📄 arXiv 论文速递

💡 言语脑机接口缺乏统一的性能评估标准，阻碍临床比较与转化。该文提出通用通信度量，为瘫痪患者恢复言语的BCI系统提供可比的评价基准，对神经工程领域具有关键推动作用。

Speech brain-computer interfaces (speech BCIs) translate neural activity into language, offering a path towards restoring speech for people with paralysis and, more broadly, enabli…

💡 现有Web智能体依赖生成式世界模型进行动作选择，效率低且易错。该文提出判别式世界模型，直接学习状态优劣，显著提升测试时决策的准确性与速度，推动自主网页操作在真实任务中的实用化。

Recent web agents use world models for test-time action selection by sampling candidate actions, predicting the resulting web states, and ranking them with a ranker model or a Proc…

We introduce the Graph Machine (GM), an architecture that maintains an $O(n)$-sized state and accesses it through sparse, dynamic routing. Unlike methods with fixed-size states or …

Ordinary differential equations (ODEs) underlie models in science and engineering, and many applications need derivatives of their solutions with respect to parameters. Ensembles o…

Autonomous robots powered by deep learning face a fundamental auditability challenge: when incidents occur, investigators cannot reconstruct why the system made specific decisions.…

💡 梯度下降的加速极限是优化理论的核心问题。该文突破Nesterov经典下界，证明预定步长在平滑凸优化中无法超越特定复杂度，为算法设计提供新理论边界，影响大规模机器学习训练效率。

We study how far gradient descent (GD) can be accelerated by predetermined stepsizes in smooth convex optimization. Going beyond the classical $Ω(n^{-2})$ first-order oracle lower …

💡 LLM的安全对齐依赖自然语言输出，但内部表征存在不可读性，导致越狱攻击难以防御。该文揭示语言不可读性与安全漏洞的深层关联，为设计更鲁棒的对齐机制提供新视角，对AI安全至关重要。

LLMs are trained to generate natural language. However, various strands of evidence indicate that an LLM's externalized linguistic outputs and mechanistically-extracted linguistic …

💡 竞赛编程是检验LLM推理能力的极限场景。该文通过后训练方法使模型达到国际奥赛金牌水平，显著超越现有代码模型，对AI在复杂算法推理与工程应用中的能力提升具有里程碑意义。

Competitive programming has become a key test of large language model reasoning, with international competitions such as IOI and ICPC representing its most challenging settings. We…

Stable 4-bit floating-point (FP4) pretraining is difficult because the E2M1 payload represents only a narrow range of magnitudes. NVIDIA's Transformer Engine \nv{} recipe addresses…

Meshfree methods such as smoothed particle hydrodynamics (SPH) with kernel corrections, radial basis function-generated finite differences (RBF-FD), and the local anisotropic basis…

Researchers increasingly use artificial intelligence to construct measures of social, organizational, and occupational characteristics that are absent from conventional surveys. We…

Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for large language model (LLM) post-training, but its reliance on coarse outcome rewards le…