❌

Normal view

Received — 15 September 2026 ⏭

Reinforcement Learning over Patient Trajectories for Clinical Reasoning in EHR Foundation Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yuxin Xiao · Sheng Zhang · Chandan Singh · Tristan Naumann · Hoifung Poon · Jianfeng Gao · Xiaodong Liu
14 September 2026 at 12:00
arXiv:2609.12277v1 Announce Type: cross Abstract: Electronic health record (EHR) foundation models trained on longitudinal patient trajectories have demonstrated strong performance across diverse clinical prediction tasks. However, their clinical reasoning capabilities remain constrained by next-token prediction on limited and incomplete EHR data. To address this, we propose a reinforcement learning (RL) fine-tuning framework that treats EHR foundation models as generative policies over patient trajectories. We formulate common clinical prediction problems (e.g., hospital readmission) as event-conditioned, time-windowed reasoning tasks. We then design time-aware, rollout-sensitive rewards to account for finite rollout lengths and temporally inconclusive outcomes. We find that RL fine-tuning consistently improves over pre-trained backbones and strong baselines. Notably, it enables smaller models to surpass larger pre-trained models in data-limited regimes and induces positive transfer across tasks. Further analysis shows that RL fine-tuned models generate trajectories with stronger structural and semantic alignment to ground truth and greater downstream utility.
Received — 10 September 2026 ⏭

Integrative Multi-Omics Analysis Identifies Thrombosis-Associated Molecular Features Linked to Germline Susceptibility and Immune Cell Communication in Gastric Cancer

✇Omics in Gastric
By: Xiaogang Lu · Lin Sun · Fujun Jin · Biao Cheng · Ying Huang · Yuzhu Tang · Xiaolong Nie · Feng Gao
2 September 2026 at 18:00

Chem Biol Drug Des. 2026 Sep;108(3):e70386. doi: 10.1111/cbdd.70386.

ABSTRACT

Emerging evidence indicates that coagulation-related molecular programs are associated with thrombosis, tumor progression, and molecular dysregulation in gastric cancer (GC). However, thrombosis-associated molecular features in GC and their potential links to inherited susceptibility remain insufficiently understood. Integrated analyses of transcriptomic data from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) datasets were performed to identify thrombosis-associated genes and establish a machine learning-based prognostic signature. Genome-wide association study (GWAS), expression quantitative trait loci (eQTL), transcriptome-wide association study (TWAS), and Mendelian randomization (MR) analyses were conducted to investigate susceptibility-associated transcriptional programs in GC. Functional assays were used to evaluate candidate genes associated with malignant phenotypes. Single-cell RNA sequencing (scRNA-seq) and cell-cell communication analyses were further performed to characterize cell-type-specific expression patterns and potential intercellular interactions. A total of 22 differentially expressed thrombosis-associated genes were identified, and a prognostic signature comprising 14 genes was established. The signature stratified patients into high- and low-risk groups and showed prognostic performance in both the training and validation cohorts. Integrative GWAS, eQTL, and TWAS analyses identified susceptibility-associated transcriptional programs that were positively correlated with the thrombosis-associated risk score. Silencing ACTN2 and CRYAB significantly reduced GC cell migration and invasion. scRNA-seq analysis revealed relatively high CRYAB expression in neutrophils, and CellChat analysis suggested potential neutrophil-B cell interactions involving COLLAGEN-related signaling. This integrative multi-omics study identified a thrombosis-associated molecular signature linked to prognosis and germline susceptibility-associated transcriptional programs in GC. ACTN2 and CRYAB may represent candidate genes associated with GC cell migration and invasion, while single-cell analysis suggested potential immune-related communication features.

PMID:42681916 | PMC:PMC13534880 | DOI:10.1111/cbdd.70386

Received — 27 May 2026 ⏭

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xiao Li · Xiang Zheng · Yifeng Gao · Xinyu Xia · Yixu Wang · Xin Wang · Ye Sun · Yunhan Zhao · Ming Wen · Jiayu Li · Zixing Chen · Xun Gong · Yi Liu · Yige Li · Yutao Wu · Cong Wang · Jun Sun · Yixin Cao · Zhineng Chen · Jingjing Chen · Tao Gui · Qi Zhang · Zuxuan Wu · Xipeng Qiu · Xuanjing Huang · Tiehua Zhang · Zhipeng Wei · Kun Wang · Xinfeng Li · Hanxun Huang · Sarah Erfani · James Bailey · Jianping Wang · Chaowei Xiao · Ran He · Bo Li · Xingjun Ma · Yu-Gang Jiang
26 May 2026 at 12:00
arXiv:2605.02900v2 Announce Type: replace-cross Abstract: Embodied Artificial Intelligence (Embodied AI) integrates perception, cognition, planning, and interaction into agents that operate in open-world, safety-critical environments. As these systems gain autonomy and enter domains such as transportation, healthcare, and industrial or assistive robotics, ensuring their safety becomes both technically challenging and socially indispensable. Unlike digital AI systems, embodied agents must act under uncertain sensing, incomplete knowledge, and dynamic human-robot interactions, where failures can directly lead to physical harm. This survey provides a comprehensive and structured review of safety research in embodied AI, examining attacks and defenses across the full embodied pipeline, from perception and cognition to planning, action and interaction, and agentic system. We introduce a multi-level taxonomy that unifies fragmented lines of work and connects embodied-specific safety findings with broader advances in vision, language, and multimodal foundation models. Our review synthesizes insights from over 500 papers spanning adversarial, backdoor, jailbreak, and hardware-level attacks; attack detection, safe training and robust inference; and risk-aware human-agent interaction. This analysis reveals several overlooked challenges, including the fragility of multimodal perception fusion, the instability of planning under jailbreak attacks, and the trustworthiness of human-agent interaction in open-ended scenarios. By organizing the field into a coherent framework and identifying critical research gaps, this survey provides a roadmap for building embodied agents that are not only capable and autonomous but also safe, robust, and reliable in real-world deployment.
Received — 8 April 2026 ⏭

