In RLHF pipelines, reward scoring blocks policy updates. Slow scoring bottlenecks the entire loop, since no update runs until every rollout gets a score.
Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.
arXiv:2607. 19712v1 Announce Type: new Abstract: In RLHF pipelines, reward scoring blocks policy updates.
arXiv:2607. 16241v1 Announce Type: cross Abstract: Recent large language models (LLMs) can generate custom CUDA kernels that appear to outperform PyTorch on benchmarks such as KernelBench.
arXiv:2605. 09708v2 Announce Type: replace-cross Abstract: We present Metal-Sci, a 10-task benchmark of scientific Apple Silicon Metal compute kernels spanning six optimization regimes (stencils, all-pairs in $n$-body problems, multi-field Boltzmann, neighbor-list molecular dynamics, multi-kernel PDE, FFT).
arXiv:2607. 27271v1 Announce Type: new Abstract: Code models are increasingly trained with execution feedback, but most training signals still stop at correctness.
arXiv:2608. 15089v1 Announce Type: new Abstract: Long-horizon agents can fail even when their underlying models can solve the constituent steps.
arXiv:2606. 29119v1 Announce Type: cross Abstract: We introduce a pre-registered screening rule that decides, before any implementation, whether an evolutionary / population / lifecycle outer loop over neural-network parameters or structure is worth building.