❌

Normal view

Received — 27 May 2026 ⏭

Mechanisms and reversal strategies of liver fibrosis: from regulation of cell fate to clinical translation

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Chuhan Zeng · Qiuxia Lu · Qi Zhao · Jian Li
26 May 2026 at 18:00

J Transl Med. 2026 May 25. doi: 10.1186/s12967-026-08312-w. Online ahead of print.

ABSTRACT

BACKGROUND: Liver fibrosis is a dynamic and reversible pathological process underlying chronic liver diseases, characterized by excessive extracellular matrix deposition and progressive hepatic architectural distortion. It acts as a critical precursor to cirrhosis, hepatic decompensation, and hepatocellular carcinoma, imposing a substantial global disease burden.

MAIN BODY: Accumulating evidence indicates that liver fibrosis is a highly plastic process governed by multicellular crosstalk, immune microenvironment remodeling, epigenetic-metabolic coupling, and mechanotransduction. This review outlines core cellular effectors and their heterogeneity revealed by single-cell omics, and highlights key regulatory layers including circadian rhythm, epigenetic imprinting, metabolic reprogramming, and the gut-liver axis, as well as etiology-specific differences in fibrosis progression, reversibility, and therapeutic response. We also summarize advances in non-invasive diagnosis and clinical translation of anti-fibrotic therapies, and discuss key bottlenecks leading to clinical trial failures.

CONCLUSION: A deeper understanding of cell fate regulation and multicellular ecosystem remodeling will facilitate the development of precise strategies to achieve meaningful fibrosis regression and improve long-term clinical outcomes in chronic liver diseases.

PMID:42185911 | DOI:10.1186/s12967-026-08312-w

When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yifan Zeng · Yiran Wu · Yaolun Zhang · Wentian Zhao · Kun Wan · Qingyun Wu · Huazheng Wang
26 May 2026 at 12:00
arXiv:2605.24202v1 Announce Type: new Abstract: Multi-agent LLM workflows route inference through specialized roles to lift end-task accuracy, but jointly training those roles with reinforcement learning is unstable in ways that are poorly understood. We study when end-to-end RL training of multi-agent LLM workflows improves over their base models, comparing Shared-Policy training, where all roles update one policy, with Isolated-Policy training, where each role has its own parameters. Our experimental matrix spans Eval-Opt, Voting, and Orch-Workers workflows, math and code tasks, and three model scales (0.6B, 1.7B, 4B). We find that multi-agent RL usually improves over base models, but gains depend jointly on workflow, task, and scale, not on policy sharing alone. Isolated-Policy tends to reach higher peak accuracy yet more often falls off a terminal accuracy cliff, while Shared-Policy training does not eliminate failure; it redistributes failure into qualitatively different patterns. We then explain the strongest of these patterns through role-level gradient dynamics induced by workflow topology and policy routing: under Isolated-Policy, parallel same-role agents on shared prompts amplify per-role gradients and drive terminal degradation in Voting and Orch-Workers workflows; under Shared-Policy, asymmetric per-step gradient mass causes the shared policy to be captured by the dominant role, producing different failure signatures by task and workflow. Together, the empirical map and its underlying mechanisms show that policy sharing routes training pressure through different channels rather than offering uniform stability, making it a design choice with workflow- and task-conditional tradeoffs.

Don't Retrain, Just Reuse: Recovering Dual-Target Molecules from Single-Target Diffusion Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Qingyuan Zeng · Pengxiang Cai · Zixin Guan · Ziyang Chen · Anglin Liu · Lang Qin · Xinyao Lai · Jintai Chen
26 May 2026 at 12:00
arXiv:2605.25681v1 Announce Type: cross Abstract: Designing a single molecule that modulates two targets is a promising strategy for polypharmacology, but it remains substantially harder than standard single-target generation because one candidate must satisfy two binding requirements while preserving drug-likeness and synthesizability. Existing dual-target generative methods typically introduce dual-target capability by either retraining the generator or intervening in the diffusion process during sampling. The former can be costly and difficult to stabilize when dual-target supervision is sparse, while the latter may be sensitive to denoising-time target balancing and competing update directions. These limitations motivate a generator-preserving alternative that keeps the pretrained prior intact: can dual-target candidates instead be recovered from the input space of a frozen single-target diffusion model, without modifying its parameters or denoising dynamics? We formulate this task as a constrained multi-objective optimization problem and propose REUSE, a hierarchical evolutionary input-space search framework that combines pair-conditioned exploration with structured multi-stage selection to enforce dual-target affinity, chemical quality, and diversity. Experiments show that, compared with methods that modify the diffusion process, REUSE consistently improves dual-target affinity and balance, achieving a 20.9-percentage-point gain in Dual High Affinity over the strongest prior baseline while maintaining competitive molecular quality.

