❌

Normal view

Received — 8 April 2026 ⏭

Schema-Aware Planning and Hybrid Knowledge Toolset for Reliable Knowledge Graph Triple Verification

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xinyan Ma (Harbin Institute of Technology · Harbin · China) · Xianhao Ou (Harbin Institute of Technology · Harbin · China) · Weihao Zhang (Harbin Institute of Technology · Harbin · China) · Shixin Jiang (Harbin Institute of Technology · Harbin · China) · Runxuan Liu (Harbin Institute of Technology · Harbin · China) · Dandan Tu (Huawei Technologies Co. · Ltd. · Beijing · China) · Lei Chen (Bay Area International Business School · Beijing Normal University · Beijing · China) · Ming Liu (Harbin Institute of Technology · Harbin · China) · Bing Qin (Harbin Institute of Technology · Harbin · China)
7 April 2026 at 12:00
arXiv:2604.04190v1 Announce Type: new Abstract: Knowledge Graphs (KGs) serve as a critical foundation for AI systems, yet their automated construction inevitably introduces noise, compromising data trustworthiness. Existing triple verification methods, based on graph embeddings or language models, often suffer from single-source bias by relying on either internal structural constraints or external semantic evidence, and usually follow a static inference paradigm. As a result, they struggle with complex or long-tail facts and provide limited interpretability. To address these limitations, we propose SHARP (Schema-Hybrid Agent for Reliable Prediction), a training-free autonomous agent that reformulates triple verification as a dynamic process of strategic planning, active investigation, and evidential reasoning. Specifically, SHARP combines a Memory-Augmented Mechanism with Schema-Aware Strategic Planning to improve reasoning stability, and employs an enhanced ReAct loop with a Hybrid Knowledge Toolset to dynamically integrate internal KG structure and external textual evidence for cross-verification. Experiments on FB15K-237 and Wikidata5M-Ind show that SHARP significantly outperforms existing state-of-the-art baselines, achieving accuracy gains of 4.2% and 12.9%, respectively. Moreover, SHARP provides transparent, fact-based evidence chains for each judgment, demonstrating strong interpretability and robustness for complex verification tasks.

Multi-omics integration and machine learning reveal gut-immune signatures in idiopathic pulmonary fibrosis: insights from bulk RNA-seq, single-cell profiles, spatial transcriptomics, and experimental validation

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Zhengyu Hu · Jiaqi Wang · Jialin Yu · Zheqing Hu · Jing Xue · Zhanbing Ma · Miaomiao Nian · Ruixin Qi · Tingting Zhao · Xia Cao · Hongxia Xin · Xiuyan Wang · Guilan Yang · Zhenzhen Gui · Xiaoming Liu · Juan Chen
6 April 2026 at 18:00

Front Immunol. 2026 Mar 19;17:1730289. doi: 10.3389/fimmu.2026.1730289. eCollection 2026.

ABSTRACT

BACKGROUND: Idiopathic pulmonary fibrosis (IPF) is a progressive, fatal lung disease with limited treatment options and a poor prognosis. Recent studies suggest a critical role for the gut-immune-lung axis in IPF, yet the underlying molecular mechanisms remain unclear.

METHODS: The current study performed in silico multi-omics integration of publicly available datasets, including bulk RNA-seq, single-cell and spatial transcriptomics, as well as peripheral blood multi-omics data to uncover key molecular signatures in IPF. Furthermore, machine learning techniques were utilized to identify core genes, whereas functional analyses and Mendelian randomization were conducted to evaluate the causal relationships among gut microbiota, immune cells, and IPF. Additionally, experimental validation using qPCR and ELISA assays was conducted in vitro, in vivo, and in patient plasma to confirm the expression patterns of key genes.

