❌

Normal view

Received — 13 April 2026 ⏭

Superconductivity and electronic structures of nickelate thin film superstructures

✇Nature - Issue - nature.com science feeds
By: Zihao Nie · Yueying Li · Wei Lv · Lizhi Xu · Zhicheng Jiang · Peng Fu · Guangdi Zhou · Wenhua Song · Yaqi Chen · Heng Wang · Haoliang Huang · Junhao Lin · Jin-Feng Jia · Dawei Shen · Peng Li · Qi-Kun Xue · Zhuoyu Chen
8 April 2026 at 08:00

Nature, Published online: 08 April 2026; doi:10.1038/s41586-026-10352-7

Engineered Ruddlesden–Popper nickelate superstructures show that specific Fermi surface features enable ambient-pressure superconductivity, linking structural configuration, electronic structure and superconducting behaviour. .
Received — 4 April 2026 ⏭

Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jiaqi Liu · Zipeng Ling · Shi Qiu · Yanqing Liu · Siwei Han · Peng Xia · Haoqin Tu · Zeyu Zheng · Cihang Xie · Charles Fleming · Mingyu Ding · Huaxiu Yao
3 April 2026 at 12:00
arXiv:2604.01007v2 Announce Type: replace Abstract: AI agents increasingly operate over extended time horizons, yet their ability to retain, organize, and recall multimodal experiences remains a critical bottleneck. Building effective lifelong memory requires navigating a vast design space spanning architecture, retrieval strategies, prompt engineering, and data pipelines; this space is too large and interconnected for manual exploration or traditional AutoML to explore effectively. We deploy an autonomous research pipeline to discover Omni-SimpleMem, a unified multimodal memory framework for lifelong AI agents. Starting from a na\"ive baseline (F1=0.117 on LoCoMo), the pipeline autonomously executes ${\sim}50$ experiments across two benchmarks, diagnosing failure modes, proposing architectural modifications, and repairing data pipeline bugs, all without human intervention in the inner loop. The resulting system achieves state-of-the-art on both benchmarks, improving F1 by +411% on LoCoMo (0.117$\to$0.598) and +214% on Mem-Gallery (0.254$\to$0.797) relative to the initial configurations. Critically, the most impactful discoveries are not hyperparameter adjustments: bug fixes (+175%), architectural changes (+44%), and prompt engineering (+188% on specific categories) each individually exceed the cumulative contribution of all hyperparameter tuning, demonstrating capabilities fundamentally beyond the reach of traditional AutoML. We provide a taxonomy of six discovery types and identify four properties that make multimodal memory particularly suited for autoresearch, offering guidance for applying autonomous research pipelines to other AI system domains. Code is available at this https://github.com/aiming-lab/SimpleMem.

Genetically encoded fluorescent reporters to visualize α-synuclein pathology in live brain

✇Cell
By: Li Zhang · Minhui Yu · Guoqing Chen · Siyuan Ge · Mengdi Wang · Xianying Zhang · Miao Zhao · Huating Gu · Meizhu Huang · Aixue Liu · Gengxin Ran · Zeyuan Liu · Tiepeng Liao · Qi Chen · Chenjian Miao · Yao Lu · Yibing Wang · Fengchao Wang · Zhihui Liu · Hongying Zhu · Qian Wu · Zhuan Zhou · Wei Xiong · Xiaoqun Wang · Peng Cao
4 March 2026 at 08:00
The development of genetically encoded fluorescent reporters, along with their corresponding knock-in mouse lines for labeling α-Syn inclusions, enables diverse applications in studying the propagation and pathological effects of α-Syn inclusions in the live brain.
Received — 2 April 2026 ⏭

Design Principles for the Construction of a Benchmark Evaluating Security Operation Capabilities of Multi-agent AI Systems

