❌

Reading view

↗️

Transformer-Based Multitask Framework Integrating Habitat and Deep Learning for Predicting Early Disease Control and Survival in Immunotherapy-Treated Hepatocellular Carcinoma

✇(Multiomics OR Omics) AND (Pancreatic)
By: Xiaona Fu · Yusheng Guo · Bingxin Gong · Jie Lou · Ning Wang · Xuejun Chen · Hongtao Hu · Rundong Wang · Xiaofang Guo · Shanmei Li · Yangyang Xie · Shichao Long · Mengsi Li · Shubo Pan · Wen Shen · Zhaogang Zhang · Zifang Song · Pengchen Liang · Xiaoyun Liang · Peng Sun · Guilin Zhang · Shanshan Jiang · Jinxiang Zhang · Lian Yang

Adv Sci (Weinh). 2026 Sep 27:e78005. doi: 10.1002/advs.78005. Online ahead of print.

ABSTRACT

Hepatocellular carcinoma (HCC) patients show heterogeneous responses to immune checkpoint inhibitors (ICIs). This study developed ECOS-Net, a transformer-based multitask network integrating CT-derived habitat and 2.5-dimensional (2.5D) deep learning features for simultaneously predicting early disease control (DC) and overall survival (OS). Of 1,234 patients with HCC enrolled from eight institutions and public databases, 832 ICI-treated patients were used for model development. ECOS-Net fused features using multi-head attention and generated early DC probabilities and OS risk scores. ECOS-DC achieved AUCs of 0.836, 0.822, and 0.817 in training, internal validation, and external test sets, outperforming clinical models (all p values < 0.05). ECOS-OS yielded C-indices of 0.730, 0.722, and 0.720, respectively. Integrated models also showed favorable external performance (early DC AUC: 0.825; OS C-index: 0.741). Patients with higher ECOS-DC probabilities had a higher likelihood of early DC, whereas those with higher ECOS-OS risk had shorter OS, with directionally consistent associations across most subgroups. Exploratory biological analyses suggested that the higher ECOS-DC probability and lower ECOS-OS risk groups were associated with immune-active tumor microenvironment features. Therefore, ECOS-Net shows potential as a non-invasive imaging-based risk stratification framework for simultaneously predicting early DC and OS in ICI-treated HCC patients.

PMID:42801546 | PMC:PMC13616327 | DOI:10.1002/advs.78005

  •  
  • ↗️
↗️

MUC13 promotes cisplatin resistance in intrahepatic cholangiocarcinoma through regulation by histone H3K18 lactylation

✇Cell Death Discovery nature.com science feeds
By: Zhijie Yin · Qingfu Lang · Jia Sun · Yinfan Wang · Chen Jia · Boxin Chen · Zhen Cui · Ze Wang · Wenjun Chen · Zejun Luo · Ming Yang · Tiemin Pei

Cell Death Discovery, Published online: 01 September 2026; doi:10.1038/s41420-026-03324-3

MUC13 promotes cisplatin resistance in intrahepatic cholangiocarcinoma through regulation by histone H3K18 lactylation
  •  
  • ↗️
↗️

Targeting peripheral 5-HT2AR enhances antitumor immunity in colorectal cancer

✇Cell
By: YaTing Wen · LingJie Tang · WenWen Duan · QingFei Ren · YangYue Ni · ShiYang Chen · Jun Chen · Lei Yang · Huan Wang · Yuan Chen · YunZhe Zheng · XingChao Pan · Hui Du · MengWen Huang · An Zeng · Zhaocai Zhou · ZhiGang Zhang · HongBin Ji · GaoXiang Ge · Yi Arial Zeng · Wei Zhang · ShiHui Wang · JianJun Cheng · Sheng Wang · JianFeng Chen
By selectively targeting peripheral 5-HT2AR without inducing psychedelic effects, a non-brain-penetrant agonist boosts antitumor CD8+ T cell immunity and improves immunotherapy responses in preclinical models of colorectal cancer.
  •  
  • ↗️
↗️

Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xiaodong Lu · Xiaohan Wang · Jiajun Chai · Guojun Yin · Wei Lin · Zhijun Chen · Yu Luo · Fuzhen Zhuang · Yikun Ban · Deqing Wang
arXiv:2602.08499v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is an effective paradigm for improving the reasoning capabilities of large language models. However, existing RLVR methods utilize rollouts in an indiscriminate and short-horizon manner: responses of heterogeneous quality within each prompt are treated uniformly, and historical rollouts are discarded after a single use. This leads to noisy supervision, poor sample efficiency, and suboptimal policy updates. We address these issues by formulating rollout scheduling in RLVR as a contextual bandit problem and proposing a unified neural scheduling framework that adaptively selects high-value rollouts throughout training. Each rollout is treated as an arm whose reward is defined by the induced performance gain between consecutive optimization steps. The resulting scheduler supports both noise-aware intra-group selection and adaptive global reuse of historical rollouts within a single principled framework. We provide theoretical justification by deriving sublinear regret bounds and showing that enlarging the rollout buffer improves the achievable performance upper bound. Experiments on six mathematical reasoning benchmarks demonstrate consistent gains in performance and training efficiency across multiple RLVR optimization methods.
  •  
  • ↗️
↗️

JAEGER: Joint 3D Audio-Visual Grounding and Reasoning in Simulated Physical Environments

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhan Liu · Changli Tang · Yuxin Wang · Zhiyuan Zhu · Youjun Chen · Yiwen Shao · Tianzi Wang · Lei Ke · Zengrui Jin · Chao Zhang
arXiv:2602.18527v2 Announce Type: replace-cross Abstract: Current audio-visual large language models (AV-LLMs) are predominantly restricted to 2D perception, relying on RGB video and monaural audio. This design choice introduces a fundamental dimensionality mismatch that precludes reliable source localization and spatial reasoning in complex 3D environments. We address this limitation by presenting JAEGER, a framework that extends AV-LLMs to 3D space, to enable joint spatial grounding and reasoning through the integration of RGB-D observations and multi-channel first-order ambisonics. A core contribution of our work is the neural intensity vector (Neural IV), a learned spatial audio representation that encodes robust directional cues to enhance direction-of-arrival estimation, even in adverse acoustic scenarios with overlapping sources. To facilitate large-scale training and systematic evaluation, we propose SpatialSceneQA, a benchmark of 61k instruction-tuning samples curated from simulated physical environments. Extensive experiments demonstrate that our approach consistently surpasses 2D-centric baselines across diverse spatial perception and reasoning tasks, underscoring the necessity of explicit 3D modelling for advancing AI in physical environments. Our source code, pre-trained model checkpoints, and datasets are available at https://github.com/liuzhan22/JAEGER.
  •  
  • ↗️
↗️

L-Drive: Beyond a Single Mapping-Latent Context Drives Time Series Forecasting

✇cs.AI, q-bio.NC updates on arXiv.org
By: Fan Zhang · Shijun Chen · Hua Wang
arXiv:2605.17730v2 Announce Type: replace-cross Abstract: Mainstream methods for multivariate time-series forecasting largely follow the Direct-Mapping paradigm. They learn a unified mapping from history to the future in the observation space to fit value-level dependencies. However, real-world systems often undergo distribution shifts and regime changes. In such cases, a unified mapping can exhibit response lag around turning points, causing error accumulation within the switching window and reducing forecasting reliability. To address this issue, we propose L-Drive, a change-aware forecasting framework. L-Drive introduces a Latent-Context, to explicitly characterize high-level dynamics evolving over time, and uses gating to modulate increment representations. This provides more timely change cues and improves adaptation to changing segments. In addition, it incorporates patch-shared relative positional basis functions to strengthen intra-segment structural modeling and reduce overfitting caused by absolute-position memorization. Extensive experiments validate the effectiveness of L-Drive and show a better overall trade-off between forecasting accuracy and computational efficiency.
  •  
  • ↗️
↗️

