arXiv Machine Learning
Jun 26
Generating Special Triangulations with Transformers
arXiv:2606. 26660v1 Announce Type: cross Abstract: Triangulations, i.
Sampling Triangulations and Calabi-Yau Threefolds with Autoregressive GNNs
arXiv:2605. 27770v2 Announce Type: cross Abstract: We introduce `dualGNN', an autoregressive message-passing GNN for sampling fine, regular triangulations (FRTs) of convex polytopes.
Related stories
arXiv AI
Jun 3
Exact equivariance, kept through training, buys zero-shot generalisation across the symmetry group
arXiv:2606. 03003v1 Announce Type: cross Abstract: A latent world model built from an equivariant encoder $E$ and an equivariant predictor $f$ inherits a provable symmetry of its training loss: when the world's dynamics genuinely carries a group $G$ acting on latents by an orthogonal representation $\rho(g)$, the one-step prediction relMSE is exactly invariant across the whole group, so fitting the dynamics on a restricted slice of orientations mathematically determines it on the entire orbit (j\v{u} y\=i f\v{a}n s\=an).
arXiv AI
Jun 2
UR-JEPA: Uniform Rectifiability as a Regularizer for Joint-Embedding Predictive Architectures
arXiv:2606. 01443v1 Announce Type: cross Abstract: A central difficulty in training Joint-Embedding Predictive Architectures (JEPAs) is preventing representation collapse.
arXiv Machine Learning
Aug 11
The Cost of Adaptivity: Matching Lower Bounds Across Learning Problems
arXiv:2608. 08826v1 Announce Type: new Abstract: Adaptive procedures must work without nuisance information an oracle may use, such as a gradient scale or smoothness index, and robust procedures may have to answer queries whose coordinate and inspection time are chosen only after the data are seen.
arXiv Machine Learning
Jul 7
Fast, Parallel, Query-Efficient Binary Classification
arXiv:2607. 04062v1 Announce Type: cross Abstract: We study the fundamental classification problem of computing a separating hyperplane for a binary-labeled dataset of size $n$ with normalized $d$-dimensional features.
arXiv AI
Jun 9
Scaling Neural Network Verification with Tensor Parallelism and Fully Sharded Data Parallelism
arXiv:2606. 09377v1 Announce Type: cross Abstract: Formal neural network verification -- proving that a network satisfies safety properties for \emph{all} inputs in a specified domain -- is bounded in practice by GPU memory: standard implementations of bound-propagation algorithms (IBP, CROWN, $\alpha$-CROWN) require weight and relaxation-coefficient matrices to reside entirely on one accelerator.
arXiv AI
Jul 24
When Does Recurrence Become an Algorithm? Convergence Selection in Weight-Tied Looped Transformers
arXiv:2607. 20594v1 Announce Type: cross Abstract: When does a weight-tied looped transformer -- one block applied T times -- implement an actual algorithm?
arXiv Machine Learning
Sep 23
Hill Sampling for Test-Time Scaling: A Simple and Better Alternative to Repeated Sampling, Evolution, and Training
arXiv:2609.25510v1 Announce Type: new Abstract: Large language models (LLMs) can improve solutions to verifiable scientific and algorithmic problems by spending additional computation at test time. R...
arXiv Machine Learning
Jul 21
Regularize or Localize: When Training-Time KV-Cache Geometry Pays Under Quantization
arXiv:2607. 17019v1 Announce Type: new Abstract: We study whether \sigreg -- LeJEPA's anti-collapse objective -- can reshape representations during standard autoregressive language-model pretraining, and when the resulting geometry helps \kv-cache quantization.
arXiv Machine Learning
Jul 7
LGQ: Learnable Geometric Quantization for Image Tokenization
arXiv:2602. 16086v3 Announce Type: replace-cross Abstract: Recent collapse-free quantizers such as FSQ achieve stable training by replacing the learnable codebook with an engineered geometry: a fixed scalar grid whose structure is dictated by the codebook size K.
arXiv AI
Sep 10
Everything in Moderation: Per-Domain Coverage Optima and Alignment-Resistant Domain Gaps in Multi-Domain Mid-Training
The study investigates how the composition of data during the mid‑training phase of language models affects performance across multiple domains. Experiments with Qwen3‑8B‑Base on five distinct KOR‑Bench domains show that moderate coverage (10%‑40%) yields the best per‑domain results, and that alignment passes cannot fully close the performance gaps created by mid‑training data choices. Additionally, zero coverage in mid‑training severely degrades accuracy, while a carefully tuned allocation can provide the largest overall pipeline improvement.
arXiv Machine Learning
Sep 10
Smoothed Picard Hamiltonian Monte Carlo
arXiv:2609.06906v1 Announce Type: cross Abstract: We develop a new low-accuracy sampler, called \emph{smoothed Picard Hamiltonian Monte Carlo}, which combines Gaussian smoothing, Picard iteration, an...