❌

Normal view

Received — 8 April 2026 ⏭

Cardinality Estimation for High Dimensional Similarity Queries with Adaptive Bucket Probing

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhonghan Chen · Qintian Guo · Ruiyuan Zhang · Xiaofang Zhou
7 April 2026 at 12:00
arXiv:2604.04603v1 Announce Type: cross Abstract: In this work, we address the problem of cardinality estimation for similarity search in high-dimensional spaces. Our goal is to design a framework that is lightweight, easy to construct, and capable of providing accurate estimates with satisfying online efficiency. We leverage locality-sensitive hashing (LSH) to partition the vector space while preserving distance proximity. Building on this, we adopt the principles of classical multi-probe LSH to adaptively explore neighboring buckets, accounting for distance thresholds of varying magnitudes. To improve online efficiency, we employ progressive sampling to reduce the number of distance computations and utilize asymmetric distance computation in product quantization to accelerate distance calculations in high-dimensional spaces. In addition to handling static datasets, our framework includes updating algorithm designed to efficiently support large-scale dynamic scenarios of data updates.Experiments demonstrate that our methods can accurately estimate the cardinality of similarity queries, yielding satisfying efficiency.

Xpertbench: Expert Level Tasks with Rubrics-Based Evaluation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xue Liu · Xin Ma · Yuxin Ma · Yongchang Peng · Duo Wang · Zhoufutu Wen · Ge Zhang · Kaiyuan Zhang · Xinyu Chen · Tianci He · Jiani Hou · Liang Hu · Ziyun Huang · Yongzhe Hui · Jianpeng Jiao · Chennan Ju · Yingru Kong · Yiran Li · Mengyun Liu · Luyao Ma · Fei Ni · Yiqing Ni · Yueyan Qiu · Yanle Ren · Zilin Shi · Zaiyuan Wang · Wenjie Yue · Shiyu Zhang · Xinyi Zhang · Kaiwen Zhao · Zhenwei Zhu · Shanshan Wu · Qi Zhao · Wenhao Huang
7 April 2026 at 12:00
arXiv:2604.02368v3 Announce Type: replace Abstract: As Large Language Models (LLMs) exhibit plateauing performance on conventional benchmarks, a pivotal challenge persists: evaluating their proficiency in complex, open-ended tasks characterizing genuine expert-level cognition. Existing frameworks suffer from narrow domain coverage, reliance on generalist tasks, or self-evaluation biases. To bridge this gap, we present XpertBench, a high-fidelity benchmark engineered to assess LLMs across authentic professional domains. XpertBench consists of 1,346 meticulously curated tasks across 80 categories, spanning finance, healthcare, legal services, education, and dual-track research (STEM and Humanities). These tasks are derived from over 1,000 submissions by domain experts--including researchers from elite institutions and practitioners with extensive clinical or industrial experience--ensuring superior ecological validity. Each task uses detailed rubrics with mostly 15-40 weighted checkpoints to assess professional rigor. To facilitate scalable yet human-aligned assessment, we introduce ShotJudge, a novel evaluation paradigm that employs LLM judges calibrated with expert few-shot exemplars to mitigate self-rewarding biases. Our empirical evaluation of state-of-the-art LLMs reveals a pronounced performance ceiling: even leading models achieve a peak success rate of only ~66%, with a mean score around 55%. Models also exhibit domain-specific divergence, showing non-overlapping strengths in quantitative reasoning versus linguistic synthesis.. These findings underscore a significant "expert-gap" in current AI systems and establish XpertBench as a critical instrument for navigating the transition from general-purpose assistants to specialized professional collaborators.

Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction

✇cs.AI, q-bio.NC updates on arXiv.org
By: Qintong Zhang · Bin Wang · Victor Shea-Jay Huang · Junyuan Zhang · Zhengren Wang · Hao Liang · Conghui He · Wentao Zhang
7 April 2026 at 12:00
arXiv:2410.21169v5 Announce Type: replace-cross Abstract: Document parsing (DP) transforms unstructured or semi-structured documents into structured, machine-readable representations, enabling downstream applications such as knowledge base construction and retrieval-augmented generation (RAG). This survey provides a comprehensive and timely review of document parsing research. We propose a systematic taxonomy that organizes existing approaches into modular pipeline-based systems and unified models driven by Vision-Language Models (VLMs). We provide a detailed review of key components in pipeline systems, including layout analysis and the recognition of heterogeneous content such as text, tables, mathematical expressions, and visual elements, and then systematically track the evolution of specialized VLMs for document parsing. Additionally, we summarize widely adopted evaluation metrics and high-quality benchmarks that establish current standards for parsing quality. Finally, we discuss key open challenges, including robustness to complex layouts, reliability of VLM-based parsing, and inference efficiency, and outline directions for building more accurate and scalable document intelligence systems.