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yicheng Cai · Mitchell John DeStefano · Guodong Dong · Pulkit Handa · Peng Liu · Tejas Singhal · Peiyu Tseng · Winston Jen White
1 April 2026 at 12:00
arXiv:2603.28998v1 Announce Type: cross Abstract: As Large Language Models (LLMs) and multi-agent AI systems are demonstrating increasing potential in cybersecurity operations, organizations, policymakers, model providers, and researchers in the AI and cybersecurity communities are interested in quantifying the capabilities of such AI systems to achieve more autonomous SOCs (security operation centers) and reduce manual effort. In particular, the AI and cybersecurity communities have recently developed several benchmarks for evaluating the red team capabilities of multi-agent AI systems. However, because the operations in SOCs are dominated by blue team operations, the capabilities of AI systems & agents to achieve more autonomous SOCs cannot be evaluated without a benchmark focused on blue team operations. To our best knowledge, no systematic benchmark for evaluating coordinated multi-task blue team AI has been proposed in the literature. Existing blue team benchmarks focus on a particular task. The goal of this work is to develop a set of design principles for the construction of a benchmark, which is denoted as SOC-bench, to evaluate the blue team capabilities of AI. Following these design principles, we have developed a conceptual design of SOC-bench, which consists of a family of five blue team tasks in the context of large-scale ransomware attack incident response.

Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jingwei Ni · Yihao Liu · Xinpeng Liu · Yutao Sun · Mengyu Zhou · Pengyu Cheng · Dexin Wang · Erchao Zhao · Xiaoxi Jiang · Guanjun Jiang
1 April 2026 at 12:00
arXiv:2603.25158v3 Announce Type: replace Abstract: Equipping Large Language Model (LLM) agents with domain-specific skills is critical for tackling complex tasks. Yet, manual authoring creates a severe scalability bottleneck. Conversely, automated skill generation often yields fragile or fragmented results because it either relies on shallow parametric knowledge or sequentially overfits to non-generalizable trajectory-local lessons. To overcome this, we introduce Trace2Skill, a framework that mirrors how human experts author skills: by holistically analyzing broad execution experience before distilling it into a single, comprehensive guide. Instead of reacting sequentially to individual trajectories, Trace2Skill dispatches a parallel fleet of sub-agents to analyze a diverse pool of executions. It extracts trajectory-specific lessons and hierarchically consolidates them into a unified, conflict-free skill directory via inductive reasoning. Trace2Skill supports both deepening existing human-written skills and creating new ones from scratch. Experiments in challenging domains, such as spreadsheet, VisionQA and math reasoning, show that Trace2Skill significantly improves upon strong baselines, including Anthropic's official xlsx skills. Crucially, this trajectory-grounded evolution does not merely memorize task instances or model-specific quirks: evolved skills transfer across LLM scales and generalize to OOD settings. For example, skills evolved by Qwen3.5-35B on its own trajectories improved a Qwen3.5-122B agent by up to 57.65 absolute percentage points on WikiTableQuestions. Ultimately, our results demonstrate that complex agent experience can be packaged into highly transferable, declarative skills -- requiring no parameter updates, no external retrieval modules, and utilizing open-source models as small as 35B parameters.

Two-step clinical care pathway to predict MASLD-related advanced fibrosis and long-term outcomes in type 2 diabetes

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Yuping Chen · Bingtian Dong · Xinrui Jin · Chuan Liu · Ming-Hua Zheng · Xiao Liang · Yameng Sun · Hye Won Lee · Huapeng Lin · Emmanuel Tsochatzis · Salvatore Petta · Elisabetta Bugianesi · Masato Yoneda · Hannes Hagström · Jérôme Boursier · José Luis Calleja · George Boon-Bee Goh · Wah-Kheong Chan · Rocio Gallego-Durán · Arun J Sanyal · Victor de Lédinghen · Philip N Newsome · Jian-Gao Fan · Laurent Castéra · Michelle Lai · Céline Fournier-Poizat · Grace Lai-Hung Wong · Grazia Pennisi · Angelo Armandi · Atsushi Nakajima · Wen-Yue Liu · Ying Shang · Marc de Saint-Loup · Elba Llop · Kevin Kim Jun Teh · Carmen Lara-Romero · Amon Asgharpour · Sara Mahgoub · Mandy Sau-Wai Chan · Adrien Lannes · Manuel Romero-Gomez · Airong Hu · Yiling Li · Qing-Lei Zeng · Wei Gou · Hua Bian · Xiao Han · Chenlin Sun · Seung Up Kim · Terry Cheuk-Fung Yip · Gao-Jun Teng · Vincent Wai-Sun Wong · Xiaolong Qi · DiabetesLiver Integrated Management (DLIM) Consortium
30 March 2026 at 18:00

Gut. 2026 Feb 9;75(3):576-587. doi: 10.1136/gutjnl-2025-337506.

