❌

Normal view

Received — 15 September 2026 ⏭

FEAT: A Linear-Complexity Foundation Model for Extremely Large Structured Data

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhenghang Song · Tang Qian · Lu Chen · Yushuai Li · Zhengke Hu · Bingbing Fang · Yumeng Song · Junbo Zhao · Sheng Zhang · Tianyi Li
14 September 2026 at 12:00
arXiv:2603.16513v4 Announce Type: replace-cross Abstract: Structured data is widely used in domains such as healthcare, finance, and scientific data management. Recent studies on structured data foundation models (SFMs) aim to support data analysis and mining tasks over such data, but still face scalability and generalization challenges when applied to real-world enterprise databases. First, many SFMs rely on full self-attention, which introduces an O(N^2) computational bottleneck and limits the number of tuples that can be processed jointly. Second, directly replacing attention with linear-complexity sequence models may conflict with the permutation-invariant nature of structured data, introducing artificial order bias and degrading representation quality. Moreover, models trained only on synthetic data may struggle to generalize to the heavy-tailed and heterogeneous distributions commonly found in real-world databases. To address these challenges, we propose FEAT, a linear-complexity foundation model for extremely large structured data. FEAT replaces quadratic attention with a multi-layer dual-axis encoding architecture. It integrates an adaptive-fusion bidirectional state-space model (AFBM) with convolutional gated linear attention (Conv-GLA), enabling cross-tuple contextualization in O(N) time while supporting permutation-invariant representation learning. To improve robustness under real-world data skewness, FEAT further adopts a hybrid structural causal pre-training pipeline with a robust reconstruction objective. Experiments on 12 real-world database benchmarks show that FEAT consistently outperforms representative SFMs on zero-shot tasks and scales linearly with structured-data sample length, achieving up to 50x faster inference latency.
Received — 10 September 2026 ⏭

RobustSGPO: Search-Space Control for Agent Harness Evolution

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zibo Zhao · Jijun Shi · Mo Zhou · Zhongyuan Wang · Shifu Bie · Yunfei Zhang · Xuanting Zhou · Xiangyu Wu · Bin Liu · Ruiming Tang · Wenwu Ou · Kun Gai
10 September 2026 at 12:00
arXiv:2609.09646v1 Announce Type: new Abstract: Semantic-gradient-based prompt optimization (SGPO) improves agent harnesses using execution feedback, but its local update rule leaves the choice of edit scope and operation unresolved. We introduce RobustSGPO, which specifies the requested edit, constructs and checks the patch, and continues search from either the incumbent or retained snapshots. We evaluate permission scheduling, cumulative controls, and task-family transfer in the AgentX brainstorming workflow using 120 tasks, 95 runs, and 7,350 candidate attempts. Periodic $1\to2\to3$ scheduling exceeds fixed maximum permission by 0.28 test-score points. RobustSGPO increases completion on 30 held-out tasks from 60.0% to 80.0% and improves test quality from 3.77 to 4.14 under a 20-million-token budget. Category retention reduces source-task degradation after a shift, whereas random retention reaches a higher destination endpoint. Search-space control benefits quality through executable edits and alternative starting points, with measurable retention overhead.

Beyond One-Size-Fits-All: Sample-Adaptive Strategy Routing for Vision Token Pruning in MLLMs