RESULTS: Across integrated public bulk, single-cell, spatial, and blood multi-omics, CXCL13, IL33, TLR4, and IGF1 were identified as core IPF genes consistently linked to immune infiltration and fibrotic remodeling. Deconvolution, scRNA-seq, and spatial mapping localized their dysregulation to fibroblasts and immune compartments (notably B-cell, macrophage, and mast-cell axes), highlighting fibroblast-immune crosstalk in fibrotic foci. A four-gene model robustly distinguished IPF from controls across cohorts. Mendelian randomization supported a gut-immune-lung axis, indicating causal effects of specific gut taxa on IPF risk via immune phenotypes. qPCR/ELISA in TGF-β1-stimulated fibroblasts, bleomycin mouse lungs, and patient plasma corroborated upregulation of IL33, CXCL13, IGF1 and downregulation of TLR4. Drug-signature reversal nominated cucurbitacin I and temsirolimus; molecular docking was performed as a preliminary in silico, computer-simulation-based assessment of potential ligand-protein interactions between these compounds and the four core targets.

CONCLUSION: This study provides new insights into the importance of gut-immune-lung axis in IPF and identifies CXCL13, IL33, TLR4, and IGF1 as diagnostic signatures and therapeutic targets. By integrating public multi-omics resources with experimental validation, our findings offer a foundation for future diagnostic and treatment strategies aimed at modulating the gut microbiota and immune system in IPF.

PMID:41939867 | PMC:PMC13043422 | DOI:10.3389/fimmu.2026.1730289

Multi-omics integration and machine learning reveal gut-immune signatures in idiopathic pulmonary fibrosis: insights from bulk RNA-seq, single-cell profiles, spatial transcriptomics, and experimental validation

✇Omics In Lung
By: Zhengyu Hu · Jiaqi Wang · Jialin Yu · Zheqing Hu · Jing Xue · Zhanbing Ma · Miaomiao Nian · Ruixin Qi · Tingting Zhao · Xia Cao · Hongxia Xin · Xiuyan Wang · Guilan Yang · Zhenzhen Gui · Xiaoming Liu · Juan Chen
6 April 2026 at 18:00

Front Immunol. 2026 Mar 19;17:1730289. doi: 10.3389/fimmu.2026.1730289. eCollection 2026.

ABSTRACT

BACKGROUND: Idiopathic pulmonary fibrosis (IPF) is a progressive, fatal lung disease with limited treatment options and a poor prognosis. Recent studies suggest a critical role for the gut-immune-lung axis in IPF, yet the underlying molecular mechanisms remain unclear.

METHODS: The current study performed in silico multi-omics integration of publicly available datasets, including bulk RNA-seq, single-cell and spatial transcriptomics, as well as peripheral blood multi-omics data to uncover key molecular signatures in IPF. Furthermore, machine learning techniques were utilized to identify core genes, whereas functional analyses and Mendelian randomization were conducted to evaluate the causal relationships among gut microbiota, immune cells, and IPF. Additionally, experimental validation using qPCR and ELISA assays was conducted in vitro, in vivo, and in patient plasma to confirm the expression patterns of key genes.

RESULTS: Across integrated public bulk, single-cell, spatial, and blood multi-omics, CXCL13, IL33, TLR4, and IGF1 were identified as core IPF genes consistently linked to immune infiltration and fibrotic remodeling. Deconvolution, scRNA-seq, and spatial mapping localized their dysregulation to fibroblasts and immune compartments (notably B-cell, macrophage, and mast-cell axes), highlighting fibroblast-immune crosstalk in fibrotic foci. A four-gene model robustly distinguished IPF from controls across cohorts. Mendelian randomization supported a gut-immune-lung axis, indicating causal effects of specific gut taxa on IPF risk via immune phenotypes. qPCR/ELISA in TGF-β1-stimulated fibroblasts, bleomycin mouse lungs, and patient plasma corroborated upregulation of IL33, CXCL13, IGF1 and downregulation of TLR4. Drug-signature reversal nominated cucurbitacin I and temsirolimus; molecular docking was performed as a preliminary in silico, computer-simulation-based assessment of potential ligand-protein interactions between these compounds and the four core targets.

CONCLUSION: This study provides new insights into the importance of gut-immune-lung axis in IPF and identifies CXCL13, IL33, TLR4, and IGF1 as diagnostic signatures and therapeutic targets. By integrating public multi-omics resources with experimental validation, our findings offer a foundation for future diagnostic and treatment strategies aimed at modulating the gut microbiota and immune system in IPF.