ABSTRACT

BACKGROUND: Current guidelines recommend a two-step approach for risk stratification of metabolic dysfunction-associated steatotic liver disease (MASLD), starting with Fibrosis-4 index (FIB-4) followed by liver stiffness measurement (LSM) using vibration-controlled transient elastography (VCTE).

OBJECTIVE: To evaluate this approach for predicting advanced fibrosis and liver-related events (LREs) in patients with type 2 diabetes (T2D).

DESIGN: A prospective liver biopsy cohort of T2D patients with histologically confirmed MASLD from seven centres in China was used to assess diagnostic performance for advanced fibrosis. The international VCTE-Prognosis cohort, including T2D patients with MASLD who underwent VCTE at 16 centres in the USA, Europe and Asia, with longitudinal follow-up, was used to assess LREs, defined as hepatic decompensation or hepatocellular carcinoma.

RESULTS: 4781 participants were included. In the liver biopsy cohort (n=352; 22.2% with advanced fibrosis), applying LSM thresholds of <8 kPa and >12 kPa after FIB-4 classified patients into 63.4% low-risk, 9.4% intermediate-risk and 27.3% high-risk, with a correct classification rate of 71%. In the VCTE-Prognosis cohort (n=4429; median follow-up 51.3 (IQR 27.4-70.7) months), 140 (3.2%) patients developed LREs (110 (2.5%) with hepatic decompensation and 59 (1.3%) with hepatocellular carcinoma). The two-step approach classified 72.6%, 6.8% and 20.6% of patients into low-risk, intermediate-risk and high-risk groups, with corresponding 5-year cumulative LRE incidences of 0.7%, 0.9% and 11.8%. Refining classification of intermediate FIB-4 patients using LSM <10 kPa (low-risk) and >15 kPa (high-risk) reduced the intermediate-risk group to 5.6% while preserving predictive accuracy.

CONCLUSION: The non-invasive two-step approach of FIB-4 followed by LSM effectively stratifies MASLD-related advanced fibrosis and LREs risk in T2D. Applying LSM cut-offs of 10 and 15 kPa further optimises risk stratification for future LREs.

PMID:41911049 | DOI:10.1136/gutjnl-2025-337506

Received — 26 March 2026 ⏭

UAV-DETR: DETR for Anti-Drone Target Detection

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jun Yang · Dong Wang · Hongxu Yin · Hongpeng Li · Jianxiong Yu
25 March 2026 at 12:00
arXiv:2603.22841v1 Announce Type: cross Abstract: Drone detection is pivotal in numerous security and counter-UAV applications. However, existing deep learning-based methods typically struggle to balance robust feature representation with computational efficiency. This challenge is particularly acute when detecting miniature drones against complex backgrounds under severe environmental interference. To address these issues, we introduce UAV-DETR, a novel framework that integrates a small-target-friendly architecture with real-time detection capabilities. Specifically, UAV-DETR features a WTConv-enhanced backbone and a Sliding Window Self-Attention (SWSA-IFI) encoder, capturing the high-frequency structural details of tiny targets while drastically reducing parameter overhead. Furthermore, we propose an Efficient Cross-Scale Feature Recalibration and Fusion Network (ECFRFN) to suppress background noise and aggregate multi-scale semantics. To further enhance accuracy, UAV-DETR incorporates a hybrid Inner-CIoU and NWD loss strategy, mitigating the extreme sensitivity of standard IoU metrics to minor positional deviations in small objects. Extensive experiments demonstrate that UAV-DETR significantly outperforms the baseline RT-DETR on our custom UAV dataset (+6.61% in mAP50:95, with a 39.8% reduction in parameters) and the public DUT-ANTI-UAV benchmark (+1.4% in Precision, +1.0% in F1-Score). These results establish UAV-DETR as a superior trade-off between efficiency and precision in counter-UAV object detection. The code is available at https://github.com/wd-sir/UAVDETR.

