❌

Normal view

Received — 15 September 2026 ⏭

LLM-Enhanced Dual-Branch Learning for Large-Scale Multi-Label Text Classification

✇cs.AI, q-bio.NC updates on arXiv.org
By: Hui Ye · Jing Zhang · Xiulong Yang · Rajshekhar Sunderraman
14 September 2026 at 12:00
arXiv:2609.12915v1 Announce Type: cross Abstract: Large-scale multi-label text classification assigns a small subset of relevant labels to each document from a vocabulary containing thousands or tens of thousands of candidate labels. Although pretrained language models have improved semantic text representations, most representation-based approaches center their prediction pipelines on a primary encoder or combine auxiliary features within a single ranker. The complementarity between heterogeneous language models therefore remains insufficiently explored. We propose DualMLC, a dual-branch framework that processes the same document through an autoregressive decoder-only language model and a bidirectional encoder. Each branch maintains its own representation pathway and independently estimates relevance scores over the shared label space. DualMLC combines the two score vectors through late logit fusion, allowing shared evidence to reinforce relevant labels and branch-specific evidence to compensate for limitations in the other branch's representation. DualMLC achieves state-of-the-art results on three widely used large-scale multi-label text classification benchmarks. Ablation results further confirm that integrating the heterogeneous predictors produces stronger rankings than either branch alone. The source code is publicly available at https://github.com/huiyegit/DualMLC.
Received — 27 May 2026 ⏭

Break the Brake, Not the Wheel: Untargeted Jailbreak via Entropy Maximization

✇cs.AI, q-bio.NC updates on arXiv.org
By: Mengqi He · Xinyu Tian · Xin Shen · Shu Zou · Jinhong Ni · Zhaoyuan Yang · Weikang Li · Xuesong Li · Jing Zhang
26 May 2026 at 12:00
arXiv:2605.10764v2 Announce Type: replace-cross Abstract: Recent studies show that gradient-based universal image jailbreaks on vision-language models (VLMs) exhibit little or no cross-model transferability, casting doubt on the feasibility of transferable multimodal jailbreaks. We revisit this conclusion under a strictly untargeted threat model without enforcing a fixed prefix or response pattern. Our preliminary experiment reveals that refusal behavior concentrates at high-entropy tokens during autoregressive decoding, and non-refusal tokens already carry substantial probability mass among the top-ranked candidates before attack. Motivated by this finding, we propose Untargeted Jailbreak via Entropy Maximization(UJEM)-KL, a lightweight attack that maximizes entropy at these decision tokens to flip refusal outcomes, while stabilizing the remaining low-entropy positions to preserve output quality. Across three VLMs and two safety benchmarks, UJEM-KL achieves competitive white-box attack success rates and consistently improves transferability, while remaining effective under representative defenses. Our experimental results indicate that the limited transferability primarily stems from overly constrained optimization objectives.

A convergent uPAR-positive tumor ecosystem creates broad vulnerability to CAR T cell therapy

✇Cell
By: Zeda Zhang · Yu-Jui Ho · Xin Fang · Minseo Kim · Marguerite Li · Wei Luan · Clemens Hinterleitner · Sascha Haubner · Friederike Kogel · Edwin C. Pratt · Elif Ozcelik · José Reyes · Qingwen Jiang · Vincent W. Yang · Yu-Jung Chen · Tao Wang · Haijiao Liu · Haonan Hu · Xueqian Zhuang · Jin Park · Stella V. Paffenholz · Kevin Chen · Qing Chang · Amanda Kulick · Jing Zhang · Eric Chan · Eric Rosiek · Ning Fan · Riley A. Williams · Adam C. Wang · Samuel Freeman · Sha Tian · Gertrude Gunset · Andreina Garcia Angus · Nicolas Lecomte · Selma Yeni Yildirim · Emily Ali · Michelle Wu · Ileana C. Miranda · Cristina R. Antonescu · Olca Basturk · Zeynep Tarcan · Natasha Rekhtman · Christina Wilson · Merve Basar · Jennifer L. Sauter · Hikmat A. Al-Ahmadie · Samuel Singer · Christine Iacobuzio-Donahue · Charles Rudin · Elisa de Stanchina · Karuna Ganesh · Paul B. Romesser · Britta Weigelt · Dan Dongeun Huh · Josef Leibold · Judith Feucht · Ignacio Vázquez-García · Matthew J. Bott · Dmitriy Zamarin · Sohrab P. Shah · Jason S. Lewis · Corina Amor · Dana Pe’er · Jorge Mansilla-Soto · Av
30 March 2026 at 08:00
Synergizing with senescence-inducing therapies, uPAR CAR T cells eradicate primary and metastatic solid tumors with minimal myelodepletion by targeting both tumor cells and the stroma in preclinical models.
Received — 4 April 2026 ⏭

