论文

本文综述了 Islamic LLMs 与可信 Islamic AI 这一新兴领域，并论证了仅具备阿拉伯语流利度不足以支撑 Islamic AI，进而提出面向抗幻觉 Islamic AI 系统的研究议程。This survey reviews the emerging field of Islamic LLMs and trustworthy Islamic AI, and argues that fluency in Arabic is not sufficient for Islamic AI, with a research agenda for hallucination-resistant Islamic AI systems.

AsymCache 是一个面向 LLM 推理的计算-延迟感知 KV cache 管理系统，将 cache 驻留决策与 GPU attention kernel 性能显式对齐，包含三个关键组件：用于高效处理非连续 KV 上下文的多段注意力（MSA）、联合优化命中率与位置感知重计算代价的 cache 淘汰策略，以及面向高硬件利用率的自适应分片调度器。AsymCache is proposed, a computation-latency-aware KV cache management system for LLM inference that explicitly aligns cache residency decisions with GPU attention kernel performance, including three key components: Multi-Segment Attention (MSA) for efficient non-contiguous KV context processing, a cache eviction policy that jointly optimizes hit rate and position-aware recomputation cost, and an adaptive chunking scheduler for high hardware utilization.

RTP-LLM 是一个面向工业级 LLM 部署的高性能推理引擎，已在 Alibaba Group 成功部署，服务超过 1 亿用户，通过集成设计解决根本性瓶颈。RTP-LLM is presented, a high-performance inference engine for industrial-scale LLM deployment, successfully deployed across Alibaba Group serving over 100 million users, and addresses fundamental bottlenecks through integrated design.

这篇立场论文认为，LLM 推理 serving 已超越通用启发式方法，如今需要数学优化与算法基础，并呼吁社区将 LLM serving 的算法设计视为一个新的研究前沿。This position paper argues that LLM inference serving has outgrown generic heuristics and now demands mathematical optimization and algorithmic foundations, and calls on the community to recognize algorithmic design for LLM serving as a research frontier.

SwiftCache 是一个协同推理系统，使异构模型可在同一服务器内共享未充分利用的 GPU 内存与 NVLink 带宽，支持跨模型通过 NVLink 共享 KV cache，避免使用慢速 PCIe 传输。SwiftCache is a collaborative inference system that enables heterogeneous models to share underutilized GPU memory and NVLink bandwidth within a server, allowing cross-model KV cache sharing over NVLink and avoiding slow PCIe transfers.

提出 OScaR（Omni-Scaled Canalized Rotation），一个面向 X-LLMs 的精确且轻量的 KV cache 压缩框架，作为一个鲁棒、低复杂度、通用的框架确立了新的 Pareto 前沿。OScaR (Omni-Scaled Canalized Rotation), an accurate and lightweight KV cache compression framework for X-LLMs, is proposed, establishing it as a robust, low-complexity, and universal framework that defines a new Pareto front.

WAIT (Waiting for Accumulated Inference Threshold) 是一种基于阈值的准入规则，适用于已知输出长度；Nested WAIT 通过调控请求在 decode 阶段各分段间的推进方式，将该规则扩展到未知输出长度场景。WAIT (Waiting for Accumulated Inference Threshold), a threshold-based admission rule for known output lengths, and Nested WAIT, which extends the rule to unknown output lengths by regulating how requests advance across decode-stage segments are designed.

本文对近期 KV cache 优化技术进行系统综述，将其归纳为五大方向：cache eviction、cache compression、混合内存方案、新型 attention 机制与组合策略，并指出自适应多阶段优化流水线是未来研究的重要方向。This paper provides a systematic review of recent KV cache optimization techniques, organizing them into five principal directions: cache eviction, cache compression, hybrid memory solutions, novel attention mechanisms, and combination strategies, and pointing toward adaptive, multi-stage optimization pipelines as a promising direction for future research.

本文提出 AIConfigurator，一个统一的性能建模系统，能够在不依赖 GPU profiling 的前提下进行快速、与框架无关的推理配置搜索；并提供一个抽象层，自动为目标后端解析最优启动参数，无缝集成到生产级编排系统中。AIConfigurator is presented, a unified performance-modeling system that enables rapid, framework-agnostic inference configuration search without requiring GPU-based profiling, and an abstraction layer that automatically resolves optimal launch parameters for the target backend, seamlessly integrating into production-grade orchestration systems.

研究发现 RLMs 能够成功处理超出模型上下文窗口长达两个数量级的输入，即便在较短 prompt 下，其质量也显著优于原生前沿 LLM 以及常见的长上下文与编程脚手架。It is found that RLMs can successfully process inputs up to two orders of magnitude beyond model context windows and, even for shorter prompts, dramatically outperform the quality of vanilla frontier LLMs and common long-context and coding scaffolds.

本文挑战了"推理深度与计算效率之间存在权衡"的固有假设，在无需修改架构的前提下提供了更具可扩展性的复杂推理方案。This work challenges the assumed trade-off between reasoning depth and computational efficiency, providing a more scalable approach to complex reasoning without architectural modifications.