3DCity-LLM: Empowering Multi-modality Large Language Models for 3D City-scale Perception and Understanding

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yiping Chen · Jinpeng Li · Wenyu Ke · Yang Luo · Jie Ouyang · Zhongjie He · Li Liu · Hongchao Fan · Hao Wu
25 March 2026 at 12:00
arXiv:2603.23447v1 Announce Type: cross Abstract: While multi-modality large language models excel in object-centric or indoor scenarios, scaling them to 3D city-scale environments remains a formidable challenge. To bridge this gap, we propose 3DCity-LLM, a unified framework designed for 3D city-scale vision-language perception and understanding. 3DCity-LLM employs a coarse-to-fine feature encoding strategy comprising three parallel branches for target object, inter-object relationship, and global scene. To facilitate large-scale training, we introduce 3DCity-LLM-1.2M dataset that comprises approximately 1.2 million high-quality samples across seven representative task categories, ranging from fine-grained object analysis to multi-faceted scene planning. This strictly quality-controlled dataset integrates explicit 3D numerical information and diverse user-oriented simulations, enriching the question-answering diversity and realism of urban scenarios. Furthermore, we apply a multi-dimensional protocol based on text-similarity metrics and LLM-based semantic assessment to ensure faithful and comprehensive evaluations for all methods. Extensive experiments on two benchmarks demonstrate that 3DCity-LLM significantly outperforms existing state-of-the-art methods, offering a promising and meaningful direction for advancing spatial reasoning and urban intelligence. The source code and dataset are available at https://github.com/SYSU-3DSTAILab/3D-City-LLM.
Received — 14 March 2026 ⏭

Multi-Omics and Single-Cell Mendelian Randomization Reveal a Potential Role of VNN2 in Lung Adenocarcinoma in Resting Natural Killer Cells

✇Omics In Lung
By: Zhi Chun Xue · Jing Lin · Jian Hui Wu · Zhi Wen Peng · Mei Yan Tang · Peng Liang · Hui Ling Chen · Gui Ju Fang · Qing Xue
13 March 2026 at 18:00

World J Oncol. 2026 Mar 5;17(2):247-255. doi: 10.14740/wjon2689. eCollection 2026 Apr.

ABSTRACT

BACKGROUND: We aimed to evaluate the potential association between genetically predicted vanin-2 (VNN2) expression and lung adenocarcinoma (LUAD) risk, and to explore the immune cell subtype that may underlie this relationship.

METHODS: We integrated whole-blood expression quantitative trait loci (eQTL) data from eQTLGen, plasma protein quantitative trait loci (pQTL) data from deCODE, and LUAD genome-wide association study (GWAS) data from European-ancestry cohorts, together with differential expression analysis using GEPIA2, to identify candidate genes for subsequent single-cell eQTL (sc-eQTL) Mendelian randomization (MR) analysis. For the sc-eQTL analysis, VNN2-associated eQTLs from 14 immune cell types profiled in the OneK1K single-cell eQTL resource were tested for associations with LUAD risk.

RESULTS: Bulk-level MR analysis showed that genetically predicted increases in VNN2 expression and protein levels were significantly associated with a reduced risk of LUAD (eQTL-MR: odds ratio (OR) = 0.964, 95% confidence interval (95% CI), 0.934-0.995; P = 0.024; pQTL-MR: OR = 0.946, 95% CI, 0.921-0.970; P = 2.87 × 10-5). Transcriptomic analyses confirmed significant downregulation of VNN2 in LUAD tumors compared with normal lung tissues. sc-eQTL MR identified the strongest association in resting natural killer (rNK) cells (OR = 0.896, 95% CI, 0.829-0.967; P = 0.005).

CONCLUSIONS: Multi-omics and sc-eQTL MR analyses indicated that genetically predicted increases in VNN2 expression were associated with a reduced risk of LUAD, with the most pronounced effect observed in rNK cells. These findings suggest a potential cell type-specific role of VNN2 in LUAD susceptibility and warrant further studies to validate its biological relevance and clinical implications.