Security Considerations for Artificial Intelligence Agents

✇cs.AI, q-bio.NC updates on arXiv.org
By: Ninghui Li · Kaiyuan Zhang · Kyle Polley · Jerry Ma
7 April 2026 at 12:00
arXiv:2603.12230v2 Announce Type: replace-cross Abstract: This article, a lightly adapted version of Perplexity's response to NIST/CAISI Request for Information 2025-0035, details our observations and recommendations concerning the security of frontier AI agents. These insights are informed by Perplexity's experience operating general-purpose agentic systems used by millions of users and thousands of enterprises in both controlled and open-world environments. Agent architectures change core assumptions around code-data separation, authority boundaries, and execution predictability, creating new confidentiality, integrity, and availability failure modes. We map principal attack surfaces across tools, connectors, hosting boundaries, and multi-agent coordination, with particular emphasis on indirect prompt injection, confused-deputy behavior, and cascading failures in long-running workflows. We then assess current defenses as a layered stack: input-level and model-level mitigations, sandboxed execution, and deterministic policy enforcement for high-consequence actions. Finally, we identify standards and research gaps, including adaptive security benchmarks, policy models for delegation and privilege control, and guidance for secure multi-agent system design aligned with NIST risk management principles.

Decoding macrophage heterogeneity in the pulmonary fibrosis lung cancer transition

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Hanming Yu · Mengmeng Zhao · Qiuhong Li · Yuan Zhang
6 April 2026 at 18:00

Front Immunol. 2026 Mar 20;17:1787094. doi: 10.3389/fimmu.2026.1787094. eCollection 2026.

ABSTRACT

Pulmonary fibrosis (PF) significantly increases the risk of lung cancer (LC), but the mechanisms underlying this transition remain unclear. This overview positions macrophage heterogeneity as a central node within the PF-LC continuum. First, we describe important subpopulations of profibrotic and pro-tumor macrophages, including SPP1+, MERTK+, TREM2+, and MARCO+ cells, using high-resolution spatial and single-cell omics technologies. Next, we analyze the fundamental mechanisms that determine their function: the fibrotic microenvironment (e.g., extracellular matrix stiffness, hypoxia) induces profound metabolic reprogramming (e.g., Warburg effect, lipid peroxidation) and stabilizes epigenetic memory (e.g., DNA methylation, histone modifications), locking them into a pathogenic state. This reprogramming occurs through two main pathways: (1) metabolic reprogramming, characterized by aerobic glycolytic conversion and dysregulated lipid metabolism, which stimulates both pathogenic functions and suppression of T cell activity; (2) Epigenetic modifications, including stabilized alterations in DNA methylation, histone modifications, and superactivator patterns, which maintain cells in a tumor-promoting phenotype. As central nodes of communication, these macrophages interact pathologically with fibroblasts and epithelial cells through secreted factors and extracellular vesicles, forming self-reinforcing feedback loops that promote disease progression. We are studying the crucial role of new technologies, particularly multi-omic spatial models and high-precision organoids, in fostering mechanistic discoveries. These discoveries pave the way for new macrophage-focused therapeutic strategies, including the precise stratification of patients using biomarkers from liquid biopsies (such as soluble SPP1 and MARCO) and the development of targeted drug delivery systems for the selective modulation of macrophage function, thus establishing a new paradigm for therapeutic interventions in pulmonary fibrosis with concomitant lung cancer.