PMID:41939867 | PMC:PMC13043422 | DOI:10.3389/fimmu.2026.1730289

SRSF10 promotes cisplatin resistance in bladder cancer via BIN1 Exon 12 retention and ANXA1 activation

✇Oncogene - Issue - nature.com science feeds
By: Mengqing Xiao · Yanni Ma · Ganghua Zhang · Guanjun Chen · Yuxing Zhu · Xiaoming Liu · Yaxin Cheng · Ziyang Feng · Ke Cao
6 April 2026 at 08:00

Oncogene, Published online: 06 April 2026; doi:10.1038/s41388-026-03735-7

SRSF10 promotes cisplatin resistance in bladder cancer via BIN1 Exon 12 retention and ANXA1 activation
Received — 4 April 2026 ⏭

Hierarchical Memory Orchestration for Personalized Persistent Agents

✇cs.AI, q-bio.NC updates on arXiv.org
By: Junming Liu · Yifei Sun · Weihua Cheng · Haodong Lei · Yuqi Li · Yirong Chen · Ding Wang
3 April 2026 at 12:00
arXiv:2604.01670v1 Announce Type: new Abstract: While long-term memory is essential for intelligent agents to maintain consistent historical awareness, the accumulation of extensive interaction data often leads to performance bottlenecks. Naive storage expansion increases retrieval noise and computational latency, overwhelming the reasoning capacity of models deployed on constrained personal devices. To address this, we propose Hierarchical Memory Orchestration (HMO), a framework that organizes interaction history into a three-tiered directory driven by user-centric contextual relevance. Our system maintains a compact primary cache, coupling recent and pivotal memories with an evolving user profile to ensure agent reasoning remains aligned with individual behavioral traits. This primary cache is complemented by a high-priority secondary layer, both of which are managed within a global archive of the full interaction history. Crucially, the user persona dictates memory redistribution across this hierarchy, promoting records mapped to long-term patterns toward more active tiers while relegating less relevant information. This targeted orchestration surfaces historical knowledge precisely when needed while maintaining a lean and efficient active search space. Evaluations on multiple benchmarks achieve state-of-the-art performance. Real-world deployments in ecosystems like OpenClaw demonstrate that HMO significantly enhances agent fluidity and personalization.
Received — 2 April 2026 ⏭

Scaling Whole-Body Human Musculoskeletal Behavior Emulation for Specificity and Diversity

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yunyue Wei · Chenhui Zuo · Shanning Zhuang · Haixin Gong · Yaming Liu · Yanan Sui
1 April 2026 at 12:00
arXiv:2603.29332v1 Announce Type: cross Abstract: The embodied learning of human motor control requires whole-body neuro-actuated musculoskeletal dynamics, while the internal muscle-driven processes underlying movement remain inaccessible to direct measurement. Computational modeling offers an alternative, but inverse dynamics methods struggled to resolve redundant control from observed kinematics in the high-dimensional, over-actuated system. Forward imitation approaches based on deep reinforcement learning exhibited inadequate tracking performance due to the curse of dimensionality in both control and reward design. Here we introduce a large-scale parallel musculoskeletal computation framework for biomechanically grounded whole-body motion reproduction. By integrating large-scale parallel GPU simulation with adversarial reward aggregation and value-guided flow exploration, the MS-Emulator framework overcomes key optimization bottlenecks in high-dimensional reinforcement learning for musculoskeletal control, which accurately reproduces a broad repertoire of motions in a whole-body human musculoskeletal system actuated by approximately 700 muscles. It achieved high joint angle accuracy and body position alignment for highly dynamic tasks such as dance, cartwheel, and backflip. The framework was also used to explore the musculoskeletal control solution space, identifying distinct musculoskeletal control policies that converge to nearly identical external kinematic and mechanical measurements. This work establishes a tractable computational route to analyzing the specificity and diversity underlying human embodied control of movement. Project page: https://lnsgroup.cc/research/MS-Emulator.