PMID:41822323 | PMC:PMC12978397 | DOI:10.14740/wjon2689

Inhibition of ZBTB7B-mediated ADPGK transcription by NEDD4 impedes glycolysis and progression of lung adenocarcinoma

✇Oncogenesis - nature.com science feeds
By: Fang-Peng Liu · Ting Huang · Hai-Yan Yang · Jian-Hua Zha · Chuan Xu · Cheng-Peng Qiu · Xing Wang · Zhuo Lu · Tao Wang
11 March 2026 at 08:00

Oncogenesis, Published online: 11 March 2026; doi:10.1038/s41389-026-00605-5

Inhibition of ZBTB7B-mediated ADPGK transcription by NEDD4 impedes glycolysis and progression of lung adenocarcinoma
Received — 11 March 2026 ⏭

CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Haodong Li · Chunmei Qing · Huanyu Zhang · Dongzhi Jiang · Yihang Zou · Hongbo Peng · Dingming Li · Yuhong Dai · ZePeng Lin · Juanxi Tian · Yi Zhou · Siqi Dai · Jingwei Wu
10 March 2026 at 12:00
arXiv:2603.08652v1 Announce Type: new Abstract: Recent advancements in Unified Multimodal Models (UMMs) have significantly advanced text-to-image (T2I) generation, particularly through the integration of Chain-of-Thought (CoT) reasoning. However, existing CoT-based T2I methods largely rely on abstract natural-language planning, which lacks the precision required for complex spatial layouts, structured visual elements, and dense textual content. In this work, we propose CoCo (Code-as-CoT), a code-driven reasoning framework that represents the reasoning process as executable code, enabling explicit and verifiable intermediate planning for image generation. Given a text prompt, CoCo first generates executable code that specifies the structural layout of the scene, which is then executed in a sandboxed environment to render a deterministic draft image. The model subsequently refines this draft through fine-grained image editing to produce the final high-fidelity result. To support this training paradigm, we construct CoCo-10K, a curated dataset containing structured draft-final image pairs designed to teach both structured draft construction and corrective visual refinement. Empirical evaluations on StructT2IBench, OneIG-Bench, and LongText-Bench show that CoCo achieves improvements of +68.83%, +54.8%, and +41.23% over direct generation, while also outperforming other generation methods empowered by CoT. These results demonstrate that executable code is an effective and reliable reasoning paradigm for precise, controllable, and structured text-to-image generation. The code is available at: https://github.com/micky-li-hd/CoCo

Improved Constrained Generation by Bridging Pretrained Generative Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xiaoxuan Liang · Saeid Naderiparizi · Yunpeng Liu · Berend Zwartsenberg · Frank Wood
10 March 2026 at 12:00
arXiv:2603.06742v1 Announce Type: cross Abstract: Constrained generative modeling is fundamental to applications such as robotic control and autonomous driving, where models must respect physical laws and safety-critical constraints. In real-world settings, these constraints rarely take the form of simple linear inequalities, but instead complex feasible regions that resemble road maps or other structured spatial domains. We propose a constrained generation framework that generates samples directly within such feasible regions while preserving realism. Our method fine-tunes a pretrained generative model to enforce constraints while maintaining generative fidelity. Experimentally, our method exhibits characteristics distinct from existing fine-tuning and training-free constrained baselines, revealing a new compromise between constraint satisfaction and sampling quality.

iGVLM: Dynamic Instruction-Guided Vision Encoding for Question-Aware Multimodal Understanding