PMID:41939908 | PMC:PMC13046558 | DOI:10.3389/fimmu.2026.1787094

Decoding macrophage heterogeneity in the pulmonary fibrosis lung cancer transition

✇Omics In Lung
By: Hanming Yu · Mengmeng Zhao · Qiuhong Li · Yuan Zhang
6 April 2026 at 18:00

Front Immunol. 2026 Mar 20;17:1787094. doi: 10.3389/fimmu.2026.1787094. eCollection 2026.

ABSTRACT

Pulmonary fibrosis (PF) significantly increases the risk of lung cancer (LC), but the mechanisms underlying this transition remain unclear. This overview positions macrophage heterogeneity as a central node within the PF-LC continuum. First, we describe important subpopulations of profibrotic and pro-tumor macrophages, including SPP1+, MERTK+, TREM2+, and MARCO+ cells, using high-resolution spatial and single-cell omics technologies. Next, we analyze the fundamental mechanisms that determine their function: the fibrotic microenvironment (e.g., extracellular matrix stiffness, hypoxia) induces profound metabolic reprogramming (e.g., Warburg effect, lipid peroxidation) and stabilizes epigenetic memory (e.g., DNA methylation, histone modifications), locking them into a pathogenic state. This reprogramming occurs through two main pathways: (1) metabolic reprogramming, characterized by aerobic glycolytic conversion and dysregulated lipid metabolism, which stimulates both pathogenic functions and suppression of T cell activity; (2) Epigenetic modifications, including stabilized alterations in DNA methylation, histone modifications, and superactivator patterns, which maintain cells in a tumor-promoting phenotype. As central nodes of communication, these macrophages interact pathologically with fibroblasts and epithelial cells through secreted factors and extracellular vesicles, forming self-reinforcing feedback loops that promote disease progression. We are studying the crucial role of new technologies, particularly multi-omic spatial models and high-precision organoids, in fostering mechanistic discoveries. These discoveries pave the way for new macrophage-focused therapeutic strategies, including the precise stratification of patients using biomarkers from liquid biopsies (such as soluble SPP1 and MARCO) and the development of targeted drug delivery systems for the selective modulation of macrophage function, thus establishing a new paradigm for therapeutic interventions in pulmonary fibrosis with concomitant lung cancer.

PMID:41939908 | PMC:PMC13046558 | DOI:10.3389/fimmu.2026.1787094

Received — 4 April 2026 ⏭

Countering Catastrophic Forgetting of Large Language Models for Better Instruction Following via Weight-Space Model Merging

✇cs.AI, q-bio.NC updates on arXiv.org
By: Mengxian Lyu · Cheng Peng · Ziyi Chen · Mengyuan Zhang · Jieting Li Lu · Yonghui Wu
3 April 2026 at 12:00
arXiv:2604.01538v1 Announce Type: cross Abstract: Large language models have been adopted in the medical domain for clinical documentation to reduce clinician burden. However, studies have reported that LLMs often "forget" a significant amount of instruction-following ability when fine-tuned using a task-specific medical dataset, a critical challenge in adopting general-purpose LLMs for clinical applications. This study presents a model merging framework to efficiently adapt general-purpose LLMs to the medical domain by countering this forgetting issue. By merging a clinical foundation model (GatorTronLlama) with a general instruct model (Llama-3.1-8B-Instruct) via interpolation-based merge methods, we seek to derive a domain-adapted model with strong performance on clinical tasks while retaining instruction-following ability. Comprehensive evaluation across medical benchmarks and five clinical generation tasks (e.g., radiology and discharge summarization) shows that merged models can effectively mitigate catastrophic forgetting, preserve clinical domain expertise, and retain instruction-following ability. In addition, our model merging strategies demonstrate training efficiency, achieving performance on par with fully fine-tuned baselines under severely constrained supervision (e.g., 64-shot vs. 256-shot). Consequently, weight-space merging constitutes a highly scalable solution for adapting open-source LLMs to clinical applications, facilitating broader deployment in resource-constrained healthcare environments.
Received — 2 April 2026 ⏭

Catgut implantation at acupoints improves anti-PD-1 inhibitor efficacy in lung cancer by inducing immune responses and remodeling the tumor microenvironment

✇Omics In Lung
By: Qian Wu · Ting Su · Yuanyuan Zhang · Yuerong Xiong · Xiaoyan Hu · Lijuan Shao · Size Chen
31 March 2026 at 18:00

Cancer Immunol Immunother. 2026 Mar 31;75(4):126. doi: 10.1007/s00262-026-04368-1.