Design Conditions for Intra-Group Learning of Sequence-Level Rewards: Token Gradient Cancellation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Fei Ding · Yongkang Zhang · youwei wang · Zijian Zeng
26 May 2026 at 12:00
arXiv:2604.13088v2 Announce Type: replace-cross Abstract: Reinforcement learning for multi-step reasoning with large language models (LLMs) typically relies on sparse terminal rewards, which creates a poorly conditioned credit-assignment problem: the final feedback is propagated uniformly across all intermediate decisions. This leads to high gradient variance, unstable training, and many ineffective updates, ultimately limiting sustained model improvement. We propose a counterfactual-comparison framework for credit assignment. For each input, the framework samples multiple reasoning trajectories and treats their differences as implicit approximations to alternative decisions. This yields an implicit process-level advantage estimator that converts sparse terminal rewards into step-sensitive learning signals. Building on this framework, we introduce Implicit Behavior Policy Optimization (IBPO), which substantially improves training stability and the performance ceiling on mathematical and code-reasoning benchmarks. Our results point to a promising direction for unlocking the reasoning potential of LLMs.

Rethinking the Comparison Unit in Sequence-Level Reinforcement Learning: An Equal-Length Paired Training Framework from Loss Correction to Sample Construction

✇cs.AI, q-bio.NC updates on arXiv.org
By: Fei Ding · Yongkang Zhang · Runhao Liu · Yuhao Liao · Zijian Zeng · Huiming Yang · Sibo wang · Linglin Liao
26 May 2026 at 12:00
arXiv:2604.17328v2 Announce Type: replace-cross Abstract: This paper investigates the length problem in sequence-level relative reinforcement learning. We observe that, although existing methods partially alleviate length-related phenomena, a more fundamental issue remains insufficiently characterized: the comparison units used during training lack inherent comparability. Building on this observation, we propose a new perspective: the length problem should not be viewed merely as a loss-scaling or normalization bias, but rather as a \emph{comparison unit construction} problem. We further establish a sample-construction-based training framework that, instead of applying post-hoc corrections to unequal-length responses, proactively constructs equal-length, alignable, and comparable training segments during generation. Within this framework, we propose EqLen, a concrete method applicable to group-relative comparison algorithms such as GRPO, GSPO, and RLOO. Through dual-track synchronous generation, prefix inheritance, and segment masking, EqLen efficiently collects effective equal-length training segments and enables stable

Internalizing Outcome Supervision into Process Supervision: A New Paradigm for Reinforcement Learning for Reasoning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Fei Ding · Yongkang Zhang · Runhao Liu · Yuhao Liao · Zijian Zeng · Sibo wang · Huiming Yang
26 May 2026 at 12:00
arXiv:2605.05226v2 Announce Type: replace-cross Abstract: The central challenge of reinforcement learning for reasoning lies not only in the sparsity of outcome-level supervision, but more fundamentally in how to transform feedback provided only at the end of a sequence into fine-grained learning signals that can guide intermediate reasoning steps. Existing approaches either rely on outcome-level rewards for sequence-level optimization, which makes precise credit assignment difficult, or depend on externally constructed process supervision, which is costly and difficult to scale sustainably. To address this, we propose a new perspective: reinforcement learning for reasoning can be understood as the problem of internalizing outcome supervision into process supervision. From this perspective, we introduce a supervision-internalization method for reinforcement learning for reasoning, enabling the model to automatically extract process-level learning signals through identifying, correcting, and reusing failed reasoning trajectories, thereby achieving finer-grained policy optimization under outcome-only supervision. We further abstract this idea into a new training paradigm, in which the model continually generates and refines its own internal process supervision during reinforcement learning, opening a new path for fine-grained credit assignment in reinforcement learning for reasoning that differs from externally provided process supervision.

