❌

Reading view

↗️

VectorArk: Learning Practical Image Vectorization with Rounded Polygon Representation

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Tarun Gehlaut Β· Difan Liu Β· Charu Bansal Β· Krutik Malani Β· Souymodip Chakraborty Β· Ankit Phogat Β· Matthew Fisher Β· Vineet Batra
arXiv:2605.24398v1 Announce Type: cross Abstract: Recent vision-language model (VLM)-based approaches have achieved impressive results on image vectorization tasks. However, they are typically evaluated on synthetic benchmarks, where clean SVGs are rasterized at high resolution and then re-vectorized. As a result, these methods generalize poorly to real-world scenarios, such as images with unknown rasterization methods or those generated by text-to-image models. We introduce VectorArk, a new VLM-based model designed for robust and practical image vectorization. VectorArk employs a novel rounded polygon representation that simplifies the learning process while naturally producing smooth, visually appealing primitives. We also propose a degradation model that enhances robustness across diverse and imperfect inputs. Our experiments show that, in contrast to previous methods, VectorArk achieves superior geometric completeness and artifact suppression across multiple datasets, with comprehensive ablations validating the contribution of each component.
  •  
  • ↗️
↗️

Step-TP: A Grounded, Step-Level Dataset with Chain-of-Thought Reasoning for LLM-Guided Tensor Program Optimization

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Mengfan Liu Β· Da Zheng Β· Junwei Su Β· Chuan Wu
arXiv:2605.25954v1 Announce Type: cross Abstract: Despite the strong reasoning capabilities of large language models (LLMs), optimizing the execution efficiency of tensor programs remains challenging due to the need for precise, composable transformation decisions. Recent LLM-guided approaches frame tensor program optimization as an iterative decision process, but existing datasets provide only end-to-end optimized program pairs using token-inefficient representations, lacking verifiable step-level supervision and interpretability. As a result, LLMs struggle to make reliable single-step decisions in large combinatorial optimization spaces. We introduce Step-TP, a post-training dataset for tensor program optimization that provides grounded, atomic, step-level supervision with structured chain-of-thought (CoT) reasoning. Step-TP forms a closed reasoning loop over intermediate program states, enabling reliable multi-step optimization rather than outcome imitation. Its design is guided by four principles: (i) a token-efficient, verifiable intermediate representation (IR) that deterministically lowers to TVM TIR; (ii) atomic and composable optimization strategies that decompose complex trajectories into interpretable single-step decisions; (iii) structured CoT supervision coupled with explicit IR-to-IR state transitions; and (iv) strategy filtering to balance coverage while preventing shortcut exploitation. The dataset and implementation are available at a GitHub link, https://github.com/LIUMENGFAN-gif/StepTP.
  •  
  • ↗️
↗️

HiTeC: Hierarchical Contrastive Learning on Text-Attributed Hypergraph with Semantic-Aware Augmentation

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Mengting Pan Β· Fan Li Β· Chen Chen Β· Xiaoyang Wang Β· Wenjie Zhang
arXiv:2508.03104v3 Announce Type: replace-cross Abstract: Contrastive learning (CL) has become a dominant paradigm for self-supervised hypergraph learning, enabling effective training without costly labels. However, node entities in real-world hypergraphs are often associated with rich textual information, which has been largely ignored in prior works. Directly applying existing CL-based methods to such text-attributed hypergraphs (TAHGs) leads to three key limitations: (1) The common use of graph-agnostic text encoders fails to capture the correlations between textual semantics and hypergraph topology, resulting in less expressive representations. (2) Their reliance on random data augmentations introduces noise and weakens the contrastive signals. (3) The primary focus on node- and hyperedge-level contrastive signals limits the ability to capture long-range dependencies, which is essential for effective representation learning. To address these challenges, we introduce HiTeC, a two-stage hierarchical contrastive learning framework for effective self-supervised learning on TAHGs. In the first stage, we pre-train the text encoder with a structure-aware contrastive objective to overcome the graph-agnostic nature of conventional methods. In the second stage, we begin by introducing semantic-aware augmentations, including structure-contextualized text augmentation and semantic-aware hyperedge dropping, to facilitate informative view generation. Subsequently, we propose a multi-scale contrastive loss with an $s$-walk-based subgraph-level objective to capture long-range dependencies. Extensive experiments on six real-world datasets validate the effectiveness of our proposed method.
  •  
  • ↗️
↗️

