I ntelligent drug recommendation based on Electronic Health Records (EHRs) is critical for improving the quality and efficiency of clinical decision - making . By leveraging large - scale patient data, drug recommendation systems can assist physicians in selecting the most appropriate medications according to a patient's medical history, diagnoses, laboratory results, and comorbidities. Recent advances in large language models (LLMs) have shown remarkable capabilities in complex reasoning and medical text understanding, making them promising tools for drug recommendation tasks. However, the application of LLMs for Chinese clinical medication recommendation remains l argely unexplored. In this work, we conduct a systematic investigation of LLM - based methodologies for Chinese discharge medication recommendation . W e evaluate several representative LLM families (GLM, Llama, Qwen) under a unified methodological framework including zero - shot prompting, in - context learning, chain - of - thought prompting, and supervised fine - tuning using LoRA. W e analyze model behavior acro ss reasoning styles, error patterns, domain adaptation mechanisms, and robustness . Experimental results show that while supervised fine - tuning improves model performance, there remains substantial room for improvement, with the best model achieving the F1 score of 0.5648 and Jaccard score of 0.4477 . Our findings highlight both the potential and limitations of LLMs for Chinese drug recommendation.

As large language models (LLMs) become increasingly integrated into applications serving users across diverse cultures, communities and demographics, it is critical to align LLMs with pluralistic human values beyond average principles (e.g., HHH). In psychological and social value theories such as Schwartz's Value Theory, pluralistic values are represented by multiple value dimensions paired with various priorities. However, existing methods encounter two challenges when aligning with such fine-grained value objectives: 1) they often treat multiple values as independent and equally important, ignoring their interdependence and relative priorities (value complexity); 2) they struggle to precisely control nuanced value priorities, especially those underrepresented ones (value steerability). To handle these challenges, we propose COUPLE, a COUnterfactual reasoning framework for PLuralistic valuE alignment. It introduces a structural causal model (SCM) to feature complex interdependency and prioritization among features, as well as the causal relationship between high-level value dimensions and behaviors. Moreover, it applies counterfactual reasoning to generate outputs aligned with any desired value objectives. Benefitting from explicit causal modeling, COUPLE also provides better interpretability. We evaluate COUPLE on two datasets with different value systems and demonstrate that COUPLE advances other baselines across diverse types of value objectives.

Large language models (LLMs) have been shown to internalize human-like biases during finetuning, yet the mechanisms by which these biases manifest remain unclear. In this work, we investigated whether the well-known Knobe effect, a moral bias in intentionality judgements, emerges in finetuned LLMs and whether it can be traced back to specific components of the model. We conducted a Layer-Patching analysis across 3 open-weights LLMs and demonstrated that the bias is not only learned during finetuning but also localized in a specific set of layers. Surprisingly, we found that patching activations from the corresponding pretrained model into just a few critical layers is sufficient to eliminate the effect. Our findings offer new evidence that social biases in LLMs can be interpreted, localized, and mitigated through targeted interventions, without the need for model retraining.

KV cache has traditionally been stored in GPU memory to accelerate the decoding phase of large language model (LLM) inference. However, it is increasingly necessary to move KV caches outside GPU devices, to enable cache reuse across different queries and inference engines. Our real-world usage statistics confirm this trend: over time, the total KV cache stored by users has grown rapidly, far exceeding the capacity of GPU memory. Despite this need, there lacks an efficient solution for offloading and transferring KV caches. We present LMCACHE, the first and so far the most efficient open-source KV caching solution, which extracts and stores KV caches generated by modern LLM engines (vLLM and SGLang) out of the GPU memory and shares them across engines and queries. LMCACHE supports both cache offloading (prefix reuse across queries) and prefill-decode (PD) disaggregation (cross-engine/GPU cache transfer). LMCACHE's high performance and wide adoption stem from the following contributions: (1) highly optimized KV cache data movement powered by batched data movement operations, compute and I/O pipelining; (2) a modular KV cache connector component, decoupling LMCACHE from the rapid evolution of inference engines; (3) a first-class control API for flexible cache orchestration across GPU, CPU, storage, and network layers. Our evaluation shows that combining LMCACHE with vLLM achieves up to 15x improvement in throughput across workloads such as multi-round question answering and document analysis. Large-scale adoption of LMCACHE in enterprise settings provides us valuable insights, for example, fetching KV cache from remote storage has unsurprisingly benefits to prefill delay, and that context truncation, which is a widely applied technique in industry, can greatly reduce prefix cache hit ratio by half. The source code of LMCACHE is at: https://github.com/LMCache/LMCache.

Abstract--Amid the rapid rise of agentic dialogue models, realistic user-simulator studies are essential for tuning effective conversation strategies. This work investigates a sales-oriented agent that adapts its dialogue based on user profiles spanning age, gender, and occupation. While age and gender influence overall performance, occupation produces the most pronounced differences in conversational intent. Leveraging this insight, we introduce a lightweight, occupation-conditioned strategy that guides the agent to prioritize intents aligned with user preferences, resulting in shorter and more successful dialogues. Our findings highlight the importance of rich simulator profiles and demonstrate how simple persona-informed strategies can enhance the effectiveness of sales-oriented dialogue systems. With the ongoing evolution of Agentic AI, researchers have begun to explore its application across diverse domains. Among these, dialogue systems designed for business recommendation tasks have attracted significant attention.