✇cs.AI, q-bio.NC updates on arXiv.org
By: Hanpeng Liu · Yaqian Li · Zidan Wang · Shuoxi Zhang · Zihao Bo · Rinyoichi Takezoe · Kaiwen Long · Kun He
10 March 2026 at 12:00
arXiv:2603.02748v2 Announce Type: replace-cross Abstract: Despite the success of Large Vision--Language Models (LVLMs), most existing architectures suffer from a representation bottleneck: they rely on static, instruction-agnostic vision encoders whose visual representations are utilized in an invariant manner across different textual tasks. This rigidity hinders fine-grained reasoning where task-specific visual cues are critical. To address this issue, we propose iGVLM, a general framework for instruction-guided visual modulation. iGVLM introduces a decoupled dual-branch architecture: a frozen representation branch that preserves task-agnostic visual representations learned during pre-training, and a dynamic conditioning branch that performs affine feature modulation via Adaptive Layer Normalization (AdaLN). This design enables a smooth transition from general-purpose perception to instruction-aware reasoning while maintaining the structural integrity and stability of pre-trained visual priors. Beyond standard benchmarks, we introduce MM4, a controlled diagnostic probe for quantifying logical consistency under multi-query, multi-instruction settings. Extensive results show that iGVLM consistently enhances instruction sensitivity across diverse language backbones, offering a plug-and-play paradigm for bridging passive perception and active reasoning.

ITO: Images and Texts as One via Synergizing Multiple Alignment and Training-Time Fusion

✇cs.AI, q-bio.NC updates on arXiv.org
By: Hanpeng Liu · Yaqian Li · Zidan Wang · Shuoxi Zhang · Zonglin Zhao · Zihao Bo · Rinyoichi Takezoe · Kaiwen Long · Kun He
10 March 2026 at 12:00
arXiv:2603.02767v3 Announce Type: replace-cross Abstract: Image-text contrastive pretraining has become a dominant paradigm for visual representation learning, yet existing methods often yield representations that remain partially organized by modality. We propose ITO, a framework addressing this limitation through two synergistic mechanisms. Multimodal multiple alignment enriches supervision by mining diverse image-text correspondences, while a lightweight training-time multimodal fusion module enforces structured cross-modal interaction. Crucially, the fusion module is discarded at inference, preserving the efficiency of standard dual-encoder architectures. Extensive experiments show that ITO consistently outperforms strong baselines across classification, retrieval, and multimodal benchmarks. Our analysis reveals that while multiple alignment drives discriminative power, training-time fusion acts as a critical structural regularizer -- eliminating the modality gap and stabilizing training dynamics to prevent the early saturation often observed in aggressive contrastive learning.
Received — 5 March 2026 ⏭

Separators in Enhancing Autoregressive Pretraining for Vision Mamba

✇cs.AI, q-bio.NC updates on arXiv.org
By: Hanpeng Liu · Zidan Wang · Shuoxi Zhang · Kaiyuan Gao · Kun He
5 March 2026 at 13:00
arXiv:2603.03806v1 Announce Type: cross Abstract: The state space model Mamba has recently emerged as a promising paradigm in computer vision, attracting significant attention due to its efficient processing of long sequence tasks. Mamba's inherent causal mechanism renders it particularly suitable for autoregressive pretraining. However, current autoregressive pretraining methods are constrained to short sequence tasks, failing to fully exploit Mamba's prowess in handling extended sequences. To address this limitation, we introduce an innovative autoregressive pretraining method for Vision Mamba that substantially extends the input sequence length. We introduce new \textbf{S}epara\textbf{T}ors for \textbf{A}uto\textbf{R}egressive pretraining to demarcate and differentiate between different images, known as \textbf{STAR}. Specifically, we insert identical separators before each image to demarcate its inception. This strategy enables us to quadruple the input sequence length of Vision Mamba while preserving the original dimensions of the dataset images. Employing this long sequence pretraining technique, our STAR-B model achieved an impressive accuracy of 83.5\% on ImageNet-1k, which is highly competitive in Vision Mamba. These results underscore the potential of our method in enhancing the performance of vision models through improved leveraging of long-range dependencies.