Reducing Credit Assignment Variance via Counterfactual Reasoning Paths

✇cs.AI, q-bio.NC updates on arXiv.org
By: Fei Ding · Yongkang Zhang · Youwei Wang · Zijian Zeng
26 May 2026 at 12:00
arXiv:2605.16302v2 Announce Type: replace-cross Abstract: Reinforcement learning for multi-step reasoning with large language models (LLMs) typically relies on sparse terminal rewards, which creates a poorly conditioned credit-assignment problem: the final feedback is propagated uniformly across all intermediate decisions. This leads to high gradient variance, unstable training, and many ineffective updates, ultimately limiting sustained model improvement. We propose a counterfactual-comparison framework for credit assignment. For each input, the framework samples multiple reasoning trajectories and treats their differences as implicit approximations to alternative decisions. This yields an implicit process-level advantage estimator that converts sparse terminal rewards into step-sensitive learning signals. Building on this framework, we introduce Implicit Behavior Policy Optimization (IBPO), which substantially improves training stability and the performance ceiling on mathematical and code-reasoning benchmarks. Our results point to a promising direction for unlocking the reasoning potential of LLMs.

GPNMB Drives Brain Metastasis by Sculpting a Pathological Endothelial-Immune Interactome

✇Omics In Lung
By: Xuefei Liu · Jun Tan · Chun Wu · Guanyin Huang · Yixin Cheng · Jianyang Hu · Binyu Zhang · Mao Zhao · Boxi Zhao · Jingru Lian · Shuqian Zheng · Lin Zeng · Meng Xu · Yang Xu · Shan Zeng · Hao Yu · Hui Yang · Zhixiang Zuo · Chuanyu Liu · Weineng Feng · Weinan Guo · Chunying Li · Sai-Lan Liu · Qing Liu · Feiqiu Wen · Xin Hong
13 April 2026 at 18:00

Cancer Discov. 2026 Apr 15. doi: 10.1158/2159-8290.CD-25-1663. Online ahead of print.

ABSTRACT

Brain metastases (BM) remain a devastating disease with dismal prognosis. How circulating tumor cells (CTCs) penetrate the blood brain barrier (BBB) and reprogram the brain microenvironment remain unclear. Using spatially resolved multi-omic profiling of CTCs and brain metastases, integrated with experimental and clinical analyses, we identified Glycoprotein Non-Metastatic Melanoma Protein B (GPNMB) as a CTC-secreted driver of vascular disruption and brain colonization. CBX3 upregulation induced GPNMB expression, which bound endothelial EGFR, triggering CBL-mediated ubiquitination and degradation. Attenuated EGFR signaling suppressed FTO and disrupted endothelial junctions via YTHDF2-dependent TJP1 m6A methylation. Remarkably, GPNMB-induced BBB remodeling promoted immune infiltration via CXCL12-CXCR4 axis, and induced time course-dependent T cell exhaustion within the brain microenvironment. Clinically, elevated CBX3⁺GPNMB⁺ CTCs and plasma CXCL12 were significantly associated with BM progression in lung cancer and melanoma. Therapeutically, dual blockade of GPNMB and PD1 enhanced anti-BM efficacy in mice, unveiling GPNMB as a promising target for precision immunotherapy.

PMID:41973996 | DOI:10.1158/2159-8290.CD-25-1663

Received — 26 March 2026 ⏭

OmniDiT: Extending Diffusion Transformer to Omni-VTON Framework

✇cs.AI, q-bio.NC updates on arXiv.org
By: Weixuan Zeng · Pengcheng Wei · Huaiqing Wang · Boheng Zhang · Jia Sun · Dewen Fan · Lin HE · Long Chen · Qianqian Gan · Fan Yang · Tingting Gao
25 March 2026 at 12:00
arXiv:2603.19643v2 Announce Type: replace-cross Abstract: Despite the rapid advancement of Virtual Try-On (VTON) and Try-Off (VTOFF) technologies, existing VTON methods face challenges with fine-grained detail preservation, generalization to complex scenes, complicated pipeline, and efficient inference. To tackle these problems, we propose OmniDiT, an omni Virtual Try-On framework based on the Diffusion Transformer, which combines try-on and try-off tasks into one unified model. Specifically, we first establish a self-evolving data curation pipeline to continuously produce data, and construct a large VTON dataset Omni-TryOn, which contains over 380k diverse and high-quality garment-model-tryon image pairs and detailed text prompts. Then, we employ the token concatenation and design an adaptive position encoding to effectively incorporate multiple reference conditions. To relieve the bottleneck of long sequence computation, we are the first to introduce Shifted Window Attention into the diffusion model, thus achieving a linear complexity. To remedy the performance degradation caused by local window attention, we utilize multiple timestep prediction and an alignment loss to improve generation fidelity. Experiments reveal that, under various complex scenes, our method achieves the best performance in both the model-free VTON and VTOFF tasks and a performance comparable to current SOTA methods in the model-based VTON task.
Received — 17 March 2026 ⏭