Multi-omics Analysis Reveals the Correlation of Gut Microbiota and Metabolites With Thalidomide Treatment for Chemotherapy-Induced Nausea and Vomiting in Small Cell Lung Cancer

✇Omics In Lung
By: Qiang-Guo Sun · Dan Zang · Yu Xin · Jia Cui · Xu Han · Jun Chen

Biotechnol J. 2026 Apr;21(4):e70228. doi: 10.1002/biot.70228.

ABSTRACT

Small cell lung cancer (SCLC) is a highly aggressive malignancy, and chemotherapy frequently causes nausea and vomiting, which can impair treatment tolerance. Because thalidomide (THD) has shown potential clinical benefit in alleviating nausea and anorexia, we investigated whether its effects might be associated with changes in gut microbial composition and metabolite profiles. Fecal samples were collected from patients with SCLC and categorized into THD-treated and control groups. Metagenomic sequencing and nontargeted metabolomic profiling were performed to characterize microbial composition and metabolic signatures. THD treatment was also associated with higher microbial alpha diversity and increased abundance of genera such as Eubacterium and Prevotella. Metabolomic analysis identified several differential metabolites, including hydrogenated MDI, becocalcidiol, β-octylglucoside, and azelaic acid. Collectively, these findings suggest that the gut microbiota-metabolite axis may be associated with the potential effects of THD on CINV and anorexia in patients with SCLC. The identified microbial taxa and metabolites may serve as candidate biomarkers or potential therapeutic targets, although further validation in larger studies is necessary.

PMID:41994961 | PMC:PMC13088213 | DOI:10.1002/biot.70228

  •  
  • ↗️
↗️

Mummified early Permian reptile reveals ancient amniote breathing apparatus

✇Nature - Issue - nature.com science feeds
By: Robert R. Reisz · Ethan D. Mooney · Tea Maho · David Mazierski · Xu Chu · Joseph J. Bevitt · Yao-Chang Lee · Pei-Yu Huang · Xiaobo Li · Jun Chen

Nature, Published online: 08 April 2026; doi:10.1038/s41586-026-10307-y

A mummified fossil of the early Permian reptile Captorhinus reveals the potential ancestral amniote breathing mechanism and its impact on terrestrial vertebrate evolution.
  •  
  • ↗️
↗️

LightThinker++: From Reasoning Compression to Memory Management

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yuqi Zhu · Jintian Zhang · Zhenjie Wan · Yujie Luo · Shuofei Qiao · Zhengke Gui · Da Zheng · Lei Liang · Huajun Chen · Ningyu Zhang
arXiv:2604.03679v1 Announce Type: cross Abstract: Large language models (LLMs) excel at complex reasoning, yet their efficiency is limited by the surging cognitive overhead of long thought traces. In this paper, we propose LightThinker, a method that enables LLMs to dynamically compress intermediate thoughts into compact semantic representations. However, static compression often struggles with complex reasoning where the irreversible loss of intermediate details can lead to logical bottlenecks. To address this, we evolve the framework into LightThinker++, introducing Explicit Adaptive Memory Management. This paradigm shifts to behavioral-level management by incorporating explicit memory primitives, supported by a specialized trajectory synthesis pipeline to train purposeful memory scheduling. Extensive experiments demonstrate the framework's versatility across three dimensions. (1) LightThinker reduces peak token usage by 70% and inference time by 26% with minimal accuracy loss. (2) In standard reasoning, LightThinker++ slashes peak token usage by 69.9% while yielding a +2.42% accuracy gain under the same context budget for maximum performance. (3) Most notably, in long-horizon agentic tasks, it maintains a stable footprint beyond 80 rounds (a 60%-70% reduction), achieving an average performance gain of 14.8% across different complex scenarios. Overall, our work provides a scalable direction for sustaining deep LLM reasoning over extended horizons with minimal overhead.
  •  
  • ↗️
↗️

