arXiv:2602.00913v3 Announce Type: replace-cross Abstract: Human value detection from single sentences is a sparse, imbalanced multi-label task. We study whether Schwartz higher-order (HO) categories help this setting on ValueEval’24 / ValuesML (74K English sentences) under a compute-frugal budget. Rather than…
arXiv:2604.05112v1 Announce Type: new Abstract: Recent progress in in-context reinforcement learning (ICRL) has demonstrated its potential for training generalist agents that can acquire new tasks directly at inference. Algorithm Distillation (AD) pioneered this paradigm and was subsequently scaled to multi-domain…
arXiv:2604.03885v2 Announce Type: replace-cross Abstract: We address the problem of recovering a time-varying 4D distribution from a sparse sequence of 2D projections – analogous to novel-view synthesis from sparse cameras, but applied to the 4D transverse phase space density $rho(x,p_x,y,p_y)$…
arXiv:2604.05134v1 Announce Type: new Abstract: How can you get a language model to reason in a task it natively struggles with? We study how reasoning evolves in a language model — from supervised fine-tuning (SFT) to reinforcement learning (RL) —…
arXiv:2604.06039v1 Announce Type: cross Abstract: Value iteration-type methods have been extensively studied for computing a nearly optimal value function in reinforcement learning (RL). Under a generative sampling model, these methods can achieve sharper sample complexity than policy optimization approaches, particularly…
arXiv:2603.22816v2 Announce Type: replace-cross Abstract: Language models increasingly “show their work” by writing step-by-step reasoning before answering. But are these reasoning steps genuinely used, or decorative narratives generated after the model has already decided? We introduce step-level faithfulness evaluation –…
arXiv:2506.22480v2 Announce Type: replace-cross Abstract: As users in small cell networks increasingly rely on computation-intensive services, cloud-based access often results in high latency. Multi-access edge computing (MEC) mitigates this by bringing computational resources closer to end users, with small base…
arXiv:2512.20983v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly evaluated in clinical settings using multi-dimensional rubrics which quantify reasoning quality, safety, and patient-centeredness. Yet, replicating specific mistakes in other LLM models is not straightforward and often requires manual…
arXiv:2602.13151v3 Announce Type: replace Abstract: Large Language Model (LLM) unlearning aims to remove targeted knowledge from a trained model, but practical deployments often require post-training quantization (PTQ) for efficient inference. However, aggressive low-bit PTQ can mask unlearning updates, causing quantized…
arXiv:2604.03541v2 Announce Type: replace Abstract: This study surveys the historical development of regularization, tracing its evolution from stepwise regression in the 1960s to recent advancements in formal error control, structured penalties for non-independent features, Bayesian methods, and l0-based regularization (among…