A Role-Based LLM Framework for Structured Information Extraction from Healthy Food Policies

✇cs.AI, q-bio.NC updates on arXiv.org
By: Congjing Zhang · Ruoxuan Bao · Jingyu Li · Yoav Ackerman · Shuai Huang · Yanfang Su
3 April 2026 at 12:00
arXiv:2604.01529v1 Announce Type: new Abstract: Current Large Language Model (LLM) approaches for information extraction (IE) in the healthy food policy domain are often hindered by various factors, including misinformation, specifically hallucinations, misclassifications, and omissions that result from the structural diversity and inconsistency of policy documents. To address these limitations, this study proposes a role-based LLM framework that automates the IE from unstructured policy data by assigning specialized roles: an LLM policy analyst for metadata and mechanism classification, an LLM legal strategy specialist for identifying complex legal approaches, and an LLM food system expert for categorizing food system stages. This framework mimics expert analysis workflows by incorporating structured domain knowledge, including explicit definitions of legal mechanisms and classification criteria, into role-specific prompts. We evaluate the framework using 608 healthy food policies from the Healthy Food Policy Project (HFPP) database, comparing its performance against zero-shot, few-shot, and chain-of-thought (CoT) baselines using Llama-3.3-70B. Our proposed framework demonstrates superior performance in complex reasoning tasks, offering a reliable and transparent methodology for automating IE from health policies.

Integrated proteomics and metabolomics analysis reveals mechanisms by which SFYC decoction regulates airway inflammation in asthma

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Yujing Zhang · Lei Liang · Xinxin Zhang · Yongbin Yan
1 April 2026 at 18:00

J Ethnopharmacol. 2026 Mar 30;365:121612. doi: 10.1016/j.jep.2026.121612. Online ahead of print.

ABSTRACT

ETHNOPHARMACOLOGICAL RELEVANCE: Airway inflammation is one of the primary pathological characteristics of asthma. Soufeng Yuchuan (SFYC) decoction, a compound formula derived from multiple traditional Chinese medicine prescriptions, is widely applied clinically and exhibits significant therapeutic efficacy against asthma. However, its anti-asthmatic mechanisms remain incompletely understood.

MATERIALS AND METHODS: Asthmatic rat models induced by ovalbumin (OVA) and ferroptosis models induced by erastin in BEAS-2B cells were established. Proteomics and metabolomics analyses were conducted on lung tissues and serum. Key ferroptosis-related targets (GPX4, SLC7A11/SLC3A2, GCLC, GSS, and VDAC2) were validated using Western blotting, RT-qPCR, and biochemical assays. The direct anti-ferroptosis effects of SFYC-containing serum were compared with ferrostatin-1 and blank serum in vitro.

RESULTS: Integrated omics analysis revealed that ferroptosis, glutathione metabolism, and ROS signaling pathways were the core targets modulated by SFYC. In vivo, SFYC significantly reduced airway inflammation and ROS accumulation, restored pulmonary GSH levels, upregulated the expression of GPX4, GCLC, GSS, SLC7A11, and SLC3A2, and downregulated VDAC2 expression (P < 0.05). In vitro, SFYC-containing serum effectively reversed erastin-induced lipid peroxidation, iron overload, GSH depletion, ROS elevation, and apoptosis in BEAS-2B cells, demonstrating comparable or superior efficacy to ferrostatin-1.