ABSTRACT

While anti-programmed death-1 (anti-PD-1) therapy has revolutionized lung cancer treatment, its efficacy remains limited by an immunosuppressive tumor microenvironment (TME). We therefore investigated whether combining anti-PD-1 inhibitor with catgut embedding at the Zusanli acupoint (CIAA) could enhance anti-tumor immunity by reprogramming the TME in a lung cancer mouse model. Combining in vivo tumor monitoring, multi-parametric immune profiling (flow cytometry, IHC, ELISA), and multi-omics analyses (transcriptomics and metabolomics), we found that the combination therapy was associated with enhanced tumor growth inhibition. This effect correlated with a comprehensive TME transformation: conversion to an immunologically active state with increased effector immune cell infiltration (CD8⁺ T, CD4⁺ T, B cells, macrophages) and decreased regulatory T cells, coupled with suppression of pro-tumorigenic factors (VEGF, IL-6). Integrated omics analysis suggests that the combined treatment may modulate tumor-stroma interaction pathways (e.g., PI3K-Akt, focal adhesion) and rewire immunometabolic networks (e.g., tryptophan metabolism). Our study provides hypothesis-generating correlative data positioning CIAA as a potential adjunct capable of remodeling the TME to potentiate anti-PD-1 therapy in lung cancer.

PMID:41915222 | PMC:PMC13038699 | DOI:10.1007/s00262-026-04368-1

Catgut implantation at acupoints improves anti-PD-1 inhibitor efficacy in lung cancer by inducing immune responses and remodeling the tumor microenvironment

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Qian Wu · Ting Su · Yuanyuan Zhang · Yuerong Xiong · Xiaoyan Hu · Lijuan Shao · Size Chen
31 March 2026 at 18:00

Cancer Immunol Immunother. 2026 Mar 31;75(4):126. doi: 10.1007/s00262-026-04368-1.

ABSTRACT

While anti-programmed death-1 (anti-PD-1) therapy has revolutionized lung cancer treatment, its efficacy remains limited by an immunosuppressive tumor microenvironment (TME). We therefore investigated whether combining anti-PD-1 inhibitor with catgut embedding at the Zusanli acupoint (CIAA) could enhance anti-tumor immunity by reprogramming the TME in a lung cancer mouse model. Combining in vivo tumor monitoring, multi-parametric immune profiling (flow cytometry, IHC, ELISA), and multi-omics analyses (transcriptomics and metabolomics), we found that the combination therapy was associated with enhanced tumor growth inhibition. This effect correlated with a comprehensive TME transformation: conversion to an immunologically active state with increased effector immune cell infiltration (CD8⁺ T, CD4⁺ T, B cells, macrophages) and decreased regulatory T cells, coupled with suppression of pro-tumorigenic factors (VEGF, IL-6). Integrated omics analysis suggests that the combined treatment may modulate tumor-stroma interaction pathways (e.g., PI3K-Akt, focal adhesion) and rewire immunometabolic networks (e.g., tryptophan metabolism). Our study provides hypothesis-generating correlative data positioning CIAA as a potential adjunct capable of remodeling the TME to potentiate anti-PD-1 therapy in lung cancer.

PMID:41915222 | DOI:10.1007/s00262-026-04368-1

A monocyte-centered framework for predicting immunochemotherapy efficacy in lung squamous cell carcinoma patients

✇Omics In Lung
By: Jiangnan Zhao · Zijin Wang · Manyu Xiao · Yeyuan Zhang · Boxin Liu · Silin Chen · Yiping Tian · Dongqing Lv · Pingli Wang · Hai Song · Yuefeng Wu · Jian Liu · Kai Wang
30 March 2026 at 18:00

EMBO Mol Med. 2026 Mar 30. doi: 10.1038/s44321-026-00410-y. Online ahead of print.