本文在 KV cache 约束下对 LLM 推理进行理论建模，提出一种新型批处理与调度算法，在有效管理 KV cache 内存的同时最小化推理延迟，并通过在合成数据集上与后视最优的对比展示其强劲的实证性能。This work model LLM inference with KV cache constraints theoretically and proposes a novel batching and scheduling algorithm that minimizes inference latency while effectively managing the KV cache's memory, and demonstrates the algorithm's strong empirical performance by comparing it to the hindsight optimal in a synthetic dataset.

本文提出了一种实证方法，用于研究基于 GPU 的 LLM 推理服务系统中的 software aging 问题，并提供了一个可复现的框架，开辟了 software aging 与 software rejuvenation 与 LLM serving 交叉方向的研究。This paper proposes an empirical methodology to study software aging in GPU-based LLM serving systems and provides a reproducible framework that opens a research direction at the intersection of the software aging and rejuvenation and LLM serving communities.

本文提出首个将计算与 GPU 显存约束显式纳入 LLM 推理分析的排队论框架，并推导了严格的稳定性与不稳定性条件，用以判定 LLM 推理服务能否在持续到达的请求下避免队列无界增长。This paper introduces the first queueing-theoretic framework that explicitly incorporates both computation and GPU memory constraints into the analysis of LLM inference, and derives rigorous stability and instability conditions that determine whether an LLM inference service can sustain incoming demand without unbounded queue growth.

介绍 Albireo，一种并行推理系统：通过调度与 I/O 与计算及序列并行采样的重叠来压缩不可扩展部分，从而提高可达到的 TP 度 t，且不改变模型架构。Albireo is presented, a parallel inference system that raises the attainable TP degree t by shrinking the non-scalable portion via overlap of scheduling and I/O with compute and sequence-parallel sampling, without changing model architectures.

实验表明，在该数据上微调的模型不仅持续优于基座模型和面向写作的专门基线，还优于基于现有写作语料训练的模型，表明受控的题材扩展是稳健创意写作能力的关键驱动力Experiments demonstrate that models fine-tuned on the data consistently surpass not only base models and writing-specialized baselines, but also models trained on existing writing corpora, indicating that controlled genre expansion is a key driver of robust creative writing capability.

本文引入一个均值修正项，有效抑制近似误差，即使在极端稀疏度下也能将性能下降保持在可控范围；并使用 PackGQA 内存访问、warp specialization 和 pingpong 流水线重新设计稀疏注意力算子。This paper introduces a mean correction term that effectively suppresses the approximation error, keeping performance degradation manageable even at extreme sparsity levels, and redesigns the sparse attention operator with PackGQA memory access, warp specialization, and pingpong pipelining.

本文研究 LLM 在测试时从迭代经验中学习的机制，称之为 Chain-of-Experience (CoE)：模型通过与自身或环境反馈的迭代交互积累经验痕迹，形成超越零样本推理的持续改进循环。This study studies how LLMs learn from iterative experience at test time, a setting the authors refer to as Chain-of-Experience (CoE), where models accumulate experiential traces through iterative interactions with self or environmental feedback to form a continual improvement loop beyond zero-shot inference.

本文对 LLM 推理服务方法进行了全面综述，涵盖基础的实例级方法、深入的集群级策略、新兴的场景方向以及其他重要但零散的领域。This paper provides a comprehensive survey of LLM inference serving methods, covering fundamental instance-level approaches, in-depth cluster-level strategies, emerging scenario directions, and other miscellaneous but important areas.

本文提出 User Behavioral Densing Law，为大规模用户表示学习中的 tokenization 配置选择提供实用指导，并开发了 ALGN——一种自适应变长 tokenization 方法，可改善容量分配。The proposed User Behavioral Densing Law is proposed, providing practical guidance for tokenization configuration selection in large-scale user representation learning and ALGN, an adaptive variable-length tokenization method that improves capacity allocation, is developed.

目标是提供无需数周超参搜索即可部署的方案，直接从原始未压缩模型蒸馏 4-bit 学生模型，并以开源权重形式发布为 Hypernova-60B。The aim is a recipe deployable without a multi-week hyper-parameter search, which distills the 4-bit student directly from the original, uncompressed model, and is released open-weight as Hypernova-60B.

本工作开发了一个 SOTA 的 paged attention kernel，完全基于领域特定即时编译语言 Triton 构建，在 NVIDIA 与 AMD GPU 上均达到 SOTA 性能。This work develops a state-of-the-art paged attention kernel that builds exclusively on the domain-specific just-in-time compiled language Triton to achieve state-of-the-art performance on both NVIDIA and AMD GPUs.

本工作提出一种新颖的混合精度 PTQ 策略，直接最小化整个模型的全局误差传播，而非孤立地处理逐层误差，并开发了一种新颖的联合优化方法，在统一搜索空间中同时学习结构化剪枝决策与混合精度量化策略。This work proposes a novel mixed-precision PTQ strategy that directly minimizes global error propagation across the entire model, rather than isolating layer-wise errors, and develops a novel joint optimization approach that simultaneously learns structural pruning decisions and mixed-precision quantization policies within a unified search space.