CONCLUSION: SFYC alleviates airway inflammation in asthma primarily by inhibiting ferroptosis. This study provides evidence that SFYC exerts anti-asthmatic effects, at least in part, via the regulation of ferroptosis pathways.

PMID:41921764 | DOI:10.1016/j.jep.2026.121612

Received — 26 March 2026 ⏭

Children's Intelligence Tests Pose Challenges for MLLMs? KidGym: A 2D Grid-Based Reasoning Benchmark for MLLMs

✇cs.AI, q-bio.NC updates on arXiv.org
By: Hengwei Ye · Yuanting Guan · Yuxuan Ge · Tianying Zhu · Zhenhan Guan · Yijia Zhong · Yijing Zhang · Han Zhang · Yingna Wu · Zheng Tian
25 March 2026 at 12:00
arXiv:2603.20209v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) combine the linguistic strengths of LLMs with the ability to process multimodal data, enbaling them to address a broader range of visual tasks. Because MLLMs aim at more general, human-like competence than language-only models, we take inspiration from the Wechsler Intelligence Scales - an established battery for evaluating children by decomposing intelligence into interpretable, testable abilities. We introduce KidGym, a comprehensive 2D grid-based benchmark for assessing five essential capabilities of MLLMs: Execution, Perception Reasoning, Learning, Memory and Planning. The benchmark comprises 12 unique tasks, each targeting at least one core capability, specifically designed to guage MLLMs' adaptability and developmental potential, mirroring the stages of children's cognitive growth. Additionally, our tasks encompass diverse scenarios and objects with randomly generated layouts, ensuring a more accurate and robust evluation of MLLM capabilities. KidGym is designed to be fully user-customizable and extensible, allowing researchers to create new evaluation scenarios and adjust difficuly levels to accommodate the rapidly growing MLLM community. Through the evaluation of state-of-the-art MLLMs using KidGym, we identified significant insights into model capabilities and revealed several limitations of current models. We release our benchmark at: https://bobo-ye.github.io/KidGym/.

β-hydroxybutyrate enhances the metabolic fitness of CAR T cells in cancer

✇Cell
By: Shan Liu · Puneeth Guruprasad · Ranjani Ramasubramanian · Bhoomi Madhu · Luca Paruzzo · Kecheng Han · Andre Kelly · Alexander Shestov · He N. Xu · Alberto Carturan · Chaoting Zhou · Kevin R. Amses · Amichay Afriat · Lev Litichevskiy · Jason Lin · Ezra Dubowitz · Neil Tangal · Jing Zhang · Alana McSween · Melody Tan · Federico Stella · Andrew Lee · Siena Nason · Xianxin Hua · Michael Schneider · Madeleine Sleeman · Yunlin Zhang · Giulia Gabrielli · Ziqi Yang · Raymone Pajarillo · Ruchi Patel · Guido Ghilardi · Vrutti Patel · Akshita Joshi · Shunzhou Jiang · Yanqing Jiang · Patrizia Porazzi · Julia C. Tchou · Brian Keith · Mingyao Li · Elise Chong · Stephen J. Schuster · Michael Milone · Joshua Rabinowitz · Roddy S. O’Connor · Christoph A. Thaiss · Maayan Levy · Marco Ruella
6 March 2026 at 08:00
β-hydroxybutyrate (BHB), the ketone body associated with a ketogenic diet, metabolically reprograms and fuels CAR T cells to achieve proliferation, cytokine production, and superior tumor control. These findings suggest that BHB supplementation may be a practical way to boost adoptive cancer immunotherapy.