X-World: Controllable Ego-Centric Multi-Camera World Models for Scalable End-to-End Driving

✇cs.AI, q-bio.NC updates on arXiv.org
By: Chaoda Zheng · Sean Li · Jinhao Deng · Zhennan Wang · Shijia Chen · Liqiang Xiao · Ziheng Chi · Hongbin Lin · Kangjie Chen · Boyang Wang · Yu Zhang · Xianming Liu
1 April 2026 at 12:00
arXiv:2603.19979v2 Announce Type: replace-cross Abstract: Scalable and reliable evaluation is increasingly critical in the end-to-end era of autonomous driving, where vision--language--action (VLA) policies directly map raw sensor streams to driving actions. Yet, current evaluation pipelines still rely heavily on real-world road testing, which is costly, biased toward limited scenario coverage, and difficult to reproduce. These challenges motivate a real-world simulator that can generate realistic future observations under proposed actions, while remaining controllable and stable over long horizons. We present X-World, an action-conditioned multi-camera generative world model that simulates future observations directly in video space. Given synchronized multi-view camera history and a future action sequence, X-World generates future multi-camera video streams that follow the commanded actions. To ensure reproducible and editable scene rollouts, X-World further supports optional controls over dynamic traffic agents and static road elements, and retains a text-prompt interface for appearance-level control (e.g., weather and time of day). Beyond world simulation, X-World also enables video style transfer by conditioning on appearance prompts while preserving the underlying action and scene dynamics. At the core of X-World is a multi-view latent video generator designed to explicitly encourage cross-view geometric consistency and temporal coherence under diverse control signals. Experiments show that X-World achieves high-quality multi-view video generation with (i) strong view consistency across cameras, (ii) stable temporal dynamics over long rollouts, and (iii) high controllability with strict action following and faithful adherence to optional scene controls. These properties make X-World a practical foundation for scalable and reproducible evaluation.
Received — 26 March 2026 ⏭

EVA: Aligning Video World Models with Executable Robot Actions via Inverse Dynamics Rewards

✇cs.AI, q-bio.NC updates on arXiv.org
By: Ruixiang Wang · Qingming Liu · Yueci Deng · Guiliang Liu · Zhen Liu · Kui Jia
25 March 2026 at 12:00
arXiv:2603.17808v2 Announce Type: replace-cross Abstract: Video generative models are increasingly used as world models for robotics, where a model generates a future visual rollout conditioned on the current observation and task instruction, and an inverse dynamics model (IDM) converts the generated frames into executable robot actions. However, current video world models lack explicit executability constraints. As a result, visually coherent rollouts may still violate rigid-body and kinematic consistency, producing unstable or infeasible control commands when decoded by an IDM. We refer to this mismatch between visual generation and physically executable control as the executability gap. While this gap can be mitigated at inference time using techniques such as rejection sampling, such approaches are inefficient due to the high cost of video generation. In this paper, we leverage the executability gap as a training signal and introduce Executable Video Alignment (EVA), a reinforcement-learning post-training framework for aligning video world models. EVA trains an inverse dynamics model on real robot trajectories and repurposes it as a reward model that evaluates generated videos through the action sequences they induce, encouraging smooth motions measured by velocity, acceleration, and jerk while penalizing actions that violate embodiment constraints. Importantly, the reward remains informative even when generated videos contain severe visual artifacts, since such artifacts typically translate into unstable or out-of-bound actions. Experiments on the RoboTwin benchmark and a real bimanual robot show that EVA reduces embodiment-specific artifacts in generated rollouts and improves downstream task execution success.

Boosting foundation models for rare eye disease diagnosis via a multimodal text-to-image generative framework

✇npj Digital Medicine
By: Ruoyu Chen · Weiyi Zhang · Bowen Liu · Xinyuan Wu · Xiaolan Chen · Pusheng Xu · Shunming Liu · Mingguang He · Danli Shi
24 March 2026 at 08:00

npj Digital Medicine, Published online: 24 March 2026; doi:10.1038/s41746-026-02560-2

