arXiv:2605. 20919v3 Announce Type: replace-cross Abstract: Sutra is a typed, purely functional programming language whose compiled forward pass is a PyTorch neural network.
arXiv:2606. 19279v1 Announce Type: new Abstract: Neurosymbolic semantics is fragmented: classical, fuzzy, probabilistic and neural systems each define truth by their own inductive rules.
The paper introduces Numbat, a self‑contained machine‑learning stack implemented entirely in Zig with no external runtime dependencies. It covers tensor computation, automatic differentiation, neural‑network modules, mixed precision, multi‑GPU training, data loading, and monitoring, and exposes a stable C ABI with over 1,400 entry points and bindings for six languages. The authors verify the stack against a reference implementation at multiple levels, uncovering ten silent recipe divergences, and demonstrate its practical capability by training a 25.9M‑parameter YOLOv8m detector on COCO 2017, achieving a competitive mAP score and matching single‑GPU performance.
arXiv:2604. 11284v5 Announce Type: replace-cross Abstract: We present THEIA, a 2.
arXiv:2607. 18254v1 Announce Type: new Abstract: Multi-Level Intermediate Representation (MLIR) underlies modern ML compiler infrastructure (TensorFlow, JAX/StableHLO, PyTorch Inductor, IREE), yet appears only in trace amounts in code-LM pretraining corpora.
arXiv:2608. 08118v1 Announce Type: new Abstract: There are several methods for searching for graphs with prescribed properties, such as SAT solvers and specialized generators.
arXiv:2609.24942v1 Announce Type: new Abstract: A model generalizes outside its training distribution only when it computes a representation structurally equivalent to the generating mechanism, not a...
arXiv:2608.28421v2 Announce Type: replace Abstract: Post training a language model to reason means updating its weights. Supervised finetuning and reinforcement learning both place the acquired capab...
arXiv:2606. 00671v3 Announce Type: replace Abstract: We present Moxia (formerly AXIOM), a trust-first neuro-symbolic architecture for self-explaining mathematical reasoning over natural-language input.
arXiv:2606. 18923v1 Announce Type: new Abstract: Programmability is a missing first-class interface in fixed-tensor neural networks: editing a relation, freezing a subgraph, auditing a local function, or changing the execution backend should be an operation on the neural program rather than ad-hoc parameter surgery.
arXiv:2606. 31845v1 Announce Type: cross Abstract: A transformer's feed-forward (FFN) sublayer materializes the distinctions attention gathers, yet gives no account of what it computes.
arXiv:2607. 11696v1 Announce Type: new Abstract: Self-refinement often fails to strengthen few-shot inductive reasoning in large language models.
arXiv:2606. 09930v1 Announce Type: cross Abstract: The boundary between program execution and gradient-based optimization has long limited the use of code itself as a learnable scientific model.