Tuning the sensitivity of mechanosensory receptors through histidine scanning

✇Cell
By: Yuanhao Wang · Yuhan Wang · Wenjie Yuan · Mingyu Fan · Xiaojing Wang · Anhui Wang · Yanling Bao · Yajing Zhang · Jia Chi Tan · Jianglai Wang · Junshuang Liu · Tianqi Huang · Zixuan Han · Biling Pei · Lijuan Chen · Zhengxu Ren · Xueqing Wang · Lanxin Hu · Siqi Wu · Mengke Pang · Sifan Wang · Zihuan Yang · Jiaze Li · Delian Huang · Shuai Shao · Huairui Yuan · Ling Wu · Yinnian Feng · Penghui Zhou · Guohui Li · Bo Sun · Chenqi Xu · Nicholas R.J. Gascoigne · Xiang Zhao
18 February 2026 at 08:00
Histidine scanning represents a broadly applicable technique for the identification of critical interaction sites within TCRs and other mechanosensory receptors to enhance receptor signaling strength and augment therapeutic efficacy via the catch bond mechanism.
Received — 17 March 2026 ⏭

Evaluating VLMs' Spatial Reasoning Over Robot Motion: A Step Towards Robot Planning with Motion Preferences

✇cs.AI, q-bio.NC updates on arXiv.org
By: Wenxi Wu · Jingjing Zhang · Martim Brand\~ao
16 March 2026 at 12:00
arXiv:2603.13100v1 Announce Type: cross Abstract: Understanding user instructions and object spatial relations in surrounding environments is crucial for intelligent robot systems to assist humans in various tasks. The natural language and spatial reasoning capabilities of Vision-Language Models (VLMs) have the potential to enhance the generalization of robot planners on new tasks, objects, and motion specifications. While foundation models have been applied to task planning, it is still unclear the degree to which they have the capability of spatial reasoning required to enforce user preferences or constraints on motion, such as desired distances from objects, topological properties, or motion style preferences. In this paper, we evaluate the capability of four state-of-the-art VLMs at spatial reasoning over robot motion, using four different querying methods. Our results show that, with the highest-performing querying method, Qwen2.5-VL achieves 71.4% accuracy zero-shot and 75% on a smaller model after fine-tuning, and GPT-4o leads to lower performance. We evaluate two types of motion preferences (object-proximity and path-style), and we also analyze the trade-off between accuracy and computation cost in number of tokens. This work shows some promise in the potential of VLM integration with robot motion planning pipelines.
Received — 14 March 2026 ⏭
Received — 11 March 2026 ⏭

Detecting Fake Reviewer Groups in Dynamic Networks: An Adaptive Graph Learning Method

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jing Zhang · Ke Huang · Yao Zhang · Bin Guo · Zhiwen Yu
10 March 2026 at 12:00
arXiv:2603.08332v1 Announce Type: cross Abstract: The proliferation of fake reviews, often produced by organized groups, undermines consumer trust and fair competition on online platforms. These groups employ sophisticated strategies that evade traditional detection methods, particularly in cold-start scenarios involving newly launched products with sparse data. To address this, we propose the \underline{D}iversity- and \underline{S}imilarity-aware \underline{D}ynamic \underline{G}raph \underline{A}ttention-enhanced \underline{G}raph \underline{C}onvolutional \underline{N}etwork (DS-DGA-GCN), a new graph learning model for detecting fake reviewer groups. DS-DGA-GCN achieves robust detection since it focuses on the joint relationships among products, reviews, and reviewers by modeling product-review-reviewer networks. DS-DGA-GCN also achieves adaptive detection by integrating a Network Feature Scoring (NFS) system and a new dynamic graph attention mechanism. The NFS system quantifies network attributes, including neighbor diversity, network self-similarity, as a unified feature score. The dynamic graph attention mechanism improves the adaptability and computational efficiency by captures features related to temporal information, node importance, and global network structure. Extensive experiments conducted on two real-world datasets derived from Amazon and Xiaohongshu demonstrate that DS-DGA-GCN significantly outperforms state-of-the-art baselines, achieving accuracies of up to \textbf{89.8\% and 88.3\%}, respectively.

