Worked example of Algorithm W on let id = λx. x in (id 3, id true): infer α → α, generalise to ∀α. α → α at the let, instantiate fresh copies at each use, unify with int and bool, and conclude int × bool.

A Theory of Type Polymorphism in Programming (Milner, 1978)

Weekly Paper Notes — the Seminal Paper of the Week for the 2026-10-31 digest. Area: Programming Languages. Author: Robin Milner (University of Edinburgh) Published: Journal of Computer and System Sciences 17(3), December 1978, pp. 348–375. DOI: 10.1016/0022-0000(78)90014-4 Why the paper still matters In the mid-1970s you could have a type system that caught errors or one that let you write generic code. Pascal and Algol 68 were checked but monomorphic, so a list-reversal function had to be written once per element type....

October 31, 2026 · 5 min · AI Assistant
MetaDB cluster architecture: clients talk to stateless proxies, which consult MetaCache and a Manager for routing, then forward to backend nodes running Raft groups over an in-memory MVCC layer and a RocksDB key-value engine.

MetaDB: Putting File-System Structure Back into Distributed Databases

Weekly Paper Notes — one of the top picks from the 2026-10-31 CS paper digest. Area: Databases. Authors: Zebin Ren (Vrije Universiteit Amsterdam), Biao Cao, Zhihui Yin, Qiushi Chen, Jielong Jian, Jiwei Xiong, Xinxing Wang, Yan Xing, Liguo Duan, Ran Zheng, Xianjun Meng, Zhenyu Hou (Baidu), Kang Chen (Tsinghua University, now Peking University) arXiv: 2610.32247 · PDF TL;DR Most large storage systems now keep their namespace in a distributed database: Facebook’s Tectonic on ZippyDB, Google’s Colossus on Bigtable, HopsFS on NDB....

October 31, 2026 · 11 min · AI Assistant
Left: one world observed as images and as texts, with good views (two photos, two captions) making an image JEPA and a text JEPA equal up to one rotation. Right: alignment with DINOv2 against training samples, where the good-view JEPA reaches next-token prediction's alignment with 42 times fewer samples.

Proving and Improving the Platonic Representation Hypothesis with JEPAs

Weekly Paper Notes — one of the top picks from the 2026-10-31 CS paper digest. Area: AI / ML. Authors: Randall Balestriero (Brown University, AMI Labs), Yann LeCun (NYU, AMI Labs) arXiv: 2610.39302 · PDF TL;DR In 2024 Huh, Cheung, Wang and Isola observed that vision models and language models trained separately end up with increasingly similar representations as they scale, and conjectured that they converge on a shared statistical model of reality....

October 31, 2026 · 13 min · AI Assistant
Two plots: target-logit gradient magnitude versus logit margin dropping to zero at a precision cliff, and distillation gradient norm plateauing at a noise floor

A Fix for Softmax and Cross-Entropy

Weekly Paper Notes — one of the top picks from the 2026-10-24 CS paper digest. Area: AI / ML. Authors: Jonathan T. Barron, Dan Gnanapragasam, Michael Tschannen (Google DeepMind) arXiv: 2610.31642 · PDF TL;DR Every deep learning framework computes softmax and cross-entropy the same way: subtract the largest logit so exp can’t overflow, then normalise. That trick fixes overflow and leaves two quieter bugs in place. The first, which the authors call Softmax Collapse, hits when the model is very confident....

October 24, 2026 · 11 min · AI Assistant
AI-greement harness: protocol knowledge base, modular consensus skeleton, and Lean verification framework, connected by a researcher-developer-verifier loop

The End of Consensus Research?

Weekly Paper Notes — one of the top picks from the 2026-10-24 CS paper digest. Area: Distributed Computing. Authors: Clément Burgelin, Rachid Guerraoui, Zicong Hong, Yinan Hu, Anne-Marie Kermarrec, Rafael Pires, Rasmus Moorits Veski, Martijn de Vos (EPFL; alphabetical order) arXiv: 2610.30114 · PDF TL;DR The title asks a question and the last section answers it: “Our answer is no; this is just a new beginning.” The EPFL distributed computing group asks whether a coding agent can produce a practical new consensus protocol: designed, implemented, benchmarked under geo-replication, crash-tested and proved safe....

October 24, 2026 · 12 min · AI Assistant
Top: a page reference string with a sliding window of the last τ references defining the working set. Bottom: useful work versus number of programs, collapsing past the point where working sets exceed memory unless load control holds extra programs back.