Boosting foundation models for rare eye disease diagnosis via a multimodal text-to-image generative framework
Received — 17 March 2026 ⏭

daVinci-Env: Open SWE Environment Synthesis at Scale

✇cs.AI, q-bio.NC updates on arXiv.org
By: Dayuan Fu · Shenyu Wu · Yunze Wu · Zerui Peng · Yaxing Huang · Jie Sun · Ji Zeng · Mohan Jiang · Lin Zhang · Yukun Li · Jiarui Hu · Liming Liu · Jinlong Hou · Pengfei Liu
16 March 2026 at 12:00
arXiv:2603.13023v1 Announce Type: cross Abstract: Training capable software engineering (SWE) agents demands large-scale, executable, and verifiable environments that provide dynamic feedback loops for iterative code editing, test execution, and solution refinement. However, existing open-source datasets remain limited in scale and repository diversity, while industrial solutions are opaque with unreleased infrastructure, creating a prohibitive barrier for most academic research groups. We present OpenSWE, the largest fully transparent framework for SWE agent training in Python, comprising 45,320 executable Docker environments spanning over 12.8k repositories, with all Dockerfiles, evaluation scripts, and infrastructure fully open-sourced for reproducibility. OpenSWE is built through a multi-agent synthesis pipeline deployed across a 64-node distributed cluster, automating repository exploration, Dockerfile construction, evaluation script generation, and iterative test analysis. Beyond scale, we propose a quality-centric filtering pipeline that characterizes the inherent difficulty of each environment, filtering out instances that are either unsolvable or insufficiently challenging and retaining only those that maximize learning efficiency. With $891K spent on environment construction and an additional $576K on trajectory sampling and difficulty-aware curation, the entire project represents a total investment of approximately $1.47 million, yielding about 13,000 curated trajectories from roughly 9,000 quality guaranteed environments. Extensive experiments validate OpenSWE's effectiveness: OpenSWE-32B and OpenSWE-72B achieve 62.4% and 66.0% on SWE-bench Verified, establishing SOTA among Qwen2.5 series. Moreover, SWE-focused training yields substantial out-of-domain improvements, including up to 12 points on mathematical reasoning and 5 points on science benchmarks, without degrading factual recall.
Received — 11 March 2026 ⏭

Thinking with Gaze: Sequential Eye-Tracking as Visual Reasoning Supervision for Medical VLMs

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yiwei Li · Zihao Wu · Yanjun Lv · Hanqi Jiang · Weihang You · Zhengliang Liu · Dajiang Zhu · Xiang Li · Quanzheng Li · Tianming Liu · Lin Zhao
10 March 2026 at 12:00
arXiv:2603.06697v1 Announce Type: cross Abstract: Vision--language models (VLMs) process images as visual tokens, yet their intermediate reasoning is often carried out in text, which can be suboptimal for visually grounded radiology tasks. Radiologists instead diagnose via sequential visual search; eye-tracking captures this process as time-ordered gaze trajectories that reveal how evidence is acquired over time. We use eye-gaze as supervision to guide VLM reasoning by introducing a small set of dedicated gaze tokens. These tokens are trained to predict gaze-selected image patch indices in temporal order, encouraging the model to follow human-like evidence acquisition and integration. Experiments on MIMIC-EYE and multiple external zero-shot benchmarks show consistent gains over baselines, achieving state-of-the-art in-domain performance and improved out-of-domain robustness. These results highlight temporally ordered gaze as an effective supervision signal for learning visually grounded medical reasoning.

Hit-RAG: Learning to Reason with Long Contexts via Preference Alignment

✇cs.AI, q-bio.NC updates on arXiv.org
By: Junming Liu · Yuqi Li · Shiping Wen · Zhigang Zeng · Tingwen Huang
10 March 2026 at 12:00
arXiv:2603.07023v1 Announce Type: cross Abstract: Despite the promise of Retrieval-Augmented Generation in grounding Multimodal Large Language Models with external knowledge, the transition to extensive contexts often leads to significant attention dilution and reasoning hallucinations. The surge in information density causes critical evidence to be submerged by voluminous noise, which complicates the discernment of relevant fragments within a dense input. In this paper, we propose \textbf{Hit-RAG}, a multi-stage preference alignment framework designed to resolve these cognitive bottlenecks through a progressive optimization pipeline. Our approach systematically refines the utilization of external evidence via three distinct stages. First, Supervised Fine-tuning establishes baseline context awareness to minimize information neglect. Next, Discriminative Preference Alignment enhances robustness against misleading distractors. Finally, Group-Relative Policy Optimization stabilizes logical synthesis to prevent reasoning collapse. Extensive evaluations on eight benchmarks demonstrate that Hit-RAG consistently yields substantial performance gains, enabling models to bridge the gap between context acquisition and accurate reasoning while surpassing much larger counterparts in long-context scenarios.
Received — 5 March 2026 ⏭

