Multi-turn conversational systems based on large language models are increasingly being integrated into web platforms and applied across a wide range of domains. However, these systems typically combine the userߣs current query with contextual information from previous interactions, resulting in continuously expanding input prompts. This leads to a significant increase in time-to-first-token (TTFT), causing intolerable delays in web response times. To address this issue, we introduce TransformKV, which maximizes the reuse of the KV cache from previous conversations rather than recomputing, thereby reducing TTFT latency. TransformKV first identifies the specific locations that require transformation to maximize the reuse of the KV cache with minimal operations. It then efficiently transforms the KV cache for a subset of tokens by recomputing only the KV cache that impact semantics. Additionally, TransformKV further reduces TTFT latency by performing only QKV computations in certain layers while skipping other computations that contribute less to overall performance. Experimental results demonstrate that in multi-turn conversation tasks, TransformKV can reduce inference latency by up to 30%, achieving up to a 1.8× improvement in performance compared to similar approaches. Notably, as the context window size increases, the performance gains become even more pronounced.

Graph node clustering is a fundamental unsupervised task. Existing methods typically train an encoder through self-supervised learning and then apply K-means to the encoder output. Some methods use this clustering result directly as the final assignment, while others initialize centroids based on this initial clustering and then finetune both the encoder and these learnable centroids. However, due to their reliance on K-means, these methods inherit its drawbacks when the cluster separability of encoder output is low, facing challenges from the Uniform Effect and Cluster Assimilation. We summarize three reasons for the low cluster separability in existing methods: (1) lack of contextual information prevents discrimination between similar nodes from different clusters; (2) training tasks are not sufficiently aligned with the downstream clustering task; (3) the cluster information in the graph structure is not appropriately exploited. To address these issues, we propose conTrastive grapH clustEring by SwApping fUsed gRomov-wasserstein coUplingS (THESAURUS). Our method introduces semantic prototypes to provide contextual information, and employs a cross-view assignment prediction pretext task that aligns well with the downstream clustering task. Additionally, it utilizes Gromov-Wasserstein Optimal Transport (GW-OT) along with the proposed prototype graph to thoroughly exploit cluster information in the graph structure. To adapt to diverse real-world data, THESAURUS updates the prototype graph and the prototype marginal distribution in OT by using momentum. Extensive experiments demonstrate that THESAURUS achieves higher cluster separability than the prior art, effectively mitigating the Uniform Effect and Cluster Assimilation issues.

Graph classification has long assumed a closed-world setting, limiting its applicability to real-world scenarios where new categories often emerge. To address this limitation, we introduce Graph-Level Novel Category Discovery (GLNCD), a new task aimed at identifying unseen graph categories without supervision from novel classes. We first adapt classical Novel Category Discovery (NCD) methods for images to the graph domain and evaluate these baseline methods on four diverse graph datasets curated for the GLNCD task. Our analysis reveals that these methods suffer a notable performance degradation compared to their image-based counterparts, due to two key challenges: (1) insufficient utilization of structural information in graph self-supervised learning (SSL), and (2) ineffective pseudo-labeling strategies based on ranking statistics (RS) that neglect graph structure. To alleviate these issues, we propose ProtoFGW-NCD, a framework consisting of two core components: ProtoFGW-CL, a novel graph SSL framework, and FGW-RS, a structure-aware pseudo-labeling method. Both components employ a differentiable Fused Gromov-Wasserstein (FGW) distance to effectively compare graphs by incorporating structural information. These components are built upon learnable prototype graphs, which enable efficient, parallel FGW-based graph comparisons and capture representative patterns within graph datasets. Experiments on four GLNCD benchmark datasets demonstrate the effectiveness of ProtoFGW-NCD.

Sea surface temperature (SST) is critically important for understanding ocean dynamics and supporting various marine activities, making accurate short-term SST forecasting highly significant. However, accurately modeling the multi-scale variability of SST remains challenging for existing deep learning (DL) models. This study introduces the Coupled Transformer-CNN Network (CoTCN), a hybrid architecture designed to leverage the multi-scale variability of SST. The CoTCN combines the strengths of Transformers and convolutional neural networks (CNNs), significantly enhancing SST forecasts’ spatial continuity and predictive accuracy. Compared to five state-of-the-art DL models based on Transformer or CNN that include ConvLSTM, ConvGRU, AFNO, PredRNN, and SwinLSTM, CoTCN demonstrates superior performance in global and local areas of SST forecasting. At 1-day lead time, CoTCN reduces the global average root mean square error (RMSE) by over 15%, with forecast errors ranging from 0.20°C to 0.53°C across 1–10 day lead times. Moreover, the CoTCN effectively mitigates the checkerboard artifacts inherent to the Vision Transformer architecture. These findings highlight the effectiveness of CoTCN in capturing SST’s multi-scale features and underscore the promising potential of hybrid architectures for future DL models.

Ocean general circulation models (OGCMs) are indispensable for studying the multi-scale oceanic processes and climate change. High-resolution ocean simulations require immense computational power and thus become a challenge in climate science. We present LICOMK++, a performance-portable OGCM using Kokkos, to facilitate global kilometer-scale ocean simulations. The breakthroughs include: (1) we enhance cuttingedge Kokkos with the Sunway architecture, enabling LICOMK++ to become the first performance-portable OGCM on diversified architectures, i.e., Sunway processors, CUDA/HIP-based GPUs, and ARM CPUs. (2) LICOMK++ overcomes the one simulated-years-per-day (SYPD) performance challenge for global realistic OGCM at $1-\mathrm{km}$ resolution. It records $\mathbf{1. 0 5}$ and 1.70 SYPD with a parallel efficiency of 54.8% and 55.6% scaling on almost the entire new Sunway supercomputer and two-thirds of the ORISE supercomputer. (3) LICOMK++ is the first global 1-km-resolution realistic OGCM to generate scientific results. It successfully reproduces mesoscale and submesoscale structures that have considerable climate effects.

Path planning is a crucial process for unmanned aerial vehicles (UAVs) and involves finding a path that is both short and safe. However, with the ever-increasing complexity of the environment, solving the UAV path-planning problem is challenging. Traditional path-planning methods cannot handle conflicting goals effectively, and existing objective methods lack targeted exploration mechanisms, resulting in unsatisfactory outcomes. By modeling the UAV path-planning problem via multi-objective optimization, this study designed a reasonable objective function composition for the model and considered obstacle avoidance as a hard constraint to satisfy the actual situation . A multi-objective evolutionary algorithm based on dimensional exploration and discrepancy evolution (MOEA-2DE) is presented. In particular, MOEA-2DE utilizes dimensional perturbation to identify key dimensions to facilitate prior exploration and enhance the targeted search. An adaptive evolution strategy based on population discrepancy was employed to assess the evolution process, and various methods were adopted to balance convergence and diversity. The effectiveness of the MOEA-2DE was demonstrated through the design of two intricate terrain sets and comparisons with various classic and state-of-the-art multi-objective evolutionary algorithms (MOEAs), including those designed for UAV path planning across multiple metrics. The results verify the superiority of MOEA-2DE in terms of both convergence speed and final effect.