Arginine methylation-dependent stabilization of SUV39H1 promotes breast cancer growth

✇Oncogene - Issue - nature.com science feeds
By: Wei Zhao · Ge Wang · Peng Wang · Bo Ma · Bo Liu · Yenan Fu · Youzhi Tang · Xinwei Duan · Kunhao Zhou · Jing Zhang · Wei-Guo Zhu · Hongquan Zhang · Yu Yu
7 March 2026 at 08:00

Oncogene, Published online: 07 March 2026; doi:10.1038/s41388-026-03712-0

Arginine methylation-dependent stabilization of SUV39H1 promotes breast cancer growth
Received — 25 February 2026 ⏭

AdaWorldPolicy: World-Model-Driven Diffusion Policy with Online Adaptive Learning for Robotic Manipulation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Ge Yuan · Qiyuan Qiao · Jing Zhang · Dong Xu
24 February 2026 at 13:00
arXiv:2602.20057v1 Announce Type: cross Abstract: Effective robotic manipulation requires policies that can anticipate physical outcomes and adapt to real-world environments. Effective robotic manipulation requires policies that can anticipate physical outcomes and adapt to real-world environments. In this work, we introduce a unified framework, World-Model-Driven Diffusion Policy with Online Adaptive Learning (AdaWorldPolicy) to enhance robotic manipulation under dynamic conditions with minimal human involvement. Our core insight is that world models provide strong supervision signals, enabling online adaptive learning in dynamic environments, which can be complemented by force-torque feedback to mitigate dynamic force shifts. Our AdaWorldPolicy integrates a world model, an action expert, and a force predictor-all implemented as interconnected Flow Matching Diffusion Transformers (DiT). They are interconnected via the multi-modal self-attention layers, enabling deep feature exchange for joint learning while preserving their distinct modularity characteristics. We further propose a novel Online Adaptive Learning (AdaOL) strategy that dynamically switches between an Action Generation mode and a Future Imagination mode to drive reactive updates across all three modules. This creates a powerful closed-loop mechanism that adapts to both visual and physical domain shifts with minimal overhead. Across a suite of simulated and real-robot benchmarks, our AdaWorldPolicy achieves state-of-the-art performance, with dynamical adaptive capacity to out-of-distribution scenarios.
Received — 17 February 2026 ⏭

GeoEyes: On-Demand Visual Focusing for Evidence-Grounded Understanding of Ultra-High-Resolution Remote Sensing Imagery

✇cs.AI, q-bio.NC updates on arXiv.org
By: Fengxiang Wang · Mingshuo Chen · Yueying Li · Yajie Yang · Yifan Zhang · Long Lan · Xue Yang · Hongda Sun · Yulin Wang · Di Wang · Jun Song · Jing Zhang · Bo Du
17 February 2026 at 13:00
arXiv:2602.14201v1 Announce Type: cross Abstract: The "thinking-with-images" paradigm enables multimodal large language models (MLLMs) to actively explore visual scenes via zoom-in tools. This is essential for ultra-high-resolution (UHR) remote sensing VQA, where task-relevant cues are sparse and tiny. However, we observe a consistent failure mode in existing zoom-enabled MLLMs: Tool Usage Homogenization, where tool calls collapse into task-agnostic patterns, limiting effective evidence acquisition. To address this, we propose GeoEyes, a staged training framework consisting of (1) a cold-start SFT dataset, UHR Chain-of-Zoom (UHR-CoZ), which covers diverse zooming regimes, and (2) an agentic reinforcement learning method, AdaZoom-GRPO, that explicitly rewards evidence gain and answer improvement during zoom interactions. The resulting model learns on-demand zooming with proper stopping behavior and achieves substantial improvements on UHR remote sensing benchmarks, with 54.23% accuracy on XLRS-Bench.
There are no more articles
❌