CD300ld on pathologically activated neutrophils promotes tumor immune suppression by binding phosphatidylserine on CD8<sup>+</sup> T cells

βœ‡Nature Cancer
By: Chaoxiong Wang Β· Peixuan Zheng Β· Anhui Wang Β· Xinrui Fan Β· Tianxiang Li Β· Jingjing Hong Β· Runze Wang Β· Chunyan Zhang Β· Chaogui Luo Β· Weiwei Yang Β· Dong Gao Β· Adili Salai Β· Min Luo Β· Zhigang Lu Β· Dianfan Li Β· Moubin Lin Β· Jiayin Peng Β· Guohui Li Β· Shuo Han Β· Yun Zhao

Nature Cancer, Published online: 15 May 2026; doi:10.1038/s43018-026-01169-4

Zhao and colleagues show that CD300ld, upregulated in pathologically activated neutrophils, mediates contact-dependent suppression of cytotoxic CD8+ T cells by binding to phosphatidylserine, inhibiting antitumor immune responses.
  •  
  • ↗️
↗️

An Orally Deliverable, Food-Compatible Lyophilized Recombinant Whole-Cell Catalyst for Alcohol-Associated Liver Injury

βœ‡Omics in Gastric
By: Fan Li Β· Meng-Yue Zhang Β· Xiao-Le Shan Β· Cai-Yun Wang Β· Ying-Ying Wu Β· Shuang Li Β· Shi-Qiao Xu Β· Yi-Xuan Zhang

Microorganisms. 2026 Mar 26;14(4):746. doi: 10.3390/microorganisms14040746.

ABSTRACT

Effective oral interventions for alcohol-induced metabolic stress and liver injury remain limited. Pre-absorptive gastrointestinal alcohol handling is gaining interest as a non-pharmacological strategy to reduce hepatic burden. In this study, we developed a formulation-integrated, food-compatible lyophilized recombinant whole-cell catalyst based on Escherichia coli Nissle 1917 engineered to express alcohol dehydrogenase and acetaldehyde dehydrogenase. Rather than focusing exclusively on strain-level genetic modification, the engineered cells were protected by lyophilization combined with a food-grade chitosan-alginate layer-by-layer coating, forming an artificial cell wall designed to enhance survivability during oral delivery. The formulation resisted simulated gastric acid, sodium taurocholate, and ethanol, retained enzymatic activity after storage, and demonstrated formulation stability. In alcohol-exposed mice, oral administration reduced blood ethanol and acetaldehyde levels, improved liver biochemical parameters, attenuated hepatic steatosis, and partially restored oxidative stress indicators. Integrated multi-omics analyses indicated coordinated gut-associated metabolic and inflammatory responses to alcohol and intervention, rather than a single dominant pathway. These findings provide hypothesis-generating evidence; causality remains to be established. Overall, this study demonstrates a proof-of-concept, food-compatible lyophilized recombinant whole-cell catalyst that integrates enzymatic function with formulation stability and gastrointestinal resilience, highlighting an applied, food-compatible microbial framework for exploring alcohol-related metabolic stress.

PMID:42075143 | PMC:PMC13119499 | DOI:10.3390/microorganisms14040746

  •  
  • ↗️
↗️

Respiratory viral infections prime accelerated lung cancer growth

βœ‡Cell
By: Wei Qian Β· Xiaoqin Wei Β· Andrew J. Barros Β· Xiangyu Ye Β· Haibo Zhang Β· Qing Yu Β· Samuel P. Young Β· Eric V. Yeatts Β· Yury Park Β· Chaofan Li Β· Sijie Hao Β· Gislane Almeida-Santos Β· Jinyi Tang Β· Harish Narasimhan Β· Nicole A. Kirk Β· Valeria Molinary Β· Ying Li Β· Li Li Β· Bimal N. Desai Β· Peter Chen Β· Kwon-Sik Park Β· Anny Xiaobo Zhou Β· Jeffrey M. Sturek Β· Wei Chen Β· In Su Cheon Β· Jie Sun
Severe COVID-19 is associated with an increased subsequent risk of lung cancer. Viral pneumonia induces durable lung epigenetic imprinting that promotes tumor-supportive neutrophils and impairs T cell immunity, which is reversible with combined CXCR2 inhibition and PD-L1 blockade.
  •  
  • ↗️
There are no more articles
❌