IntPro: A Proxy Agent for Context-Aware Intent Understanding via Retrieval-conditioned Inference

✇cs.AI, q-bio.NC updates on arXiv.org
By: Guanming Liu · Meng Wu · Peng Zhang · Yu Zhang · Yubo Shu · Xianliang Huang · Kainan Tu · Ning Gu · Liuxin Zhang · Qianying Wang · Tun Lu
5 March 2026 at 13:00
arXiv:2603.03325v1 Announce Type: cross Abstract: Large language models (LLMs) have become integral to modern Human-AI collaboration workflows, where accurately understanding user intent serves as a crucial step for generating satisfactory responses. Context-aware intent understanding, which involves inferring user intentions from situational environments, is inherently challenging because it requires reasoning over both the immediate context and the user's underlying motivations that drive their behavior. Moreover, existing approaches often treat intent understanding as a static recognition task, overlooking users' accumulated intent patterns that could provide valuable references for more accurate and generalizable understanding. To address this gap, we propose IntPro, a proxy agent that learns to adapt to individual users via retrieval-conditioned intent inference. We design intent explanations that abstract how contextual signals connect to expressed intents, and store them in an individual intent history library for retrieval. We train IntPro through supervised fine-tuning on retrieval-conditioned trajectories and multi-turn Group Relative Policy Optimization (GRPO) with tool-aware reward functions, enabling the agent to learn when to leverage historical intent patterns and when to infer directly. Experiments across three diverse scenarios (Highlight-Intent, MIntRec2.0, and Weibo Post-Sync) demonstrate that IntPro achieves strong intent understanding performance with effective context-aware reasoning capabilities across different scenarios and model types.

Merlin: A Computed Tomography Vision-Language Foundation Model and Dataset

✇cs.AI, q-bio.NC updates on arXiv.org
By: Louis Blankemeier · Ashwin Kumar · Joseph Paul Cohen · Jiaming Liu · Longchao Liu · Dave Van Veen · Syed Jamal Safdar Gardezi · Hongkun Yu · Magdalini Paschali · Zhihong Chen · Jean-Benoit Delbrouck · Eduardo Reis · Robbie Holland · Cesar Truyts · Christian Bluethgen · Yufu Wu · Long Lian · Malte Engmann Kjeldskov Jensen · Sophie Ostmeier · Maya Varma · Jeya Maria Jose Valanarasu · Zhongnan Fang · Zepeng Huo · Zaid Nabulsi · Diego Ardila · Wei-Hung Weng · Edson Amaro Junior · Neera Ahuja · Jason Fries · Nigam H. Shah · Greg Zaharchuk · Marc Willis · Adam Yala · Andrew Johnston · Robert D. Boutin · Andrew Wentland · Curtis P. Langlotz · Jason Hom · Sergios Gatidis · Akshay S. Chaudhari
5 March 2026 at 13:00
arXiv:2406.06512v2 Announce Type: replace-cross Abstract: The large volume of abdominal computed tomography (CT) scans coupled with the shortage of radiologists have intensified the need for automated medical image analysis tools. Previous state-of-the-art approaches for automated analysis leverage vision-language models (VLMs) that jointly model images and radiology reports. However, current medical VLMs are generally limited to 2D images and short reports. Here to overcome these shortcomings for abdominal CT interpretation, we introduce Merlin, a 3D VLM that learns from volumetric CT scans, electronic health record data and radiology reports. This approach is enabled by a multistage pretraining framework that does not require additional manual annotations. We trained Merlin using a high-quality clinical dataset of paired CT scans (>6 million images from 15,331 CT scans), diagnosis codes (>1.8 million codes) and radiology reports (>6 million tokens). We comprehensively evaluated Merlin on 6 task types and 752 individual tasks that covered diagnostic, prognostic and quality-related tasks. The non-adapted (off-the-shelf) tasks included zero-shot classification of findings (30 findings), phenotype classification (692 phenotypes) and zero-shot cross-modal retrieval (image-to-findings and image-to-impression). The model-adapted tasks included 5-year chronic disease prediction (6 diseases), radiology report generation and 3D semantic segmentation (20 organs). We validated Merlin at scale, with internal testing on 5,137 CT scans and external testing on 44,098 CT scans from 3 independent sites and 2 public datasets. The results demonstrated high generalization across institutions and anatomies. Merlin outperformed 2D VLMs, CT foundation models and off-the-shelf radiology models. We also release our trained models, code, and dataset, available at: https://github.com/StanfordMIMI/Merlin.