提出 Prefix Sliding，在推理过程中丢弃不属于前缀或最近几千 token 窗口的 token，从而实现高效的长时程 test-time scaling。Prefix Sliding is proposed, which discards tokens during reasoning that are not part of the prefix or the window of the last few thousand tokens, allowing for efficient long-horizon test-time scaling.

更大的模型显著更具样本效率，因此最优的算力高效训练方式是：在相对适中的数据量上训练非常大的模型，并在远未收敛时显著提前停止训练。Larger models are significantly more sample-efficient, such that optimally compute-efficient training involves training very large models on a relatively modest amount of data and stopping significantly before convergence.

实验结果表明，CritICL 持续优于标准 in-context learning，并以显著更少的生成次数和更低的 token 成本，取得与 test-time scaling 方法相当或更优的性能。Experimental results show that CritICL consistently outperforms standard in-context learning and achieves performance competitive with or superior to test-time scaling methods, while requiring significantly fewer generations and lower token cost.

冻结一个大规模评测集合，并尝试对其历史断言进行 replay，以使这一原本隐式的推理步骤变得显式且可执行。A large evaluation collection is frozen and an attempt to replay its historical claims is made to make this otherwise implicit inference step explicit and executable.

提出 ABot-Recon，一个简易的流式模型，仅缓存前 11 帧的 KV 特征，在当前相机坐标系下预测点图，并同时预测一个相对于相邻帧的相对位姿，该位姿在参考系变化下保持等变性。ABot-Recon is presented, a simple streaming model that caches KV features from only the preceding 11 frames and predicts a point map in the current camera coordinate system together with an adjacent-frame relative pose that remains equivariant under changes of reference frame.

该框架将循环序列模型中的 temporal alignment、plasticity、forgetting 与 bounded rehearsal 分离，并结合数值稳定的 positive-decay renormalization，使其在语言建模上保持竞争力，同时提升在可变位数加法任务上的长度外推能力。This framework separates temporal alignment, plasticity, forgetting, and bounded rehearsal in recurrent sequence models, together with numerically stable positive-decay renormalization, to remain competitive in language modeling and improve length extrapolation on variable-digit addition.

GGSS——Geodesic-Gated Spherical Steering——一种保范的干预方法，在单位超球面上发现反事实偏差子空间，沿 geodesic arc 引导视觉 token，并通过自适应门控聚焦于承载更强人口统计信号的 token。GGSS---Geodesic-Gated Spherical Steering---a norm-preserving intervention that discovers a counterfactual bias subspace on the unit hypersphere, steers visual tokens along geodesic arcs, and uses an adaptive gate to focus correction on tokens that carry stronger demographic signal.

该工作表明带 sink 的 Sliding Window Attention（SWA）表现不逊于甚至优于后训练的 Linear Attention 模型，并建议改用 SWA 而非后训练线性模型。This work shows that Sliding Window Attention (SWA) with sinks performs as well or better than post-trained Linear Attention models, and recommends switching to SWA instead of post-training linear models.

端到端天气预报系统直接从原始地球观测数据生成高质量的全球网格与站点预报，仅以数值天气预报流水线（含数据同化）一小部分的成本取而代之。这类系统是确定性的，不输出不确定性结果。本文通过在每个组件上附加一种随机机制，将 Aardvark Weather 模型概率化：在观测编码器中加入学习到的、依赖输入的噪声，以捕捉源自观测系统的偶然不确定性；在处理器中使用 Monte Carlo dropout，以捕捉认知不确定性。End-to-end weather forecasting systems produce skillful global gridded and station forecasts directly from raw Earth observations, replacing the numerical weather prediction pipeline, including data assimilation, at a fraction of its cost. These systems are deterministic and issue no uncertainty. Here we render the Aardvark Weather model probabilistic by attaching one stochastic mechanism to each component: learned, input-dependent noise at the observation encoder, capturing aleatoric uncertainty inherited from the observing system, and Monte Carlo dropout in the processor, capturing epistemic

本文提出 DagEvo，通过利用 self-play 中求解器的失败历史来引导问题生成，无需外部任务资源，并表明混合生成、跨状态拼接的记忆状态更新以及双置信度过滤共同贡献了这些性能提升。DagEvo is introduced, which guides question generation using the solver's failure history from self-play, without external task resources, and shows that mixed generation, memory-state updates with cross-state stitching, and double-confidence filtering contribute to these gains.

本工作借鉴线性模型的 state space model（SSM）视角，提出三项核心方法改进并组合形成更具表达力的递推结构：源自 SSM 离散化的递推式、用于更丰富状态追踪的复数值状态更新规则，以及在不增加 decode 延迟前提下提升模型性能的多输入多输出（MIMO）建模。This work introduces three core methodological improvements inspired by the state space model (SSM) viewpoint of linear models that combine to form a more expressive recurrence derived from SSM discretization, a complex-valued state update rule that enables richer state tracking, and a multi-input, multi-output (MIMO) formulation for better model performance without increasing decode latency.