Preserving Forgery Artifacts: AI-Generated Video Detection at Native Scale

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhengcen Li · Chenyang Jiang · Hang Zhao · Shiyang Zhou · Yunyang Mo · Feng Gao · Fan Yang · Qiben Shan · Shaocong Wu · Jingyong Su
7 April 2026 at 12:00
arXiv:2604.04634v1 Announce Type: cross Abstract: The rapid advancement of video generation models has enabled the creation of highly realistic synthetic media, raising significant societal concerns regarding the spread of misinformation. However, current detection methods suffer from critical limitations. They rely on preprocessing operations like fixed-resolution resizing and cropping. These operations not only discard subtle, high-frequency forgery traces but also cause spatial distortion and significant information loss. Furthermore, existing methods are often trained and evaluated on outdated datasets that fail to capture the sophistication of modern generative models. To address these challenges, we introduce a comprehensive dataset and a novel detection framework. First, we curate a large-scale dataset of over 140K videos from 15 state-of-the-art open-source and commercial generators, along with Magic Videos benchmark designed specifically for evaluating ultra-realistic synthetic content. In addition, we propose a novel detection framework built on the Qwen2.5-VL Vision Transformer, which operates natively at variable spatial resolutions and temporal durations. This native-scale approach effectively preserves the high-frequency artifacts and spatiotemporal inconsistencies typically lost during conventional preprocessing. Extensive experiments demonstrate that our method achieves superior performance across multiple benchmarks, underscoring the critical importance of native-scale processing and establishing a robust new baseline for AI-generated video detection.
Received — 11 March 2026 ⏭

SmartBench: Evaluating LLMs in Smart Homes with Anomalous Device States and Behavioral Contexts

✇cs.AI, q-bio.NC updates on arXiv.org
By: Qingsong Zou · Zhi Yan · Zhiyao Xu · Kuofeng Gao · Jingyu Xiao · Yong Jiang
10 March 2026 at 12:00
arXiv:2603.06636v1 Announce Type: cross Abstract: Due to the strong context-awareness capabilities demonstrated by large language models (LLMs), recent research has begun exploring their integration into smart home assistants to help users manage and adjust their living environments. While LLMs have been shown to effectively understand user needs and provide appropriate responses, most existing studies primarily focus on interpreting and executing user behaviors or instructions. However, a critical function of smart home assistants is the ability to detect when the home environment is in an anomalous state. This involves two key requirements: the LLM must accurately determine whether an anomalous condition is present, and provide either a clear explanation or actionable suggestions. To enhance the anomaly detection capabilities of next-generation LLM-based smart home assistants, we introduce SmartBench, which is the first smart home dataset designed for LLMs, containing both normal and anomalous device states as well as normal and anomalous device state transition contexts. We evaluate 13 mainstream LLMs on this benchmark. The experimental results show that most state-of-the-art models cannot achieve good anomaly detection performance. For example, Claude-Sonnet-4.5 achieves only 66.1% detection accuracy on context-independent anomaly categories, and performs even worse on context-dependent anomalies, with an accuracy of only 57.8%. More experimental results suggest that next-generation LLM-based smart home assistants are still far from being able to effectively detect and handle anomalous conditions in the smart home environment. Our dataset is publicly available at https://github.com/horizonsinzqs/SmartBench.
Received — 5 March 2026 ⏭

PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents

✇cs.AI, q-bio.NC updates on arXiv.org
By: Ke Yang · Zixi Chen · Xuan He · Jize Jiang · Michel Galley · Chenglong Wang · Jianfeng Gao · Jiawei Han · ChengXiang Zhai
5 March 2026 at 13:00
arXiv:2603.03296v1 Announce Type: cross Abstract: Long-term memory is essential for large language model (LLM) agents operating in complex environments, yet existing memory designs are either task-specific and non-transferable, or task-agnostic but less effective due to low task-relevance and context explosion from raw memory retrieval. We propose PlugMem, a task-agnostic plugin memory module that can be attached to arbitrary LLM agents without task-specific redesign. Motivated by the fact that decision-relevant information is concentrated as abstract knowledge rather than raw experience, we draw on cognitive science to structure episodic memories into a compact, extensible knowledge-centric memory graph that explicitly represents propositional and prescriptive knowledge. This representation enables efficient memory retrieval and reasoning over task-relevant knowledge, rather than verbose raw trajectories, and departs from other graph-based methods like GraphRAG by treating knowledge as the unit of memory access and organization instead of entities or text chunks. We evaluate PlugMem unchanged across three heterogeneous benchmarks (long-horizon conversational question answering, multi-hop knowledge retrieval, and web agent tasks). The results show that PlugMem consistently outperforms task-agnostic baselines and exceeds task-specific memory designs, while also achieving the highest information density under a unified information-theoretic analysis. Code and data are available at https://github.com/TIMAN-group/PlugMem.