LightMoE: Reducing Mixture-of-Experts Redundancy through Expert Replacing

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jiawei Hao · Zhiwei Hao · Jianyuan Guo · Li Shen · Yong Luo · Han Hu · Dan Zeng
16 March 2026 at 12:00
arXiv:2603.12645v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) based Large Language Models (LLMs) have demonstrated impressive performance and computational efficiency. However, their deployment is often constrained by substantial memory demands, primarily due to the need to load numerous expert modules. While existing expert compression techniques like pruning or merging attempt to mitigate this, they often suffer from irreversible knowledge loss or high training overhead. In this paper, we propose a novel expert compression paradigm termed expert replacing, which replaces redundant experts with parameter-efficient modules and recovers their capabilities with low training costs. We find that even a straightforward baseline of this paradigm yields promising performance. Building on this foundation, we introduce LightMoE, a framework that enhances the paradigm by introducing adaptive expert selection, hierarchical expert construction, and an annealed recovery strategy. Experimental results show that LightMoE matches the performance of LoRA fine-tuning at a 30% compression ratio. Even under a more aggressive 50% compression rate, it outperforms existing methods and achieves average performance improvements of 5.6% across five diverse tasks. These findings demonstrate that LightMoE strikes a superior balance among memory efficiency, training efficiency, and model performance.
Received — 14 March 2026 ⏭

From Black Box to Biological Insight: AttentioFuse Unlocks Multi-Omics Dynamics in Lung Cancer

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Yuhang Huang · Yungang He · Liyan Zeng · Lei Liu · Fan Zhong
14 March 2026 at 18:00

Cancers (Basel). 2026 Mar 9;18(5):878. doi: 10.3390/cancers18050878.

ABSTRACT

BACKGROUND: Lung adenocarcinoma (LUAD) and squamous cell carcinoma (LUSC), the major subtypes of non-small cell lung cancer (NSCLC), exhibit distinct molecular landscapes that demand precision in prognosis and therapy. While deep learning models can achieve high predictive accuracy, their black-box nature limits clinical translation.

METHODS: We introduce AttentioFuse, an interpretable deep learning framework employing a Reactome-guided mid-fusion strategy for multi-omics integration. AttentioFuse builds on three pillars: (i) dual-phase learning with omics-specific encoders to preserve modality-unique patterns, (ii) hierarchical attention mechanisms (cross-omics, feature-level, and fusion-layer) to quantify layer contributions dynamically, and (iii) integrated explainability combining DeepSHAP and global attention weights for gene-to-pathway interpretation. Two depth variants are instantiated under identical priors: a three-layer configuration (3F) for main discrimination and a five-layer configuration (AttentioFuse-5X) for deeper hierarchical interpretation; the 5X variant is trained end-to-end and yields comparable accuracy while enhancing pathway-level resolution.

RESULTS: Evaluated on The Cancer Genome Atlas (TCGA) LUAD/LUSC cohorts, AttentioFuse matches state-of-the-art performance in TNM staging while uncovering actionable biological insights, including pan-NSCLC AKT/mTOR metabolic control, histology-divergent Notch signaling roles, and additional pathways related to developmental reactivation, microbiota-associated metastasis, and extracellular matrix remodeling.

CONCLUSIONS: By design, AttentioFuse-5X bridges predictive performance with hierarchical, pathway-resolved explanations, advancing oncology by transforming black-box predictions into biologically grounded decision support.

PMID:41827812 | PMC:PMC12985206 | DOI:10.3390/cancers18050878

From Black Box to Biological Insight: AttentioFuse Unlocks Multi-Omics Dynamics in Lung Cancer

✇Omics In Lung
By: Yuhang Huang · Yungang He · Liyan Zeng · Lei Liu · Fan Zhong
14 March 2026 at 18:00

Cancers (Basel). 2026 Mar 9;18(5):878. doi: 10.3390/cancers18050878.

