arXiv:2608. 12700v1 Announce Type: new Abstract: Systems that generate GPU kernels with language models report high correctness rates.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.
arXiv:2606. 20128v1 Announce Type: cross Abstract: Benchmarks for LLM-generated GPU kernels (KernelBench, TritonBench, GEAK) score correctness through fixed-shape, small-sample allclose-style checks.
arXiv:2606. 27396v1 Announce Type: cross Abstract: Test-input generation for tensor kernels is folkloric.
arXiv:2608. 08722v1 Announce Type: cross Abstract: Benchmarks for systems that are optimized against the evaluation signal measure something different from what they claim.
arXiv:2607. 13070v2 Announce Type: replace-cross Abstract: Safety claims for self-improving agent runtimes are almost always self-graded: a policy file, a guardrail, a promise in a README.
arXiv:2606. 31023v1 Announce Type: cross Abstract: Hard-constrained sequential decision systems have no certified way to spend the test-time compute of modern AI: executing the multi-step drafts of a learned policy or a frozen LLM forfeits the feasibility guarantee a trusted solver provides, while invoking the solver at every step forfeits the speed the AI offers.
arXiv:2608. 05863v1 Announce Type: new Abstract: Modern models no longer keep a plain KV cache: latent caches, learned sparse selectors and recurrent states each carry the model's memory in a different form, and each fails differently under compression.