ABSTRACT

Lung cancer is the leading cause of cancer-related mortality worldwide, with lung squamous cell carcinoma (LUSC) comprising 20-30% of cases. Immunochemotherapy (IC) is the standard first-line treatment for advanced LUSC, yet reliable predictors of therapeutic response remain unavailable. Using single-cell multi-omics profiling of paired pre- and post-treatment tumor and blood samples, we observed that patients responding to IC exhibited significantly higher baseline levels of peripheral blood monocytes, tumor-infiltrating classical monocytes, and APOBEC3A+ monocytes across both compartments compared with non-responders. These associations were independently validated in additional cohorts using routine complete blood count testing and multiplex immunofluorescence analysis of native tumor tissues. Our findings reveal monocyte-related parameters as clinically accessible indicators that link systemic immunity with the tumor microenvironment and hold promise for predicting IC responsiveness in patients with LUSC.

PMID:41912871 | DOI:10.1038/s44321-026-00410-y

A monocyte-centered framework for predicting immunochemotherapy efficacy in lung squamous cell carcinoma patients

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Jiangnan Zhao · Zijin Wang · Manyu Xiao · Yeyuan Zhang · Boxin Liu · Silin Chen · Yiping Tian · Dongqing Lv · Pingli Wang · Hai Song · Yuefeng Wu · Jian Liu · Kai Wang
30 March 2026 at 18:00

EMBO Mol Med. 2026 Mar 30. doi: 10.1038/s44321-026-00410-y. Online ahead of print.

ABSTRACT

Lung cancer is the leading cause of cancer-related mortality worldwide, with lung squamous cell carcinoma (LUSC) comprising 20-30% of cases. Immunochemotherapy (IC) is the standard first-line treatment for advanced LUSC, yet reliable predictors of therapeutic response remain unavailable. Using single-cell multi-omics profiling of paired pre- and post-treatment tumor and blood samples, we observed that patients responding to IC exhibited significantly higher baseline levels of peripheral blood monocytes, tumor-infiltrating classical monocytes, and APOBEC3A+ monocytes across both compartments compared with non-responders. These associations were independently validated in additional cohorts using routine complete blood count testing and multiplex immunofluorescence analysis of native tumor tissues. Our findings reveal monocyte-related parameters as clinically accessible indicators that link systemic immunity with the tumor microenvironment and hold promise for predicting IC responsiveness in patients with LUSC.

PMID:41912871 | DOI:10.1038/s44321-026-00410-y

Received — 26 March 2026 ⏭

Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidance

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xinrong Chen · Xu Chu · Yingmin Qiu · Hengyuan Zhang · Jing Xiong · Shiyu Tang · Shuai Liu · Shaokang Yang · Cheng Yang · Hayden Kwok-Hay So · Ngai Wong
25 March 2026 at 12:00
arXiv:2602.01047v3 Announce Type: replace-cross Abstract: Large Vision-Language Models (LVLMs) can reason from image-text inputs and perform well in various multimodal tasks. Despite this success, they are affected by language priors and often produce hallucinations. Hallucinations denote generated content that is grammatically and syntactically coherent, yet bears no match or direct relevance to visual input. To address this problem, we propose Residual Decoding (ResDec). It is a novel training-free method that uses historical information to aid decoding. The method relies on the internal implicit reasoning mechanism and token logits evolution mechanism of LVLMs to correct biases. Extensive experiments demonstrate that ResDec effectively suppresses hallucinations induced by language priors, significantly improves visual grounding, and reduces object hallucinations. In addition to mitigating hallucinations, ResDec also performs exceptionally well on comprehensive LVLM benchmarks, highlighting its broad applicability.

When Models Judge Themselves: Unsupervised Self-Evolution for Multimodal Reasoning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhengxian Wu · Kai Shi · Chuanrui Zhang · Zirui Liao · Jun Yang · Ni Yang · Qiuying Peng · Luyuan Zhang · Hangrui Xu · Tianhuang Su · Zhenyu Yang · Haonan Lu · Haoqian Wang
25 March 2026 at 12:00
arXiv:2603.21289v2 Announce Type: replace-cross Abstract: Recent progress in multimodal large language models has led to strong performance on reasoning tasks, but these improvements largely rely on high-quality annotated data or teacher-model distillation, both of which are costly and difficult to scale. To address this, we propose an unsupervised self-evolution training framework for multimodal reasoning that achieves stable performance improvements without using human-annotated answers or external reward models. For each input, we sample multiple reasoning trajectories and jointly model their within group structure. We use the Actor's self-consistency signal as a training prior, and introduce a bounded Judge based modulation to continuously reweight trajectories of different quality. We further model the modulated scores as a group level distribution and convert absolute scores into relative advantages within each group, enabling more robust policy updates. Trained with Group Relative Policy Optimization (GRPO) on unlabeled data, our method consistently improves reasoning performance and generalization on five mathematical reasoning benchmarks, offering a scalable path toward self-evolving multimodal models. The code are available at https://github.com/OPPO-Mente-Lab/LLM-Self-Judge.