SRSF10 promotes cisplatin resistance in bladder cancer via BIN1 Exon 12 retention and ANXA1 activation

✇Oncogene - Issue - nature.com science feeds
By: Mengqing Xiao · Yanni Ma · Ganghua Zhang · Guanjun Chen · Yuxing Zhu · Xiaoming Liu · Yaxin Cheng · Ziyang Feng · Ke Cao

Oncogene, Published online: 06 April 2026; doi:10.1038/s41388-026-03735-7

SRSF10 promotes cisplatin resistance in bladder cancer via BIN1 Exon 12 retention and ANXA1 activation
  •  
  • ↗️
↗️

Towards causal validation and clinical translation of the PAK2-fibroblast axis in idiopathic pulmonary fibrosis

✇Omics In Lung
By: Man Sun · Dan Zang · Jun Chen

Eur Respir J. 2026 Mar 19;67(3):2502148. doi: 10.1183/13993003.02148-2025. Print 2026 Mar.

ABSTRACT

While PAK2 marks fibrotic fibroblast niches in IPF, causal validation, multicellular contextualisation and lung-targeted delivery are required before clinical translation. Spatial omics should guide not only discovery but also therapeutic decision-making. https://bit.ly/4hqQS3F

PMID:41856567 | PMC:PMC13000392 | DOI:10.1183/13993003.02148-2025

  •  
  • ↗️
↗️

FastDSAC: Unlocking the Potential of Maximum Entropy RL in High-Dimensional Humanoid Control

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jun Xue · Junze Wang · Xinming Zhang · Shanze Wang · Yanjun Chen · Wei Zhang
arXiv:2603.12612v1 Announce Type: cross Abstract: Scaling Maximum Entropy Reinforcement Learning (RL) to high-dimensional humanoid control remains a formidable challenge, as the ``curse of dimensionality'' induces severe exploration inefficiency and training instability in expansive action spaces. Consequently, recent high-throughput paradigms have largely converged on deterministic policy gradients combined with massive parallel simulation. We challenge this compromise with FastDSAC, a framework that effectively unlocks the potential of maximum entropy stochastic policies for complex continuous control. We introduce Dimension-wise Entropy Modulation (DEM) to dynamically redistribute the exploration budget and enforce diversity, alongside a continuous distributional critic tailored to ensure value fidelity and mitigate high-dimensional value overestimation. Extensive evaluations on HumanoidBench and other continuous control tasks demonstrate that rigorously designed stochastic policies can consistently match or outperform deterministic baselines, achieving notable gains of 180\% and 400\% on the challenging \textit{Basketball} and \textit{Balance Hard} tasks.
  •  
  • ↗️
↗️

Scaling Generalist Data-Analytic Agents

✇cs.AI, q-bio.NC updates on arXiv.org
By: Shuofei Qiao · Yanqiu Zhao · Zhisong Qiu · Xiaobin Wang · Jintian Zhang · Zhao Bin · Ningyu Zhang · Yong Jiang · Pengjun Xie · Fei Huang · Huajun Chen
arXiv:2509.25084v3 Announce Type: replace-cross Abstract: Data-analytic agents are emerging as a key catalyst for automated scientific discovery and for the vision of Innovating AI. Current approaches, however, rely heavily on prompt engineering over proprietary models, while open-source models struggle to face diverse-format, large-scale data files and long-horizon, multi-step reasoning that real-world analytics demands. This paper introduces DataMind, a scalable data synthesis and agent training recipe designed to build generalist data-analytic agents. DataMind tackles three key challenges in building open-source data-analytic agents, including insufficient data resources, improper training strategy, and unstable code-based multi-turn rollout. Concretely, DataMind applies 1) a fine-grained task taxonomy and a recursive easy-to-hard task composition mechanism to increase the diversity and difficulty of synthesized queries; 2) a knowledge-augmented trajectory sampling strategy followed by model-based and rule-based filtering; 3) a dynamically adjustable training objective combining both SFT and RL losses; 4) a memory-frugal and stable code-based multi-turn rollout framework. Built on DataMind, we curate DataMind-12K, a high-quality trajectory set spanning diverse domains, task categories, and data file formats for data-analytic tasks. Trained on DataMind-12K, our DataMind-14B achieves state-of-the-art with an average score of 71.16% on multiple data analysis benchmarks, outperforming the strongest proprietary baselines DeepSeek-V3.1 and GPT-5. Our DataMind-7B also performs best among all open-source models with a score of 68.10%. We also incorporate some empirical insights gained from our exploratory trials into the analysis experiments, aiming to provide actionable insights about agentic training for the community. We will release DataMind-12K and DataMind-7B,14B for the community's future research.
  •  
  • ↗️
↗️