ITO: Images and Texts as One via Synergizing Multiple Alignment and Training-Time Fusion

✇cs.AI, q-bio.NC updates on arXiv.org
By: HanZpeng Liu · Yaqian Li · Zidan Wang · Shuoxi Zhang · Zonglin Zhao · Zihao Bo · Rinyoichi Takezoe · Kaiwen Long · Kun He
5 March 2026 at 13:00
arXiv:2603.02767v2 Announce Type: replace-cross Abstract: Image-text contrastive pretraining has become a dominant paradigm for visual representation learning, yet existing methods often yield representations that remain partially organized by modality. We propose ITO, a framework addressing this limitation through two synergistic mechanisms. Multimodal multiple alignment enriches supervision by mining diverse image-text correspondences, while a lightweight training-time multimodal fusion module enforces structured cross-modal interaction. Crucially, the fusion module is discarded at inference, preserving the efficiency of standard dual-encoder architectures. Extensive experiments show that ITO consistently outperforms strong baselines across classification, retrieval, and multimodal benchmarks. Our analysis reveals that while multiple alignment drives discriminative power, training-time fusion acts as a critical structural regularizer -- eliminating the modality gap and stabilizing training dynamics to prevent the early saturation often observed in aggressive contrastive learning.

iGVLM: Dynamic Instruction-Guided Vision Encoding for Question-Aware Multimodal Understanding

✇cs.AI, q-bio.NC updates on arXiv.org
By: HanZpeng Liu · Yaqian Li · Zidan Wang · Shuoxi Zhang · Zihao Bo · Rinyoichi Takezoe · Kaiwen Long · Kun He
4 March 2026 at 13:00
arXiv:2603.02748v1 Announce Type: cross Abstract: Despite the success of Large Vision--Language Models (LVLMs), most existing architectures suffer from a representation bottleneck: they rely on static, instruction-agnostic vision encoders whose visual representations are utilized in an invariant manner across different textual tasks. This rigidity hinders fine-grained reasoning where task-specific visual cues are critical. To address this issue, we propose iGVLM, a general framework for instruction-guided visual modulation. iGVLM introduces a decoupled dual-branch architecture: a frozen representation branch that preserves task-agnostic visual representations learned during pre-training, and a dynamic conditioning branch that performs affine feature modulation via Adaptive Layer Normalization (AdaLN). This design enables a smooth transition from general-purpose perception to instruction-aware reasoning while maintaining the structural integrity and stability of pre-trained visual priors. Beyond standard benchmarks, we introduce MM4, a controlled diagnostic probe for quantifying logical consistency under multi-query, multi-instruction settings. Extensive results show that iGVLM consistently enhances instruction sensitivity across diverse language backbones, offering a plug-and-play paradigm for bridging passive perception and active reasoning.

ITO: Images and Texts as One via Synergizing Multiple Alignment and Training-Time Fusion

✇cs.AI, q-bio.NC updates on arXiv.org
By: HanZpeng Liu · Yaqian Li · Zidan Wang · Shuoxi Zhang · Zonglin Zhao · Zihao Bo · Rinyoichi Takezoe · Kaiwen Long · Kun He
4 March 2026 at 13:00
arXiv:2603.02767v1 Announce Type: cross Abstract: Image-text contrastive pretraining has become a dominant paradigm for visual representation learning, yet existing methods often yield representations that remain partially organized by modality. We propose ITO, a framework addressing this limitation through two synergistic mechanisms. Multimodal multiple alignment enriches supervision by mining diverse image-text correspondences, while a lightweight training-time multimodal fusion module enforces structured cross-modal interaction. Crucially, the fusion module is discarded at inference, preserving the efficiency of standard dual-encoder architectures. Extensive experiments show that ITO consistently outperforms strong baselines across classification, retrieval, and multimodal benchmarks. Our analysis reveals that while multiple alignment drives discriminative power, training-time fusion acts as a critical structural regularizer -- eliminating the modality gap and stabilizing training dynamics to prevent the early saturation often observed in aggressive contrastive learning.
Received — 25 February 2026 ⏭

City Editing: Hierarchical Agentic Execution for Dependency-Aware Urban Geospatial Modification