Effects of multisensory stimulation based on immersive virtual reality in postoperative neuropsychiatric recovery after gynecological laparoscopy

✇npj Digital Medicine
By: Jiang Liu · Yuxiu Liu · Liuna Bi · Li Zhao · Fuchan Hu · Mengyao Huang · Jingyuan Zhang · Xun Zhou · Ting Wang · Shirong Fang · Fengxian Zhang · Yuanjian Song
24 March 2026 at 08:00

npj Digital Medicine, Published online: 24 March 2026; doi:10.1038/s41746-026-02515-7

Effects of multisensory stimulation based on immersive virtual reality in postoperative neuropsychiatric recovery after gynecological laparoscopy
Received — 17 March 2026 ⏭

Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhangquan Chen · Manyuan Zhang · Xinlei Yu · Xufang Luo · Mingze Sun · Zihao Pan · Xiang An · Yan Feng · Peng Pei · Xunliang Cai · Ruqi Huang
16 March 2026 at 12:00
arXiv:2510.18632v4 Announce Type: replace-cross Abstract: Though recent advances in vision-language models (VLMs) have achieved remarkable progress across a wide range of multimodal tasks, understanding 3D spatial relationships from limited views remains a significant challenge. Previous reasoning methods typically rely on pure text (e.g., topological cognitive maps) or on 2D visual cues. However, their limited representational capacity hinders performance in specific tasks that require 3D spatial imagination. To address this limitation, we propose 3DThinker, a framework that can effectively exploits the rich geometric information embedded within images while reasoning, like humans do. Our framework is the first to enable 3D mentaling during reasoning without any 3D prior input, and it does not rely on explicitly labeled 3D data for training. Specifically, our training consists of two stages. First, we perform supervised training to align the 3D latent generated by VLM while reasoning with that of a 3D foundation model (e.g., VGGT). Then, we optimize the entire reasoning trajectory solely based on outcome signals, thereby refining the underlying 3D mentaling. Extensive experiments across multiple benchmarks show that 3DThinker consistently outperforms strong baselines and offers a new perspective toward unifying 3D representations into multimodal reasoning. Our code is available at https://github.com/zhangquanchen/3DThinker.

Multimodal Continual Learning with MLLMs from Multi-scenario Perspectives

✇cs.AI, q-bio.NC updates on arXiv.org
By: Kai Jiang · Siqi Huang · Xiangyu Chen · Jiawei Shao · Hongyuan Zhang · Ping Luo · Xuelong Li
16 March 2026 at 12:00
arXiv:2511.18507v3 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) deployed on devices must adapt to continuously changing visual scenarios such as variations in background and perspective, to effectively perform complex visual tasks. To investigate catastrophic forgetting under real-world scenario shifts, we construct a multimodal visual understanding dataset (MSVQA), covering four distinct scenarios and perspectives: high-altitude, underwater, low-altitude, and indoor environments. Furthermore, we propose UNIFIER (mUltimodal coNtInual learning with MLLMs From multi-scenarIo pERspectives), a continual learning (CL) framework designed to address visual discrepancies while learning different scenarios. Compared to existing CL methods, UNIFIER enables knowledge accumulation within the same scenario and mutual enhancement across different scenarios via Vision Representation Expansion (VRE) and Vision Consistency Constraint (VCC). Experimental results show that UNIFIER improves the last-step VQA scores by 2.70%~10.62% and the last-step F1 scores by 3.40%~7.69% compared to the state-of-the-art method, QUAD, in 20-step cross-scenario continual learning tasks. MSVQA dataset is available at https://huggingface.co/datasets/Kaij00/MSVQA.
Received — 14 March 2026 ⏭