Contextual Counterfactual Credit Assignment for Multi-Agent Reinforcement Learning in LLM Collaboration

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yanjun Chen · Yirong Sun · Hanlin Wang · Xinming Zhang · Xiaoyu Shen · Wenjie Li · Wei Zhang
arXiv:2603.06859v1 Announce Type: cross Abstract: Cooperative multi-agent reinforcement learning (MARL) systems powered by large language models (LLMs) are frequently optimized via sparse terminal-only feedback. This shared signal entangles upstream decisions, obstructing accurate decision-level credit assignment. To address this trajectory-level diffusion, we introduce Contextual Counterfactual Credit Assignment (\textbf{\texttt{C3}}). Instead of distributing rewards across an entire episode, \textbf{\texttt{C3}} isolates the causal impact of individual messages by freezing the exact transcript-derived context, evaluating context-matched alternatives via fixed-continuation replay, and applying a leave-one-out (LOO) baseline. This localized intervention extracts unbiased, low-variance marginal advantages for standard policy-gradient optimization. Evaluated across five mathematical and coding benchmarks under matched budgets, \textbf{\texttt{C3}} improves terminal performance over established baselines. Mechanistic diagnostics further show that these gains are accompanied by higher credit fidelity, lower contextual variance, and stronger inter-agent causal dependence. Our code is available at https://github.com/EIT-EAST-Lab/C3.
  •  
  • ↗️
↗️

Multimodal Laryngoscopic Video Analysis for Assisted Diagnosis of Vocal Fold Paralysis

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yucong Zhang · Xin Zou · Jinshan Yang · Wenjun Chen · Juan Liu · Faya Liang · Ming Li
arXiv:2409.03597v4 Announce Type: replace-cross Abstract: This paper presents the Multimodal Laryngoscopic Video Analyzing System (MLVAS), a novel system that leverages both audio and video data to automatically extract key video segments and metrics from raw laryngeal videostroboscopic videos for assisted clinical assessment. The system integrates video-based glottis detection with an audio keyword spotting method to analyze both video and audio data, identifying patient vocalizations and refining video highlights to ensure optimal inspection of vocal fold movements. Beyond key video segment extraction from the raw laryngeal videos, MLVAS is able to generate effective audio and visual features for Vocal Fold Paralysis (VFP) detection. Pre-trained audio encoders are utilized to encode the patient voice to get the audio features. Visual features are generated by measuring the angle deviation of both the left and right vocal folds to the estimated glottal midline on the segmented glottis masks. To get better masks, we introduce a diffusion-based refinement that follows traditional U-Net segmentation to reduce false positives. We conducted several ablation studies to demonstrate the effectiveness of each module and modalities in the proposed MLVAS. The experimental results on a public segmentation dataset show the effectiveness of our proposed segmentation module. In addition, unilateral VFP classification results on a real-world clinic dataset demonstrate MLVAS's ability of providing reliable and objective metrics as well as visualization for assisted clinical diagnosis.
  •  
  • ↗️
↗️

