arXiv:2507.12549v4 Announce Type: replace Abstract: While machine learning has advanced through massive parallelization, we identify a critical blind spot: some problems are fundamentally sequential. These “inherently serial” problems-from mathematical reasoning to physical simulations to sequential decision-making-require sequentially dependent computational steps…
arXiv:2604.26256v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a critical paradigm for LLM post-training, yet the rollout phase — accounting for 50–80% of total step time — is bottlenecked by skewed generation: long-tailed trajectories indispensable for model performance…
arXiv:2510.06735v2 Announce Type: replace Abstract: Bayesian causal discovery benefits from prior information elicited from domain experts, and in heterogeneous domains any prior knowledge would be badly needed. However, so far prior elicitation approaches have assumed a single causal graph and…
arXiv:2604.26297v1 Announce Type: new Abstract: Optimization algorithms are fundamental to modern deep learning, yet most widely used methods rely on update rules based primarily on local gradient statistics. We introduce NeuroPlastic, a plasticity-modulated optimizer that augments gradient-based updates with an…
arXiv:2602.06603v3 Announce Type: replace Abstract: Reinforcement learning (RL) is a type of artificial intelligence for making optimal choices. In healthcare, researchers generally use offline RL (ORL), where models are trained and evaluated from retrospective observational data. To accommodate inherently irregular…
arXiv:2604.26301v1 Announce Type: new Abstract: Graph Contrastive Learning (GCL) has emerged as a prominent framework for unsupervised graph representation learning. However, relying on augmentation design alone to define the invariances learned by GCL can be brittle under structural perturbations. To…
arXiv:2603.19470v2 Announce Type: replace Abstract: Off-policy problems such as policy staleness and training–inference mismatch have become a major bottleneck for training stability and further exploration in LLM RL. The distribution gap between the inference and updated policies grows because of…
arXiv:2604.26326v1 Announce Type: new Abstract: Reinforcement learning (RL) has unlocked complex reasoning abilities in large language models (LLMs). However, most RL algorithms suffer from performance saturation, preventing further gains as RL training scales. This problem can be characterized by the…
arXiv:2604.22063v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly utilized in clinical reasoning and risk assessment. However, their interpretive reliability in critical and indeterminate domains such as psychiatry remains unclear. Prior work has identified algorithmic biases and prompt…
arXiv:2604.26337v1 Announce Type: new Abstract: Conceptual aircraft design is traditionally an expert-mediated iterative process in which a human designer proposes a configuration, runs low-order physics, inspects the result, and re-proposes. We present AlphaJet, an end-to-end automated synthesis pipeline that closes…