Risk-adaptive therapy guided by dynamic ctDNA in nasopharyngeal carcinoma

✇Nature - Issue - nature.com science feeds
By: Jiawei Lv · Dan-Xue Zheng · Jin-Hui Liang · Ning Zhang · Zu-Lu Ye · Xu-Dong Xu · Melvin. L. K. Chua · Lu-Lu Zhang · Zi-Ming Du · Zi-Chen Zhang · Wen-Fei Li · Ling-Long Tang · Lei Chen · Yan-Ping Mao · Rui Guo · Yu-Pei Chen · Li Lin · Yuan Zhang · Xu Liu · Cheng Xu · Zhi-Xuan Li · Ling-Xin Xu · Pan-Yang Yang · Kun Chen · Deng Bin · Tian-Sheng Gao · Jian-Ye Yan · Lu-Si Chen · Shao Hui Huang · Hong-Yun Zhao · Shu-Bin Hong · Yu-Sheng Jie · Hui-Ling Huang · Xu-Hua Tang · Jing-Ping Yun · Li-Zhi Liu · Li Tian · Hao-Jiang Li · Ji-Bin Li · Guan-Qun Zhou · Jun Ma · Ying Sun
11 March 2026 at 08:00

Nature, Published online: 11 March 2026; doi:10.1038/s41586-026-10244-w

A clinical trial testing whether monitoring ctDNA clearance during treatment for nasopharyngeal cancer could be used to inform decisions about an individual’s subsequent therapeutic programme shows promising results.
Received — 11 March 2026 ⏭

Attn-QAT: 4-Bit Attention With Quantization-Aware Training

✇cs.AI, q-bio.NC updates on arXiv.org
By: Peiyuan Zhang · Matthew Noto · Wenxuan Tan · Chengquan Jiang · Will Lin · Wei Zhou · Hao Zhang
10 March 2026 at 12:00
arXiv:2603.00040v2 Announce Type: replace-cross Abstract: Achieving reliable 4-bit attention is a prerequisite for end-to-end FP4 computation on emerging FP4-capable GPUs, yet attention remains the main obstacle due to FP4's tiny dynamic range and attention's heavy-tailed activations. This paper presents the first systematic study of 4-bit quantization-aware training (QAT) for attention. We find that "drop-in" QAT, which naively combines an FP4 forward pass with a high-precision Flash Attention (FA)-style backward pass, leads to training instability. We identify two key principles for stable FP4 attention: (1) matching low-precision recomputation of attention scores in the backward pass, and (2) resolving implicit precision assumptions in FA's gradient calculation. Based on these insights, we propose Attn-QAT and implement fused Triton kernels for training as well as FP4 inference kernels. Across diffusion and language models, Attn-QAT recovers the quality drop from FP4 attention without explicit outlier-mitigation heuristics used in prior FP4 attention, and delivers up to a 1.5x speedup on an RTX 5090. Video demos can be found at https://drive.google.com/drive/folders/190F6xbBDUF2kGQYIcXBt3ehSYij5jlim?usp=sharing.

ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training

✇cs.AI, q-bio.NC updates on arXiv.org
By: Haian Jin · Rundi Wu · Tianyuan Zhang · Ruiqi Gao · Jonathan T. Barron · Noah Snavely · Aleksander Holynski
10 March 2026 at 12:00
arXiv:2603.04385v2 Announce Type: replace-cross Abstract: Feed-forward transformer models have driven rapid progress in 3D vision, but state-of-the-art methods such as VGGT and $\pi^3$ have a computational cost that scales quadratically with the number of input images, making them inefficient when applied to large image collections. Sequential-reconstruction approaches reduce this cost but sacrifice reconstruction quality. We introduce ZipMap, a stateful feed-forward model that achieves linear-time, bidirectional 3D reconstruction while matching or surpassing the accuracy of quadratic-time methods. ZipMap employs test-time training layers to zip an entire image collection into a compact hidden scene state in a single forward pass, enabling reconstruction of over 700 frames in under 10 seconds on a single H100 GPU, more than $20\times$ faster than state-of-the-art methods such as VGGT. Moreover, we demonstrate the benefits of having a stateful representation in real-time scene-state querying and its extension to sequential streaming reconstruction.
❌