Large-scale Mixture of Experts (MoE) Large Language Models (LLMs) have recently become the frontier open weight models, achieving remarkable model capability similar to proprietary ones. But their random expert selection mechanism introduces significant data movement overhead that becomes the dominant bottleneck in multi-unit LLM serving systems. To understand the patterns underlying this data movement, we conduct comprehensive data-movement-centric profiling across four state-of-the-art large-scale MoE models released in 2025 (200B-1000B) using over 24,000 requests spanning diverse workloads. We perform systematic analysis from both temporal and spatial perspectives and distill six key insights to guide the design of diverse future serving systems. With our insights, we then demonstrate how to improve wafer-scale GPUs as a case study, and show that minor architectural modifications leveraging the insights achieve substantial performance gains, delivering 5.3x and 3.1x average speedups on DeepSeek V3 and Qwen3, respectively. Our work presents the first comprehensive data-centric analysis of large-scale MoE models and a concrete design study using the learned lessons, with profiling traces and simulation framework already open-sourced with $>$1k downloads. Our traces and results are publicly available at https://huggingface.co/datasets/core12345/MoE_expert_selection_trace

While contrast-enhanced CT (CECT) is standard for assessing abdominal aortic aneurysms (AAA), the required iodinated contrast agents pose significant risks, including nephrotoxicity, patient allergies, and environmental harm. To reduce contrast agent use, recent deep learning methods have focused on generating synthetic CECT from non-contrast CT (NCCT) scans. However, most adopt a multi-stage pipeline that first generates images and then performs segmentation, which leads to error accumulation and fails to leverage shared semantic and anatomical structures. To address this, we propose a unified deep learning framework that generates synthetic CECT images from NCCT scans while simultaneously segmenting the aortic lumen and thrombus. Our approach integrates conditional diffusion models (CDM) with multi-task learning, enabling end-to-end joint optimization of image synthesis and anatomical segmentation. Unlike previous multitask diffusion models, our approach requires no initial predictions (e.g., a coarse segmentation mask), shares both encoder and decoder parameters across tasks, and employs a semi-supervised training strategy to learn from scans with missing segmentation labels, a common constraint in real-world clinical data. We evaluated our method on a cohort of 264 patients, where it consistently outperformed state-of-the-art single-task and multi-stage models. For image synthesis, our model achieved a PSNR of 25.61 dB, compared to 23.80 dB from a single-task CDM. For anatomical segmentation, it improved the lumen Dice score to 0.89 from 0.87 and the challenging thrombus Dice score to 0.53 from 0.48 (nnU-Net). These segmentation enhancements led to more accurate clinical measurements, reducing the lumen diameter MAE to 4.19 mm from 5.78 mm and the thrombus area error to 33.85% from 41.45% when compared to nnU-Net. Code is available at https://github.com/yuxuanou623/AortaDiff.git.

Parallel LLM inference scaling involves sampling a set of $N>1$ responses for a single input prompt. However, these $N$ parallel responses tend to be generated independently from each other, partitioning compute resources and leaving potentially useful information in one generation untapped by others. This is in contrast to response length scaling where past computation is used in all future steps. For higher quality responses and response sets, we propose Bridge to generate interdependent responses in parallel by rethinking batched LLM hidden states as holistic tensors rather than independent slices. With only a small amount (2.8%-5.1%) of new parameters, Bridge improves the relative mean accuracy gains from reinforcement learning with verifiable rewards by up to 39% and boosts consistency of correct responses. Trained once, Bridge scales to any generation width, all with greater performance than independent generations, unlocking a more general mode of parallel scaling that effectively leverages information between sequences, compatible with any post-generation aggregation technique.

Social recommendation has been proven effective in addressing data sparsity in user-item interaction modeling by leveraging social networks. The recent integration of Graph Neural Networks (GNNs) has further enhanced prediction accuracy in contemporary social recommendation algorithms. However, many GNN-based approaches in social recommendation lack the ability to furnish meaningful explanations for their predictions. In this study, we confront this challenge by introducing SoREX, a self-explanatory GNN-based social recommendation framework. SoREX adopts a two-tower framework enhanced by friend recommendation, independently modeling social relations and user-item interactions, while jointly optimizing an auxiliary task to reinforce social signals. To offer explanations, we propose a novel ego-path extraction approach. This method involves transforming the ego-net of a target user into a collection of multi-hop ego-paths, from which we extract factor-specific and candidate-aware ego-path subsets as explanations. This process facilitates the summarization of detailed comparative explanations among different candidate items through intricate substructure analysis. Furthermore, we conduct explanation re-aggregation to explicitly correlate explanations with downstream predictions, imbuing our framework with inherent self-explainability. Comprehensive experiments conducted on four widely adopted benchmark datasets validate the effectiveness of SoREX in predictive accuracy. Additionally, qualitative and quantitative analyses confirm the efficacy of the extracted explanations in SoREX. Our code and data are available at https://github.com/antman9914/SoREX.

Phase classification has become a prototypical benchmark for data-driven analysis of condensed matter physics. The type and complexity of the phase transition dictate the level of complexity of the algorithm one has to employ. This topic has been broadly explored, offering a menu of both supervised and unsupervised techniques ranging from simple clustering [1-3] to more complex machine learning methods [4-7]. The phase classification problem is most commonly posed like so: we allow our model to view a dataset that is both relevant and straightforwardly obtainable in the scenario we wish to study. We introduce this data set to a model that has no prior knowledge of underlying physics.