Accelerating Robotic Reinforcement Learning with Agent Guidance

✇cs.AI, q-bio.NC updates on arXiv.org
By: Haojun Chen · Zili Zou · Chengdong Ma · Yaoxiang Pu · Haotong Zhang · Yuanpei Chen · Yaodong Yang
arXiv:2602.11978v2 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) offers a powerful paradigm for autonomous robots to master generalist manipulation skills through trial-and-error. However, its real-world application is stifled by low sample efficiency. Recent Human-in-the-Loop (HIL) methods accelerate training by using human corrections, yet this approach faces a scalability barrier. Reliance on human supervisors imposes a 1:1 supervision ratio that limits scalability, suffers from operator fatigue over extended sessions, and introduces high variance due to inconsistent human proficiency. We present Agent-guided Policy Search (AGPS), a framework that automates the training pipeline by replacing human supervisors with a multimodal agent. Our key insight is that the agent can be viewed as a semantic world model, injecting intrinsic value priors to structure physical exploration. By using tools, the agent provides precise guidance via corrective waypoints and spatial constraints for exploration pruning. We validate our approach on three tasks, ranging from precision insertion to deformable object manipulation. Results demonstrate that AGPS outperforms HIL methods in sample efficiency. This automates the supervision pipeline, unlocking the path to labor-free and scalable robot learning. Project website: https://agps-rl.github.io/agps/.
  •  
  • ↗️
↗️

How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities

✇cs.AI, q-bio.NC updates on arXiv.org
By: Ziwen Xu · Kewei Xu · Haoming Xu · Haiwen Hong · Longtao Huang · Hui Xue · Ningyu Zhang · Yongliang Shen · Guozhou Zheng · Huajun Chen · Shumin Deng
arXiv:2603.02578v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly deployed in socially sensitive domains, yet their unpredictable behaviors, ranging from misaligned intent to inconsistent personality, pose significant risks. We introduce SteerEval, a hierarchical benchmark for evaluating LLM controllability across three domains: language features, sentiment, and personality. Each domain is structured into three specification levels: L1 (what to express), L2 (how to express), and L3 (how to instantiate), connecting high-level behavioral intent to concrete textual output. Using SteerEval, we systematically evaluate contemporary steering methods, revealing that control often degrades at finer-grained levels. Our benchmark offers a principled and interpretable framework for safe and controllable LLM behavior, serving as a foundation for future research.
  •  
  • ↗️
↗️

JAEGER: Joint 3D Audio-Visual Grounding and Reasoning in Simulated Physical Environments

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhan Liu · Changli Tang · Yuxin Wang · Zhiyuan Zhu · Youjun Chen · Yiwen Shao · Tianzi Wang · Lei Ke · Zengrui Jin · Chao Zhang
arXiv:2602.18527v1 Announce Type: cross Abstract: Current audio-visual large language models (AV-LLMs) are predominantly restricted to 2D perception, relying on RGB video and monaural audio. This design choice introduces a fundamental dimensionality mismatch that precludes reliable source localization and spatial reasoning in complex 3D environments. We address this limitation by presenting JAEGER, a framework that extends AV-LLMs to 3D space, to enable joint spatial grounding and reasoning through the integration of RGB-D observations and multi-channel first-order ambisonics. A core contribution of our work is the neural intensity vector (Neural IV), a learned spatial audio representation that encodes robust directional cues to enhance direction-of-arrival estimation, even in adverse acoustic scenarios with overlapping sources. To facilitate large-scale training and systematic evaluation, we propose SpatialSceneQA, a benchmark of 61k instruction-tuning samples curated from simulated physical environments. Extensive experiments demonstrate that our approach consistently surpasses 2D-centric baselines across diverse spatial perception and reasoning tasks, underscoring the necessity of explicit 3D modelling for advancing AI in physical environments. Our source code, pre-trained model checkpoints and datasets will be released upon acceptance.
  •  
  • ↗️
❌