ABSTRACT

BACKGROUND: Lung adenocarcinoma (LUAD) and squamous cell carcinoma (LUSC), the major subtypes of non-small cell lung cancer (NSCLC), exhibit distinct molecular landscapes that demand precision in prognosis and therapy. While deep learning models can achieve high predictive accuracy, their black-box nature limits clinical translation.

METHODS: We introduce AttentioFuse, an interpretable deep learning framework employing a Reactome-guided mid-fusion strategy for multi-omics integration. AttentioFuse builds on three pillars: (i) dual-phase learning with omics-specific encoders to preserve modality-unique patterns, (ii) hierarchical attention mechanisms (cross-omics, feature-level, and fusion-layer) to quantify layer contributions dynamically, and (iii) integrated explainability combining DeepSHAP and global attention weights for gene-to-pathway interpretation. Two depth variants are instantiated under identical priors: a three-layer configuration (3F) for main discrimination and a five-layer configuration (AttentioFuse-5X) for deeper hierarchical interpretation; the 5X variant is trained end-to-end and yields comparable accuracy while enhancing pathway-level resolution.

RESULTS: Evaluated on The Cancer Genome Atlas (TCGA) LUAD/LUSC cohorts, AttentioFuse matches state-of-the-art performance in TNM staging while uncovering actionable biological insights, including pan-NSCLC AKT/mTOR metabolic control, histology-divergent Notch signaling roles, and additional pathways related to developmental reactivation, microbiota-associated metastasis, and extracellular matrix remodeling.

CONCLUSIONS: By design, AttentioFuse-5X bridges predictive performance with hierarchical, pathway-resolved explanations, advancing oncology by transforming black-box predictions into biologically grounded decision support.

PMID:41827812 | PMC:PMC12985206 | DOI:10.3390/cancers18050878

Received — 11 March 2026 ⏭

Learning Unbiased Cluster Descriptors for Interpretable Imbalanced Concept Drift Detection

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yiqun Zhang · Zhanpei Huang · Mingjie Zhao · Chuyao Zhang · Yang Lu · Yuzhu Ji · Fangqing Gu · An Zeng
10 March 2026 at 12:00
arXiv:2603.06757v1 Announce Type: cross Abstract: Unlabeled streaming data are usually collected to describe dynamic systems, where concept drift detection is a vital prerequisite to understanding the evolution of systems. However, the drifting concepts are usually imbalanced in most real cases, which brings great challenges to drift detection. That is, the dominant statistics of large clusters can easily mask the drifting of small cluster distributions (also called small concepts), which is known as the `masking effect'. Considering that most existing approaches only detect the overall existence of drift under the assumption of balanced concepts, two critical problems arise: 1) where the small concept is, and 2) how to detect its drift. To address the challenging concept drift detection for imbalanced data, we propose Imbalanced Cluster Descriptor-based Drift Detection (ICD3) approach that is unbiased to the imbalanced concepts. This approach first detects imbalanced concepts by employing a newly designed multi-distribution-granular search, which ensures that the distribution of both small and large concepts is effectively captured. Subsequently, it trains a One-Cluster Classifier (OCC) for each identified concept to carefully monitor their potential drifts in the upcoming data chunks. Since the detection is independently performed for each concept, the dominance of large clusters is thus circumvented. ICD3 demonstrates highly interpretability by specifically locating the drifted concepts, and is robust to the changing of the imbalance ratio of concepts. Comprehensive experiments with multi-aspect ablation studies conducted on various benchmark datasets demonstrate the superiority of ICD3 against the state-of-the-art counterparts.

Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks

✇cs.AI, q-bio.NC updates on arXiv.org
By: Kai Zeng · Zhanqian Wu · Kaixin Xiong · Xiaobao Wei · Xiangyu Guo · Zhenxin Zhu · Kalok Ho · Lijun Zhou · Bohan Zeng · Ming Lu · Haiyang Sun · Bing Wang · Guang Chen · Hangjun Ye · Wentao Zhang
10 March 2026 at 12:00
arXiv:2510.19195v4 Announce Type: replace-cross Abstract: Recent advancements in driving world models enable controllable generation of high-quality RGB videos or multimodal videos. Existing methods primarily focus on metrics related to generation quality and controllability. However, they often overlook the evaluation of downstream perception tasks, which are $\mathbf{really\ crucial}$ for the performance of autonomous driving. Existing methods usually leverage a training strategy that first pretrains on synthetic data and finetunes on real data, resulting in twice the epochs compared to the baseline (real data only). When we double the epochs in the baseline, the benefit of synthetic data becomes negligible. To thoroughly demonstrate the benefit of synthetic data, we introduce Dream4Drive, a novel synthetic data generation framework designed for enhancing the downstream perception tasks. Dream4Drive first decomposes the input video into several 3D-aware guidance maps and subsequently renders the 3D assets onto these guidance maps. Finally, the driving world model is fine-tuned to produce the edited, multi-view photorealistic videos, which can be used to train the downstream perception models. Dream4Drive enables unprecedented flexibility in generating multi-view corner cases at scale, significantly boosting corner case perception in autonomous driving. To facilitate future research, we also contribute a large-scale 3D asset dataset named DriveObj3D, covering the typical categories in driving scenarios and enabling diverse 3D-aware video editing. We conduct comprehensive experiments to show that Dream4Drive can effectively boost the performance of downstream perception models under various training epochs. Page: https://wm-research.github.io/Dream4Drive/ GitHub Link: https://github.com/wm-research/Dream4Drive
Received — 25 February 2026 ⏭

Synthesizing Multimodal Geometry Datasets from Scratch and Enabling Visual Alignment via Plotting Code

✇cs.AI, q-bio.NC updates on arXiv.org
By: Haobo Lin · Tianyi Bai · Chen Chen · Jiajun Zhang · Bohan Zeng · Wentao Zhang · Binhang Yuan
24 February 2026 at 13:00
arXiv:2602.18745v1 Announce Type: cross Abstract: Multimodal geometry reasoning requires models to jointly understand visual diagrams and perform structured symbolic inference, yet current vision--language models struggle with complex geometric constructions due to limited training data and weak visual--symbolic alignment. We propose a pipeline for synthesizing complex multimodal geometry problems from scratch and construct a dataset named \textbf{GeoCode}, which decouples problem generation into symbolic seed construction, grounded instantiation with verification, and code-based diagram rendering, ensuring consistency across structure, text, reasoning, and images. Leveraging the plotting code provided in GeoCode, we further introduce code prediction as an explicit alignment objective, transforming visual understanding into a supervised structured prediction task. GeoCode exhibits substantially higher structural complexity and reasoning difficulty than existing benchmarks, while maintaining mathematical correctness through multi-stage validation. Extensive experiments show that models trained on GeoCode achieve consistent improvements on multiple geometry benchmarks, demonstrating both the effectiveness of the dataset and the proposed alignment strategy. The code will be available at https://github.com/would1920/GeoCode.

UFO: Unlocking Ultra-Efficient Quantized Private Inference with Protocol and Algorithm Co-Optimization

✇cs.AI, q-bio.NC updates on arXiv.org
By: Wenxuan Zeng · Chao Yang · Tianshi Xu · Bo Zhang · Changrui Ren · Jin Dong · Meng Li
24 February 2026 at 13:00
arXiv:2602.18758v1 Announce Type: cross Abstract: Private convolutional neural network (CNN) inference based on secure two-party computation (2PC) suffers from high communication and latency overhead, especially from convolution layers. In this paper, we propose UFO, a quantized 2PC inference framework that jointly optimizes the 2PC protocols and quantization algorithm. UFO features a novel 2PC protocol that systematically combines the efficient Winograd convolution algorithm with quantization to improve inference efficiency. However, we observe that naively combining quantization and Winograd convolution faces the following challenges: 1) From the inference perspective, Winograd transformations introduce extensive additions and require frequent bit width conversions to avoid inference overflow, leading to non-negligible communication overhead; 2) From the training perspective, Winograd transformations introduce weight outliers that make quantization-aware training (QAT) difficult, resulting in inferior model accuracy. To address these challenges, we co-optimize both protocol and algorithm. 1) At the protocol level, we propose a series of graph-level optimizations for 2PC inference to minimize the communication. 2) At the algorithm level, we develop a mixed-precision QAT algorithm based on layer sensitivity to optimize model accuracy given communication constraints. To accommodate the outliers, we further introduce a 2PC-friendly bit re-weighting algorithm to increase the representation range without explicitly increasing bit widths. With extensive experiments, UFO demonstrates 11.7x, 3.6x, and 6.3x communication reduction with 1.29%, 1.16%, and 1.29% higher accuracy compared to state-of-the-art frameworks SiRNN, COINN, and CoPriv, respectively.

