arXiv:2604.01621v1 Announce Type: cross Abstract: Large language model (LLM) inference increasingly depends on multi-GPU execution, yet existing inference parallelization strategies require layer-wise inter-rank synchronization, making end-to-end performance sensitive to workload imbalance. We present DWDP (Distributed Weight Data Parallelism), an inference parallelization strategy that preserves data-parallel execution while offloading MoE weights across peer GPUs and fetching missing experts on demand. By removing collective inter-rank synchronization, DWDP allows each GPU to progress independently. We further address the practical overheads of this design with two optimizations for split-weight management and asynchronous remote-weight prefetch. Implemented in TensorRT-LLM and evaluated with DeepSeek-R1 on GB200 NVL72, DWDP improves end-to-end output TPS/GPU by 8.8% at comparable TPS/user in the 20-100 TPS/user serving range under 8K input sequence length and 1K output sequence length.

A multi-omic single-cell atlas of the aging mouse brain reveals cell-type-specific transposon methylation changes, strengthening of 3D genome boundaries, and regionally heterogeneous aging signatures. These findings offer a resource to understand the molecular mechanisms of brain aging and guide future research on neurodegeneration.

arXiv:2509.23067v2 Announce Type: replace-cross Abstract: The rising cost of acquiring supervised data has driven significant interest in self-improvement for large language models (LLMs). Straightforward unsupervised signals like majority voting have proven effective in generating pseudo-labels for verifiable tasks, while their applicability to unverifiable tasks (e.g., translation) is limited by the open-ended character of responses. As a result, self-evaluation mechanisms (e.g., self-judging and entropy minimization) are predominantly used to derive pseudo-labels. However, self-evaluation relying on LLMs typically incurs high computational overhead and introduces overconfidence issues due to intrinsic biases. To address these challenges, we propose a novel self-evaluation-free approach for unverifiable tasks, designed for lightweight yet effective self-improvement. Inspired by majority voting commonly employed in verifiable tasks, we propose semantic voting as a novel mechanism that relaxes the principle of hard matching (i.e., exact matching) toward soft matching (i.e., semantic similarity). Soft matching is achieved by leveraging a lightweight sentence embedding model to quantify semantic similarity, thereby mitigating excessive computational burden and intrinsic bias-associated limitations of self-evaluation. Comprehensive experiments demonstrate that our method achieves substantial gains in computational efficiency and overall better performance than self-evaluation methods across diverse model architectures and tasks.

arXiv:2602.00465v2 Announce Type: replace-cross Abstract: Functional miRNA--mRNA targeting is a large-bag prediction problem: each transcript yields a heavy-tailed pool of candidate target sites (CTSs), yet only a pair-level label is observed. We formalize this regime as \emph{Budgeted Relational Multi-Instance Learning (BR-MIL)}, where at most $K$ instances per bag may receive expensive encoding and relational processing under a hard compute budget. We propose \textbf{PAIR-Former} (Pool-Aware Instance-Relational Transformer), a BR-MIL pipeline that performs a cheap full-pool scan, selects up to $K$ diverse CTSs on CPU, and applies a permutation-invariant Set Transformer aggregator on the selected tokens. On miRAW, PAIR-Former outperforms strong pooling baselines at a practical operating budget ($K^\star{=}64$) while providing a controllable accuracy--compute trade-off as $K$ varies. We further provide theory linking budgeted selection to (i) approximation error decreasing with $K$ and (ii) generalization terms governed by $K$ in the expensive relational component.

arXiv:2603.22844v2 Announce Type: new Abstract: Surgical smoke severely degrades intraoperative video quality, obscuring anatomical structures and limiting surgical perception. Existing learning-based desmoking approaches rely on scarce paired supervision and deterministic restoration pipelines, making it difficult to perform exploration or reinforcement-driven refinement under real surgical conditions. We propose PhySe-RPO, a diffusion restoration framework optimized through Physics- and Semantics-Guided Relative Policy Optimization. The core idea is to transform deterministic restoration into a stochastic policy, enabling trajectory-level exploration and critic-free updates via group-relative optimization. A physics-guided reward imposes illumination and color consistency, while a visual-concept semantic reward learned from CLIP-based surgical concepts promotes smoke-free and anatomically coherent restoration. Together with a reference-free perceptual constraint, PhySe-RPO produces results that are physically consistent, semantically faithful, and clinically interpretable across synthetic and real robotic surgical datasets, providing a principled route to robust diffusion-based restoration under limited paired supervision.