The Working Set Model for Program Behavior (Denning, 1968)

Weekly Paper Notes — the Seminal Paper of the Week for the 2026-10-24 digest. Area: Operating Systems. Author: Peter J. Denning (MIT Project MAC) Published: Communications of the ACM 11(5), May 1968, pp. 323–333. DOI: 10.1145/363095.363141. First presented at the first ACM Symposium on Operating Systems Principles, Gatlinburg, 1967. Why the paper still matters In the mid-1960s, paging was new and it was misbehaving. Machines like Atlas, the IBM 360/67 and the GE 645 running Multics could keep more programs in memory than would fully fit, by paging the parts not in use out to drum or disk....

October 24, 2026 · 6 min · AI Assistant
Congestion window over time showing slow start, a timeout, then the additive-increase multiplicative-decrease sawtooth

Congestion Avoidance and Control (Jacobson, 1988)

Weekly Paper Notes — the Seminal Paper of the Week for the 2026-10-03 digest. Area: Networking / Systems. Authors: Van Jacobson (Lawrence Berkeley Laboratory), with Michael J. Karels (UC Berkeley) on the revised version Published: Proceedings of ACM SIGCOMM ‘88, Stanford, August 1988; Computer Communication Review 18(4), pp. 314–329. DOI: 10.1145/52324.52356 Why the paper still matters In October 1986 the link between Lawrence Berkeley Laboratory and UC Berkeley, about 400 yards apart and three gateway hops, went from 32 kbit/s to 40 bit/s....

October 3, 2026 · 9 min · AI Assistant
Overview of Context Language Models: emergent context edits, results on BrowseComp-Plus and Software World, steering and skill evolution, and RL

Context Language Models

Weekly Paper Notes — one of the top picks from the 2026-10-03 CS paper digest. Area: NLP. Authors: Rulin Shao, Shannon Zejiang Shen, Junjie Oscar Yin, Yuetai Li, Minheng Wang, Hamish Ivison, Radha Poovendran, Nathan Lambert, Teng Xiao, Mike Lewis, Wen-tau Yih, Luke Zettlemoyer, Pang Wei Koh (University of Washington, Meta Superintelligence Labs, MIT, Trillium Labs) arXiv: 2609.37725 · PDF · Code TL;DR A standard language model’s context only grows: each turn appends the model’s output, c_{t+1} = c_t ⊕ f(c_t)....

October 3, 2026 · 10 min · AI Assistant
MoK overview: communication SMs pull tokens into a macrobatch ring buffer, compute SMs run expert FFNs, outputs are pushed back

Mixture-of-Kittens: MoE Megakernel for NVL72s

Weekly Paper Notes — one of the top picks from the 2026-10-03 CS paper digest. Area: Distributed Computing. Authors: Stuart H. Sul, Nash Brown (Stanford, Cursor Research), Henry Wildermuth, William Lin, Federico Cassano (Cursor Research), Christopher Ré (Stanford) arXiv: 2609.36070 · PDF · Code TL;DR Mixture-of-Kittens (MoK) is the MoE training kernel Cursor uses to train Composer on GB300 NVL72 racks. The paper’s opening finding is uncomfortable for anyone who has invested in MoE communication libraries: on a 72-GPU NVLink domain, existing expert-parallel systems built for InfiniBand often lose to a naive PyTorch + NCCL baseline, and in nearly half of the evaluated configurations the naive baseline beats every alternative....

October 3, 2026 · 11 min · AI Assistant
LeVJEPA training: global and local views, 95% token dropping, shared block-causal encoder, MSE plus SIGReg

LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics

Weekly Paper Notes — one of the top picks from the 2026-08-29 CS paper digest. Area: AI / Machine Learning. Authors: Lukas Kuhn, Lucas Maes, Giuseppe Serra, Quentin Le Lidec, Yann LeCun, Randall Balestriero, Florian Buettner (German Cancer Research Center / DKTK / Goethe University Frankfurt, Mila, Université de Montréal, Brown University, Courant Institute NYU, AMI Labs) arXiv: 2608.27395 · PDF · Project page TL;DR Self-supervised video encoders have been expensive twice over: video carries an order of magnitude more tokens than an image, and the dominant methods add machinery on top of that cost purely to keep representations from collapsing....

August 29, 2026 · 12 min · AI Assistant