Decoding Tourist Perception in Historic Urban Quarters with Multimodal Social Media Data: An AI-Based Framework and Evidence from Shanghai

✇cs.AI, q-bio.NC updates on arXiv.org
By: Kaizhen Tan · Yufan Wu · Yuxuan Liu · Haoran Zeng
24 February 2026 at 13:00
arXiv:2509.03830v3 Announce Type: replace Abstract: Historic urban quarters are increasingly shaped by tourism and lifestyle consumption, yet planners often lack scalable evidence on what visitors notice, prefer, and criticize in these environments. This study proposes an AI-based, multimodal framework to decode tourist perception by combining visual attention, color-based aesthetic representation, and multidimensional satisfaction. We collect geotagged photos and review texts from a major Chinese platform and assemble a street view image set as a baseline for comparison across 12 historic urban quarters in Shanghai. We train a semantic segmentation model to quantify foregrounded visual elements in tourist-shared imagery, extract and compare color palettes between social media photos and street views, and apply a multi-task sentiment classifier to assess satisfaction across four experience dimensions that correspond to activity, physical setting, supporting services, and commercial offerings. Results show that tourist photos systematically foreground key streetscape elements and that the color composition represented on social media can differ from on-site street views, indicating a perception-reality gap that varies by quarter. The framework offers an interpretable and transferable approach to diagnose such gaps and to inform heritage management and visitor-oriented urban design.
Received — 17 February 2026 ⏭

FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Huajian Zeng · Lingyun Chen · Jiaqi Yang · Yuantai Zhang · Fan Shi · Peidong Liu · Xingxing Zuo
17 February 2026 at 13:00
arXiv:2602.13444v1 Announce Type: cross Abstract: Recent vision-language-action (VLA) models can generate plausible end-effector motions, yet they often fail in long-horizon, contact-rich tasks because the underlying hand-object interaction (HOI) structure is not explicitly represented. An embodiment-agnostic interaction representation that captures this structure would make manipulation behaviors easier to validate and transfer across robots. We propose FlowHOI, a two-stage flow-matching framework that generates semantically grounded, temporally coherent HOI sequences, comprising hand poses, object poses, and hand-object contact states, conditioned on an egocentric observation, a language instruction, and a 3D Gaussian splatting (3DGS) scene reconstruction. We decouple geometry-centric grasping from semantics-centric manipulation, conditioning the latter on compact 3D scene tokens and employing a motion-text alignment loss to semantically ground the generated interactions in both the physical scene layout and the language instruction. To address the scarcity of high-fidelity HOI supervision, we introduce a reconstruction pipeline that recovers aligned hand-object trajectories and meshes from large-scale egocentric videos, yielding an HOI prior for robust generation. Across the GRAB and HOT3D benchmarks, FlowHOI achieves the highest action recognition accuracy and a 1.7$\times$ higher physics simulation success rate than the strongest diffusion-based baseline, while delivering a 40$\times$ inference speedup. We further demonstrate real-robot execution on four dexterous manipulation tasks, illustrating the feasibility of retargeting generated HOI representations to real-robot execution pipelines.

MAS-on-the-Fly: Dynamic Adaptation of LLM-based Multi-Agent Systems at Test Time

✇cs.AI, q-bio.NC updates on arXiv.org
By: Guangyi Liu · Haojun Lin · Huan Zeng · Heng Wang · Quanming Yao
17 February 2026 at 13:00
arXiv:2602.13671v1 Announce Type: cross Abstract: Large Language Model (LLM)-based multi-agent systems (MAS) have emerged as a promising paradigm for solving complex tasks. However, existing works often rely on manual designs or "one-size-fits-all" automation, lacking dynamic adaptability after deployment. Inspired by how biological systems adapt, we introduce MASFly, a novel multi-agent framework enabling dynamic adaptation at test time. To adapt system generation, MASFly employs a retrieval-augmented SOP instantiation mechanism that leverages a self-constructed repository of successful collaboration patterns, enabling the LLM to assemble customized MASs for new queries. For adaptive execution, MASFly incorporates an experience-guided supervision mechanism, where a dedicated Watcher agent monitors system behaviors with reference to a personalized experience pool and provides real-time interventions. Extensive experiments demonstrate that MASFly achieves state-of-the-art performance, most notably a 61.7% success rate on the TravelPlanner benchmark, while exhibiting strong task adaptability and robustness.
There are no more articles
❌