Nature, Published online: 25 March 2026; doi:10.1038/s41586-026-10221-3

Intelligent and miniaturized drug delivery devices leveraging advances in biotechnology, artificial intelligence, electronics and materials science enable treatments with increased precision and responsiveness, with applications in cancer, diabetes, cardiovascular disease and other diseases.

arXiv:2603.08321v1 Announce Type: new Abstract: Large language models (LLMs) show significant potential for clinical decision support (CDS), yet their black-box nature -- characterized by untraceable reasoning and probabilistic hallucinations -- poses severe challenges in acupuncture, a field demanding rigorous interpretability and safety. To address this, we propose CORE-Acu, a neuro-symbolic framework for acupuncture clinical decision support that integrates Structured Chain-of-Thought (S-CoT) with knowledge graph (KG) safety verification. First, we construct the first acupuncture Structured Reasoning Trace dataset and a schema-constrained fine-tuning framework. By enforcing an explicit causal chain from pattern identification to treatment principles, treatment plans, and acupoint selection, we transform implicit Traditional Chinese Medicine (TCM) reasoning into interpretable generation constraints, mitigating the opacity of LLM-based CDS. Furthermore, we construct a TCM safety knowledge graph and establish a ``Generate--Verify--Revise'' closed-loop inference system based on a Symbolic Veto Mechanism, employing deterministic rules to intercept hallucinations and enforce hard safety boundaries. Finally, we introduce the Lexicon-Matched Entity-Reweighted Loss (LMERL), which corrects terminology drift caused by the frequency--importance mismatch in general optimization by adaptively amplifying gradient contributions of high-risk entities during fine-tuning. Experiments on 1,000 held-out cases demonstrate CORE-Acu's superior entity fidelity and reasoning quality. Crucially, CORE-Acu achieved 0/1,000 observed safety violations (95\% CI: 0--0.37\%), whereas GPT-4o exhibited an 8.5\% violation rate under identical rules. These results establish CORE-Acu as a robust neuro-symbolic framework for acupuncture clinical decision support, guaranteeing both reasoning auditability and strict safety compliance.

arXiv:2602.20980v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable performance by integrating powerful language backbones with large-scale visual encoders. Among these, latent Chain-of-Thought (CoT) methods enable implicit reasoning in continuous hidden states, facilitating seamless vision-language integration and faster inference. However, existing heuristically predefined supervision signals in latent CoT provide limited guidance for preserving critical visual information in intermediate latent states. To address this limitation, we propose CrystaL (Crystallized Latent Reasoning), a single-stage framework with two paths to process intact and corrupted images, respectively. By explicitly aligning the attention patterns and prediction distributions across the two paths, CrystaL crystallizes latent representations into task-relevant visual semantics, without relying on auxiliary annotations or external modules. Extensive experiments on perception-intensive benchmarks demonstrate that CrystaL consistently outperforms state-of-the-art baselines, achieving substantial gains in fine-grained visual understanding while maintaining robust reasoning capabilities.

arXiv:2410.04949v3 Announce Type: replace-cross Abstract: Judicial efficiency is critical to social stability. However, in many countries worldwide, grassroots courts face substantial case backlogs, and judicial decisions remain heavily dependent on judges' cognitive efforts, with insufficient intelligent tools to enhance efficiency. To address this issue, we propose a highly efficient law article recommendation approach combining a Knowledge Graph (KG) and a Large Language Model (LLM). First, we construct a Case-Enhanced Law Article Knowledge Graph (CLAKG) to store current law articles, historical case information, and their interconnections, alongside an LLM-based automated construction method. Building on this, we propose a closed-loop law article recommendation framework integrating graph embedding-based retrieval and KG-grounded LLM reasoning. Experiments on judgment documents from China Judgments Online demonstrate that our method boosts law article recommendation accuracy from 0.549 to 0.694, outperforming strong baselines significantly. To support reproducibility and future research, all source code and processed datasets are publicly available on GitHub (see Data Availability Statement).

arXiv:2602.10016v2 Announce Type: replace-cross Abstract: Deriving predictable scaling laws that govern the relationship between model performance and computational investment is crucial for designing and allocating resources in massive-scale recommendation systems. While such laws are established for large language models, they remain challenging for recommendation systems, especially those processing both user history and context features. We identify poor scaling efficiency as the main barrier to predictable power-law scaling, stemming from inefficient modules with low Model FLOPs Utilization (MFU) and suboptimal resource allocation. We introduce Kunlun, a scalable architecture that systematically improves model efficiency and resource allocation. Our low-level optimizations include Generalized Dot-Product Attention (GDPA), Hierarchical Seed Pooling (HSP), and Sliding Window Attention. Our high-level innovations feature Computation Skip (CompSkip) and Event-level Personalization. These advances increase MFU from 17% to 37% on NVIDIA B200 GPUs and double scaling efficiency over state-of-the-art methods. Kunlun is now deployed in major Meta Ads models, delivering significant production impact.