arXiv:2604.06260v1 Announce Type: new Abstract: Test-time scaling investigates whether a fixed diffusion language model (DLM) can generate better outputs when given more inference compute, without additional training. However, naive best-of-$K$ sampling is fundamentally limited because it repeatedly draws from the…
arXiv:2603.11703v2 Announce Type: replace Abstract: We introduce EvoFlows, a variable-length protein sequence-to-sequence modeling approach designed for protein engineering. Existing protein language models are poorly suited for optimization tasks: autoregressive models require full sequence generation, masked language and discrete diffusion models…
arXiv:2601.11471v3 Announce Type: replace Abstract: The key-value (KV) cache is a primary memory bottleneck in Transformers. We propose Low-Rank Key-Value (LRKV) attention, which reduces KV cache memory by exploiting redundancy across attention heads, while being compute efficient. Each layer uses…
arXiv:2604.06256v1 Announce Type: new Abstract: Training dynamics during grokking concentrate along a small number of dominant update directions — the spectral edge — which reliably distinguishes grokking from non-grokking regimes. We show that standard mechanistic interpretability tools (head attribution, activation…
arXiv:2410.08334v2 Announce Type: replace-cross Abstract: In this paper, we build a reinforcement learning framework to study how children compose numbers using base-ten blocks. Studying numerical cognition in toddlers offers a powerful window into the learning process itself, because numbers sit…
arXiv:2604.06349v1 Announce Type: new Abstract: Generalizing from a single labeled source domain to unseen target domains, without access to any target data during training, remains a fundamental challenge in robust machine learning. We address this underexplored setting, known as Single…
arXiv:2604.06253v1 Announce Type: new Abstract: Cross-lingual code generation is critical in enterprise environments where multiple programming languages coexist. However, fine-tuning large language models (LLMs) individually for each language is computationally prohibitive. This paper investigates whether parameter-efficient fine-tuning methods and optimizer…
arXiv:2604.03634v2 Announce Type: replace Abstract: We establish that temporal averaging over multiple observations is the degenerate case of algebraic group action with the trivial group $G={e}$. A General Replacement Theorem proves that a group-averaged estimator from one snapshot achieves equivalent…
arXiv:2604.06287v1 Announce Type: new Abstract: Mathematical models and numerical simulations offer a non-invasive way to explore cardiovascular phenomena, providing access to quantities that cannot be measured directly. In this study, we start with a one-dimensional multiscale blood flow model that…
arXiv:2604.06366v1 Announce Type: new Abstract: Deep linear networks (DLNs) are used as an analytically tractable model of the training dynamics of deep neural networks. While gradient descent in DLNs is known to exhibit saddle-to-saddle dynamics, the impact of stochastic gradient…
