❌

Normal view

Received — 15 September 2026 ⏭

Multi-Omics-Enabled Precision Strategies for Overcoming CAR-T Therapy Limitations in Gastrointestinal Malignancies

✇Omics in Gastric
By: Ke Su · Zunyuan Tan · Han Li · Kai You · Susu Xiao · Haiqing Chen · Danyang Li · Xin Liu · Xinrui Du · Jiaxin Hu · Kun He · Yantian Xu · Jian Chen · Yunwei Han
10 September 2026 at 18:00

Biofactors. 2026 Sep-Oct;52(5):e70150. doi: 10.1002/biof.70150.

ABSTRACT

Gastrointestinal malignancies, including gastric cancer, colorectal cancer, hepatocellular carcinoma, and pancreatic ductal adenocarcinoma, remain major causes of cancer-related morbidity and mortality worldwide. Although chimeric antigen receptor T-cell (CAR-T) therapy has revolutionized the treatment of hematologic malignancies, its efficacy in gastrointestinal solid tumors remains limited by antigen heterogeneity, insufficient trafficking and infiltration, immunosuppressive tumor microenvironments, on-target off-tumor toxicity, and adaptive resistance. In this review, we summarize the current landscape of CAR-T therapy in gastric cancer, colorectal cancer, hepatocellular carcinoma, and pancreatic cancer, with a focus on representative target antigens and emerging biomarker strategies. We further discuss two major categories of biomarkers: target antigen-related biomarkers and conventional dynamic biomarkers, including serum tumor markers, cytokine changes, CAR-T expansion kinetics, and antigen-loss monitoring. In addition, we highlight how single-cell ribonucleic acid sequencing and spatial transcriptomics provide complementary insights into cellular states, immune exhaustion, stromal barriers, and spatially restricted immune exclusion. By integrating these multi-omics approaches with biomarker-guided patient stratification and next-generation CAR-T engineering, gastrointestinal solid tumor CAR-T therapy may evolve from empirical optimization toward mechanism-driven and precision-guided clinical translation.

PMID:42717494 | PMC:PMC13558850 | DOI:10.1002/biof.70150

Received — 13 September 2026 ⏭

Multi-Omics-Enabled Precision Strategies for Overcoming CAR-T Therapy Limitations in Gastrointestinal Malignancies

✇Omics in Hepatocellular
By: Ke Su · Zunyuan Tan · Han Li · Kai You · Susu Xiao · Haiqing Chen · Danyang Li · Xin Liu · Xinrui Du · Jiaxin Hu · Kun He · Yantian Xu · Jian Chen · Yunwei Han
10 September 2026 at 18:00

Biofactors. 2026 Sep-Oct;52(5):e70150. doi: 10.1002/biof.70150.

ABSTRACT

Gastrointestinal malignancies, including gastric cancer, colorectal cancer, hepatocellular carcinoma, and pancreatic ductal adenocarcinoma, remain major causes of cancer-related morbidity and mortality worldwide. Although chimeric antigen receptor T-cell (CAR-T) therapy has revolutionized the treatment of hematologic malignancies, its efficacy in gastrointestinal solid tumors remains limited by antigen heterogeneity, insufficient trafficking and infiltration, immunosuppressive tumor microenvironments, on-target off-tumor toxicity, and adaptive resistance. In this review, we summarize the current landscape of CAR-T therapy in gastric cancer, colorectal cancer, hepatocellular carcinoma, and pancreatic cancer, with a focus on representative target antigens and emerging biomarker strategies. We further discuss two major categories of biomarkers: target antigen-related biomarkers and conventional dynamic biomarkers, including serum tumor markers, cytokine changes, CAR-T expansion kinetics, and antigen-loss monitoring. In addition, we highlight how single-cell ribonucleic acid sequencing and spatial transcriptomics provide complementary insights into cellular states, immune exhaustion, stromal barriers, and spatially restricted immune exclusion. By integrating these multi-omics approaches with biomarker-guided patient stratification and next-generation CAR-T engineering, gastrointestinal solid tumor CAR-T therapy may evolve from empirical optimization toward mechanism-driven and precision-guided clinical translation.

PMID:42717494 | PMC:PMC13558850 | DOI:10.1002/biof.70150

Multi-Omics-Enabled Precision Strategies for Overcoming CAR-T Therapy Limitations in Gastrointestinal Malignancies

✇(Multiomics OR Omics) AND (Pancreatic)
By: Ke Su · Zunyuan Tan · Han Li · Kai You · Susu Xiao · Haiqing Chen · Danyang Li · Xin Liu · Xinrui Du · Jiaxin Hu · Kun He · Yantian Xu · Jian Chen · Yunwei Han
10 September 2026 at 18:00

Biofactors. 2026 Sep-Oct;52(5):e70150. doi: 10.1002/biof.70150.

ABSTRACT

Gastrointestinal malignancies, including gastric cancer, colorectal cancer, hepatocellular carcinoma, and pancreatic ductal adenocarcinoma, remain major causes of cancer-related morbidity and mortality worldwide. Although chimeric antigen receptor T-cell (CAR-T) therapy has revolutionized the treatment of hematologic malignancies, its efficacy in gastrointestinal solid tumors remains limited by antigen heterogeneity, insufficient trafficking and infiltration, immunosuppressive tumor microenvironments, on-target off-tumor toxicity, and adaptive resistance. In this review, we summarize the current landscape of CAR-T therapy in gastric cancer, colorectal cancer, hepatocellular carcinoma, and pancreatic cancer, with a focus on representative target antigens and emerging biomarker strategies. We further discuss two major categories of biomarkers: target antigen-related biomarkers and conventional dynamic biomarkers, including serum tumor markers, cytokine changes, CAR-T expansion kinetics, and antigen-loss monitoring. In addition, we highlight how single-cell ribonucleic acid sequencing and spatial transcriptomics provide complementary insights into cellular states, immune exhaustion, stromal barriers, and spatially restricted immune exclusion. By integrating these multi-omics approaches with biomarker-guided patient stratification and next-generation CAR-T engineering, gastrointestinal solid tumor CAR-T therapy may evolve from empirical optimization toward mechanism-driven and precision-guided clinical translation.

PMID:42717494 | PMC:PMC13558850 | DOI:10.1002/biof.70150

Received — 11 March 2026 ⏭

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.
There are no more articles
❌