✇cs.AI, q-bio.NC updates on arXiv.org
By: Haiji Liang · Pengfei Zhou · Zhenglin Wan · Wei Wang · Yang You · Wangbo Zhao
10 September 2026 at 12:00
arXiv:2609.10346v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) process hundreds or thousands of visual tokens per image, incurring prohibitive inference costs. While existing vision token pruning methods mitigate this overhead, they implicitly assume that a single fixed pruning strategy can be applied uniformly across all inputs. Our analysis further reveals that ranking pruning methods by average benchmark accuracy conceals substantial sample-wise complementarity: although the average-best strategy excels overall, alternative strategies prove superior on a significant fraction of individual samples. To harness this diversity, we propose VIP-Router, a lightweight VIsion Pruning Router that adaptively selects the pruning strategy predicted to be best suited to each input at a specified pruning level. Conditioned on low-cost visual and textual features, VIP-Router identifies the most suitable candidate strategy while retaining full-token inference as an option when pruning is predicted to be unfavorable. Evaluated on a curated suite of pruning-sensitive visual perception benchmarks, VTC-Bench Group A, VIP-Router consistently outperforms the best fixed strategy baseline across all reduction ratios, achieving a 26.9% relative improvement in average accuracy, and a 22.0% relative increase in average utility after accounting for realized token cost. Crucially, VIP-Router operates in a plug-and-play manner without modifying underlying pruning algorithms or model weights, introducing trainable parameters equivalent to merely 0.017\% of the backbone. Furthermore, VIP-Router proves effective across various MLLM backbones and yields consistent gains on unseen benchmarks, highlighting the potential of sample adaptive routing for visual token pruning.

Protein glycosylation profiling in lung adenocarcinoma and precursor lesions: analysis of FFPE tissue sections

✇Pulmonary nodule
By: Jinggang Cui · Yan Chen · Shuang Yue · Jianbo Deng · Wenqi Zhang · Shengye Wen · Lingbo Zhao · Rumeng Zhang · Shuang Yang · Junhong Jiang
27 July 2026 at 18:00

Anal Bioanal Chem. 2026 Jul 27. doi: 10.1007/s00216-026-06702-z. Online ahead of print.

ABSTRACT

Protein glycosylation is a major post-translational modification that regulates tumor initiation and progression; however, its dynamic modeling during multistep evolution of lung adenocarcinoma (LUAD) remains poorly understood, particularly in clinically archived tissues. Here, we established an integrated multi-omics workflow combining global proteomes, N-glycans, and site-specific intact N-glycopeptides to comprehensively characterize glycosylation in formalin-fixed paraffin-embedded (FFPE) specimens spanning four pathological stages of LUAD progression: inflammatory nodules (IN), atypical adenomatous hyperplasia (AAH), adenocarcinoma in situ (AIS), and invasive adenocarcinoma (IAC). Using optimized protein extraction, hydrophilic interaction liquid chromatography (HILIC)-based glycopeptide enrichment, and high-resolution LC-MS/MS, we achieved large-scale identification of proteins, N-glycans, and intact glycopeptides from archival clinical samples. Integrated analyses revealed progressive remodeling of site-specific N-glycosylation during malignant transformation, characterized by increased glycan branching, fucosylation, and sialylation during the transition from premalignant lesions to invasive cancer. Sialylated glycans reached their highest abundance in the premalignant AAH stage, whereas highly branched and fucosylated complex N-glycans predominated in invasive adenocarcinoma, indicating stage-dependent glycan remodeling throughout disease progression. Functional enrichment analyses linked these glycosylation alterations to extracellular matrix organization, neutrophil degranulation, and immune-associated pathways, while representative glycoproteins, including CEACAM6 and FGB, exhibited coordinated changes in protein abundance and site-specific glycoform micro-heterogeneity across pathological stages. Collectively, this study demonstrates the feasibility of deep glycoproteomic profiling using archived FFPE tissues and provides a comprehensive molecular atlas of glycosylation remodeling during LUAD progression. These findings establish a valuable resource for elucidating disease mechanisms and identifying stage-specific glycosylation biomarkers and potential glycan-targeted therapeutic candidates for early lung adenocarcinoma.