✇cs.AI, q-bio.NC updates on arXiv.org
By: Rui Liu · Steven Jige Quan · Zhong-Ren Peng · Zijun Yao · Han Wang · Zhengzhang Chen · Kunpeng Liu · Yanjie Fu · Dongjie Wang
24 February 2026 at 13:00
arXiv:2602.19326v1 Announce Type: cross Abstract: As cities evolve over time, challenges such as traffic congestion and functional imbalance increasingly necessitate urban renewal through efficient modification of existing plans, rather than complete re-planning. In practice, even minor urban changes require substantial manual effort to redraw geospatial layouts, slowing the iterative planning and decision-making procedure. Motivated by recent advances in agentic systems and multimodal reasoning, we formulate urban renewal as a machine-executable task that iteratively modifies existing urban plans represented in structured geospatial formats. More specifically, we represent urban layouts using GeoJSON and decompose natural-language editing instructions into hierarchical geometric intents spanning polygon-, line-, and point-level operations. To coordinate interdependent edits across spatial elements and abstraction levels, we propose a hierarchical agentic framework that jointly performs multi-level planning and execution with explicit propagation of intermediate spatial constraints. We further introduce an iterative execution-validation mechanism that mitigates error accumulation and enforces global spatial consistency during multi-step editing. Extensive experiments across diverse urban editing scenarios demonstrate significant improvements in efficiency, robustness, correctness, and spatial validity over existing baselines.

Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters

✇cs.AI, q-bio.NC updates on arXiv.org
By: Ailin Huang · Ang Li · Aobo Kong · Bin Wang · Binxing Jiao · Bo Dong · Bojun Wang · Boyu Chen · Brian Li · Buyun Ma · Chang Su · Changxin Miao · Changyi Wan · Chao Lou · Chen Hu · Chen Xu · Chenfeng Yu · Chengting Feng · Chengyuan Yao · Chunrui Han · Dan Ma · Dapeng Shi · Daxin Jiang · Dehua Ma · Deshan Sun · Di Qi · Enle Liu · Fajie Zhang · Fanqi Wan · Guanzhe Huang · Gulin Yan · Guoliang Cao · Guopeng Li · Han Cheng · Hangyu Guo · Hanshan Zhang · Hao Nie · Haonan Jia · Haoran Lv · Hebin Zhou · Hekun Lv · Heng Wang · Heung-Yeung Shum · Hongbo Huang · Hongbo Peng · Hongyu Zhou · Hongyuan Wang · Houyong Chen · Huangxi Zhu · Huimin Wu · Huiyong Guo · Jia Wang · Jian Zhou · Jianjian Sun · Jiaoren Wu · Jiaran Zhang · Jiashu Lv · Jiashuo Liu · Jiayi Fu · Jiayu Liu · Jie Cheng · Jie Luo · Jie Yang · Jie Zhou · Jieyi Hou · Jing Bai · Jingcheng Hu · Jingjing Xie · Jingwei Wu · Jingyang Zhang · Jishi Zhou · Junfeng Liu · Junzhe Lin · Ka Man Lo · Kai Liang · Kaibo Liu · Kaijun Tan · Kaiwen Yan · Kaixiang Li · Kang An · Kangheng Lin · Lei Yang · Liang Lv · Liang Zhao · Liangyu Chen · Lieyu Shi · Liguo T
24 February 2026 at 13:00
arXiv:2602.10604v2 Announce Type: replace-cross Abstract: We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency. We focus on what matters most when building agents: sharp reasoning and fast, reliable execution. Step 3.5 Flash pairs a 196B-parameter foundation with 11B active parameters for efficient inference. It is optimized with interleaved 3:1 sliding-window/full attention and Multi-Token Prediction (MTP-3) to reduce the latency and cost of multi-round agentic interactions. To reach frontier-level intelligence, we design a scalable reinforcement learning framework that combines verifiable signals with preference feedback, while remaining stable under large-scale off-policy training, enabling consistent self-improvement across mathematics, code, and tool use. Step 3.5 Flash demonstrates strong performance across agent, coding, and math tasks, achieving 85.4% on IMO-AnswerBench, 86.4% on LiveCodeBench-v6 (2024.08-2025.05), 88.2% on tau2-Bench, 69.0% on BrowseComp (with context management), and 51.0% on Terminal-Bench 2.0, comparable to frontier models such as GPT-5.2 xHigh and Gemini 3.0 Pro. By redefining the efficiency frontier, Step 3.5 Flash provides a high-density foundation for deploying sophisticated agents in real-world industrial environments.
❌