xLLM Technical Report

✇cs.AI, q-bio.NC updates on arXiv.org
By: Tongxuan Liu · Tao Peng · Peijun Yang · Xiaoyang Zhao · Xiusheng Lu · Weizhe Huang · Zirui Liu · Xiaoyu Chen · Zhiwei Liang · Jun Xiong · Donghe Jin · Minchao Zhang · Jinrong Guo · Yingxu Deng · Xu Zhang · Xianzhe Dong · Siqi Wang · Siyu Wu · Yu Wu · Zihan Tang · Yuting Zeng · Yanshu Wang · Jinguang Liu · Meng Kang · Menxin Li · Yunlong Wang · Yiming Liu · Xiaolong Ma · Yifan Wang · Yichen Zhang · Jinrun Yin · Keyang Zheng · Jiawei Yin · Jun Zhang · Ziyue Wang · Xiaobo Lin · Liangyu Liu · Liwei Lan · Yang Liu · Chunhua Peng · Han Liu · Songcheng Ren · Xuezhu Wang · Yunheng Shen · Yi Wang · Guyue Liu · Yitao Hu · Hui Chen · Tong Yang · Hailong Yang · Jing Li · Guiguang Ding · Ke Zhang
4 March 2026 at 13:00
arXiv:2510.14686v2 Announce Type: replace-cross Abstract: We introduce xLLM, an intelligent and efficient Large Language Model (LLM) inference framework designed for high-performance, large-scale enterprise-grade serving, with deep optimizations for diverse AI accelerators. To address these challenges, xLLM builds a novel decoupled service-engine architecture. At the service layer, xLLM-Service features an intelligent scheduling module that efficiently processes multimodal requests and co-locates online and offline tasks through unified elastic scheduling to maximize cluster utilization. This module also relies on a workload-adaptive dynamic Prefill-Decode (PD) disaggregation policy and a novel Encode-Prefill-Decode (EPD) disaggregation policy designed for multimodal inputs. Furthermore, it incorporates a distributed architecture to provide global KV Cache management and robust fault-tolerant capabilities for high availability. At the engine layer, xLLM-Engine co-optimizes system and algorithm designs to fully saturate computing resources. This is achieved through comprehensive multi-layer execution pipeline optimizations, an adaptive graph mode and an xTensor memory management. xLLM-Engine also further integrates algorithmic enhancements such as optimized speculative decoding and dynamic EPLB, collectively serving to substantially boost throughput and inference efficiency. Extensive evaluations demonstrate that xLLM delivers significantly superior performance and resource efficiency. Under identical TPOT constraints, xLLM achieves throughput up to 1.7x that of MindIE and 2.2x that of vLLM-Ascend with Qwen-series models, while maintaining an average throughput of 1.7x that of MindIE with Deepseek-series models. xLLM framework is publicly available at https://github.com/jd-opensource/xllm and https://github.com/jd-opensource/xllm-service.
Received — 25 February 2026 ⏭