PMID:42509285 | DOI:10.1007/s00216-026-06702-z

Received — 27 May 2026 ⏭

Neuronal Stochastic Attention Circuit (NSAC) for Probabilistic Representation Learning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Waleed Razzaq · Yun-Bo Zhao
26 May 2026 at 12:00
arXiv:2605.26061v1 Announce Type: cross Abstract: Reliable quantification of uncertainty estimates in continuous-time (CT) representation learning remains nascent, particularly within CT attention architectures. We introduce the Neuronal Stochastic Attention Circuit (NSAC), a novel biologically-inspired CT attention architecture that reformulates attention logit computation as the solution of an Ornstein-Uhlenbeck stochastic differential equation modulated by input-dependent, nonlinear interlinked gates derived from repurposed C.elegans Neuronal Circuit Policies (NCPs) wiring mechanism. It induces Gaussian distribution over logits that propagates principled stochasticity through logistic-normal distribution over attention weights to yield probabilistic output. A two-term objective function combining Gaussian negative log-likelihood with an epistemic-separation regularizer enforces higher predictive variance and enables joint quantification of aleatoric and epistemic uncertainty. Empirically, we implement NSAC in a diverse set of learning tasks including: (i) irregular CT function approximation; (ii) multivariate regression; (iii) long-range forecasting; (iv) Industry 4.0; and (v) the lane-keeping of autonomous vehicles. We observe that the NSAC remains competitive against several baselines in terms of accuracy and produces reasonably well-calibrated uncertainty estimates while being interpretable at the neuronal cell level.

Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference

✇cs.AI, q-bio.NC updates on arXiv.org
By: Ziyan Liu · Yeqiu Chen · Hongyi Cai · Tao Lin · Shuo Yang · Zheng Liu · Bo Zhao
26 May 2026 at 12:00
arXiv:2511.16449v5 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have shown great potential for embodied AI by integrating visual perception, language understanding, and action execution. In real-time deployment, these models must process continuous visual streams, incurring substantial computational overhead. Visual token pruning -- a mainstream technique for accelerating Vision-Language Models (VLMs) by retaining salient tokens while discarding redundant ones -- offers a natural candidate solution to this challenge. However, directly applying VLM-oriented pruning methods to VLA inference can cause severe degradation in manipulation performance. Our analysis attributes this degradation to a key mismatch: VLA inference exhibits distinct attention patterns between the vision-language prefill stage and the action-decode stage, so pruning based only on context-prefill semantic salience is biased toward semantic cues and may remove action-critical visual tokens. Motivated by this observation, we propose VLA-Pruner, an effective plug-and-play token pruning method grounded in the visual requirements of VLA inference, further exploiting the temporal continuity of robot manipulation. Specifically, VLA-Pruner estimates visual-token importance from both semantic prefilling and temporally smoothed action relevance, and then applies a Combine-then-Filter strategy to retain compact, non-redundant tokens under the compute budget. Experiments show that VLA-Pruner outperforms state-of-the-art approaches across multiple VLA architectures, achieving up to 1.99x speedup with comparable manipulation quality.
Received — 17 February 2026 ⏭

Two-Stream Interactive Joint Learning of Scene Parsing and Geometric Vision Tasks

✇cs.AI, q-bio.NC updates on arXiv.org
By: Guanfeng Tang · Hongbo Zhao · Ziwei Long · Jiayao Li · Bohong Xiao · Wei Ye · Hanli Wang · Rui Fan
17 February 2026 at 13:00
arXiv:2602.13588v1 Announce Type: cross Abstract: Inspired by the human visual system, which operates on two parallel yet interactive streams for contextual and spatial understanding, this article presents Two Interactive Streams (TwInS), a novel bio-inspired joint learning framework capable of simultaneously performing scene parsing and geometric vision tasks. TwInS adopts a unified, general-purpose architecture in which multi-level contextual features from the scene parsing stream are infused into the geometric vision stream to guide its iterative refinement. In the reverse direction, decoded geometric features are projected into the contextual feature space for selective heterogeneous feature fusion via a novel cross-task adapter, which leverages rich cross-view geometric cues to enhance scene parsing. To eliminate the dependence on costly human-annotated correspondence ground truth, TwInS is further equipped with a tailored semi-supervised training strategy, which unleashes the potential of large-scale multi-view data and enables continuous self-evolution without requiring ground-truth correspondences. Extensive experiments conducted on three public datasets validate the effectiveness of TwInS's core components and demonstrate its superior performance over existing state-of-the-art approaches. The source code will be made publicly available upon publication.
There are no more articles
❌