

We have extended the paper submission deadline for our @icmlconf workshop to May 7th AOE due to NeurIPS paper deadline. @deshwal_aryan @HarukaKiyohara_ @syrineblk @willieneis @htnghia1187 @thanhnguyentang

I'm excited to be at #ICLR2026 this week presenting joint work with Elif Ertekin, Peter Orbanz, and @ryan_p_adams on "A Single Architecture for Representing Invariance Under Any Space Group." (1/3)

I have a postdoc position available to work on machine-learning guided antibiotic discovery. Application deadline 15 May 2026. jobs.cam.ac.uk/job/55258/

Conformal Margin Risk Minimization: An Envelope Framework for Robust Learning under Label Noise ift.tt/4cxoMsI

We’re hiring! Oregon State University is recruiting a Tenure-Track Faculty Position in Robotics. jobs.oregonstate.edu/posting… Hard to beat the Pacific Northwest excellent robotics graduate program combo.

Come to our @RealAAAI AAAI-2026 tutorial tomorrow morning. Title: Black-Box Optimization from Offline Datasets Date and Time: Jan 21 @ 8:30am in Room Opal 107 Slides: offlineopt-tutorial.github.i… w/ Azza @azza_fadhel,Aryan @deshwal_aryan,Nghia @htnghia1187

check out our new paper on adaptively allocating Monte Carlo samples of MOF-adsorbate configurations for efficient, multi-fidelity computational screening of MOFs for an adsorption property using molecular simulations. we view each MOF as a slot machine, then apply top-K arm identification algorithms, developed for the multi-armed bandit problem in reinforcement learning, to sequentially and adaptively allocate the Monte Carlo samples among the MOFs, in a data-driven manner, to obtain the most accurate top-K subset under a fixed sample budget. we propose our own heuristic, narrowing exploration. 🙏 led by my PhD student Qia Ke, co-advised by @janadoppa, @scobo06, @huazheng_wang. pubs.acs.org/doi/full/10.102…

Today's conversations about AI-assisted programming are strikingly similar to those from decades ago about the choice between low-level languages like C versus high-level languages like Python. I was in college back then and some of our professors reassured us that the same issues had come up in the assembly-vs-compiled-languages debate from their own student days! (If I were to guess, the switch from machine code to assembly even earlier must have led to similar discussions as well.) The trade-off is always the same: productivity versus control. And the challenge is how to switch to the new paradigm in a way that enhances your skills (at least the ones you care about) instead of offloading too much and letting your skills atrophy. Some approaches prove too hasty. Vibe coding is turning out to be a dead end because it offloads too much, just as WYSIWYG editors were a dead end for building web apps. But that doesn't mean we were forced to stick to raw HTML/JS: frameworks turned out to be the way forward. When a new paradigm comes along, it takes months if not years of practice to figure out how to make it work for you. There are always many people dismissing the new thing too quickly. I was one! There are some embarrassing mailing list posts from the early 2000s in which I complained about Python and kids who can't code like real programmers do 🤦 While it's good to be open-minded, I'm not saying everyone needs to jump on the bandwagon. After all, low-level programming languages haven't gone away. Of course, some people claim that AI is unlike previous waves of automation and can replace programmers. Maybe. The reason I disagree — and see AI as parallel to previous waves of productivity improvements in software engineering — is fourfold. (1) It's a matter of accountability, not just capability. (2) Writing the code was never the bottleneck. (3) I think we're underestimating the ability of experts to stay on top of even rapid AI capability increases by using these tools to dramatically expand what they can build, how well, and how quickly. (4) As these productivity improvements take shape, the potential growth in _demand_ for software is practically infinite, unlike trades where there is a fixed amount of work that needs to get done. For example, the idea that a car would contain ~100 million lines of code would have seemed head-explodingly implausible in the early days of programming. Many people have observed that software seems to be one of the only fields that is undergoing a rapid transformation due to AI. The usual reason they give is that capability improvements in AI coding have been particularly rapid. I think this is only part of the story. The bigger factor is structural. Software has a history of repeatedly undergoing seismic shifts in the technologies of production, so it has never had time or the cultural inclination to ossify institutional processes around particular ways of doing things.

Imagine moving a heavy object with a joystick—through a swarm of quadruped-arm robots. 🕹️ decPLM: decentralized RL for multi-robot pinch-lift-move. • No comms or rigid links • Hierarchical RL constellation reward • 2→ N robots, sim→real 🔗 decplm.github.io/

Join our NeurIPS 2025 social event: The Role of AI in Scientific Peer Review. Help build community and explore solutions for a fair, efficient, and transparent peer review system. Wed. Dec. 3rd, 7:00 PM – 9:00 PM #neurips2025

A visionary educator, researcher, and pioneer, Prof. Vaidyeswaran Rajaraman will always be remembered as one of the foremost architects of computer science education in India. Joining IIT Kanpur in 1963 as a faculty member in the Department of Electrical Engineering, he played a pivotal role in shaping the institute’s early computing curriculum. In 1965, with the encouragement of Prof. H. K. Kesavan and in collaboration with his colleagues, he launched an M. Tech. programme with Computer Science as an option — the first time the subject was introduced as an academic discipline in India. His foresight and leadership were instrumental in laying the foundation for computer science education in the country. A recipient of the Shanti Swarup Bhatnagar Prize, Om Prakash Bhasin Award, Homi Bhabha Prize, and the Padma Bhushan, Prof. Rajaraman was a mentor who inspired countless students and colleagues through his humility, clarity of thought, and passion for teaching. As the institute mourns the loss of Prof. Rajaraman, we also celebrate a life devoted to knowledge, innovation, and the pursuit of excellence — a legacy that continues to illuminate India’s scientific and technological journey.