A Very Big Video Reasoning Suite

✇cs.AI, q-bio.NC updates on arXiv.org
By: Maijunxian Wang, Ruisi Wang, Juyi Lin, Ran Ji, Thadd\"aus Wiedemer, Qingying Gao, Dezhi Luo, Yaoyao Qian, Lianyu Huang, Zelong Hong, Jiahui Ge, Qianli Ma, Hang He, Yifan Zhou, Lingzi Guo, Lantao Mei, Jiachen Li, Hanwen Xing, Tianqi Zhao, Fengyuan Yu, Weihang Xiao, Yizheng Jiao, Jianheng Hou, Danyang Zhang, Pengcheng Xu, Boyang Zhong, Zehong Zhao, Gaoyun Fang, John Kitaoka, Yile Xu, Hua Xu, Kenton Blacutt, Tin Nguyen, Siyuan Song, Haoran Sun, Shaoyue Wen, Linyang He, Runming Wang, Yanzhi Wang, Mengyue Yang, Ziqiao Ma, Rapha\"el Milli\`ere, Freda Shi, Nuno Vasconcelos, Daniel Khashabi, Alan Yuille, Yilun Du, Ziming Liu, Bo Li, Dahua Lin, Ziwei Liu, Vikash Kumar, Yijiang Li, Lei Yang, Zhongang Cai, Hokin Deng
24 February 2026 at 13:00
arXiv:2602.20159v1 Announce Type: cross Abstract: Rapid progress in video models has largely focused on visual quality, leaving their reasoning capabilities underexplored. Video reasoning grounds intelligence in spatiotemporally consistent visual environments that go beyond what text can naturally capture, enabling intuitive reasoning over spatiotemporal structure such as continuity, interaction, and causality. However, systematically studying video reasoning and its scaling behavior is hindered by the lack of large-scale training data. To address this gap, we introduce the Very Big Video Reasoning (VBVR) Dataset, an unprecedentedly large-scale resource spanning 200 curated reasoning tasks following a principled taxonomy and over one million video clips, approximately three orders of magnitude larger than existing datasets. We further present VBVR-Bench, a verifiable evaluation framework that moves beyond model-based judging by incorporating rule-based, human-aligned scorers, enabling reproducible and interpretable diagnosis of video reasoning capabilities. Leveraging the VBVR suite, we conduct one of the first large-scale scaling studies of video reasoning and observe early signs of emergent generalization to unseen reasoning tasks. Together, VBVR lays a foundation for the next stage of research in generalizable video reasoning. The data, benchmark toolkit, and models are publicly available at https://video-reason.com/ .

ALOE: Action-Level Off-Policy Evaluation for Vision-Language-Action Model Post-Training

✇cs.AI, q-bio.NC updates on arXiv.org
By: Rushuai Yang · Hecheng Wang · Chiming Liu · Xiaohan Yan · Yunlong Wang · Xuan Du · Shuoyu Yue · Yongcheng Liu · Chuheng Zhang · Lizhe Qi · Yi Chen · Wei Shan · Maoqing Yao
24 February 2026 at 13:00
arXiv:2602.12691v2 Announce Type: replace-cross Abstract: We study how to improve large foundation vision-language-action (VLA) systems through online reinforcement learning (RL) in real-world settings. Central to this process is the value function, which provides learning signals to guide VLA learning from experience. In practice, the value function is estimated from trajectory fragments collected from different data sources, including historical policies and intermittent human interventions. Estimating the value function of current behavior quality from the mixture data is inherently an off-policy evaluation problem. However, prior work often adopts conservative on-policy estimation for stability, which avoids direct evaluation of the current high-capacity policy and limits learning effectiveness. In this paper, we propose ALOE, an action-level off-policy evaluation framework for VLA post-training. ALOE applies chunking-based temporal-difference bootstrapping to evaluate individual action sequences instead of predicting final task outcomes. This design improves effective credit assignment to critical action chunks under sparse rewards and supports stable policy improvement. We evaluate our method on three real-world manipulation tasks, including smartphone packing as a high-precision task, laundry folding as a long-horizon deformable-object task, and bimanual pick-and-place involving multi-object perception. Across all tasks, ALOE improves learning efficiency without compromising execution speed, showing that off-policy RL can be reintroduced in a reliable manner for real-world VLA post-training. Videos and additional materials are available at our project website.
There are no more articles
❌