PROSPECT: Unified Streaming Vision-Language Navigation via Semantic--Spatial Fusion and Latent Predictive Representation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zehua Fan · Wenqi Lyu · Wenxuan Song · Linge Zhao · Yifei Yang · Xi Wang · Junjie He · Lida Huang · Haiyan Liu · Bingchuan Sun · Guangjun Bao · Xuanyao Mao · Liang Xu · Yan Wang · Feng Gao
5 March 2026 at 13:00
arXiv:2603.03739v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have advanced zero-shot end-to-end Vision-Language Navigation (VLN), yet robust navigation requires not only semantic understanding but also predictive modeling of environment dynamics and spatial structure. We propose PROSPECT, a unified streaming navigation agent that couples a streaming Vision-Language-Action (VLA) policy with latent predictive representation learning. PROSPECT uses CUT3R as a streaming 3D foundation spatial encoder to produce long-context, absolute-scale spatial features, and fuses them with SigLIP semantic features via cross-attention. During training, we introduce learnable stream query tokens that query the streaming context and predict next-step 2D and 3D latent features (rather than pixels or explicit modalities), supervised in the latent spaces of frozen SigLIP and CUT3R teachers. The predictive branch shapes internal representations without inference overhead. Experiments on VLN-CE benchmarks and real-robot deployment demonstrate state-of-the-art performance and improved long-horizon robustness under diverse lighting. We will release code for the community soon.
Received — 25 February 2026 ⏭

MolReasoner: Toward Effective and Interpretable Reasoning for Molecular LLMs

✇cs.AI, q-bio.NC updates on arXiv.org
By: Guojiang Zhao · Zixiang Lu · Yutang Ge · Sihang Li · Zheng Cheng · Haitao Lin · Lirong Wu · Hanchen Xia · Hengxing Cai · Wentao Guo · Hongshuai Wang · Mingjun Xu · Siyu Zhu · Guolin Ke · Linfeng Zhang · Zhifeng Gao
24 February 2026 at 13:00
arXiv:2508.02066v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have shown impressive performance across various domains, but their ability to perform molecular reasoning remains underexplored. Existing methods mostly rely on general-purpose prompting, which lacks domain-specific molecular semantics, or fine-tuning, which faces challenges in interpretability and reasoning depth, often leading to structural and textual hallucinations. To address these issues, we introduce MolReasoner, a two-stage framework that transitions LLMs from memorization to high-fidelity chemical reasoning. In the Mol-SFT stage, knowledge-enhanced Chain-of-Thought (CoT) data provides a strong foundation, while the Mol-RL stage refines reasoning using a novel, task-adaptive reward system to mitigate hallucinations. Extensive evaluations demonstrate that MolReasoner significantly outperforms a wide range of strong baselines in both molecule generation and captioning tasks. Further analyses highlight the framework's synergistic design and its ability to produce more interpretable outputs. Our work presents a principled and effective new approach for advancing high-fidelity molecular reasoning.
Received — 17 February 2026 ⏭

A Deployment-Friendly Foundational Framework for Efficient Computational Pathology

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yu Cai · Cheng Jin · Jiabo Ma · Fengtao Zhou · Yingxue Xu · Zhengrui Guo · Yihui Wang · Zhengyu Zhang · Ling Liang · Yonghao Tan · Pingcheng Dong · Du Cai · On Ki Tang · Chenglong Zhao · Xi Wang · Can Yang · Yali Xu · Jing Cui · Zhenhui Li · Ronald Cheong Kin Chan · Yueping Liu · Feng Gao · Xiuming Zhang · Li Liang · Hao Chen · Kwang-Ting Cheng
17 February 2026 at 13:00
arXiv:2602.14010v1 Announce Type: cross Abstract: Pathology foundation models (PFMs) have enabled robust generalization in computational pathology through large-scale datasets and expansive architectures, but their substantial computational cost, particularly for gigapixel whole slide images, limits clinical accessibility and scalability. Here, we present LitePath, a deployment-friendly foundational framework designed to mitigate model over-parameterization and patch level redundancy. LitePath integrates LiteFM, a compact model distilled from three large PFMs (Virchow2, H-Optimus-1 and UNI2) using 190 million patches, and the Adaptive Patch Selector (APS), a lightweight component for task-specific patch selection. The framework reduces model parameters by 28x and lowers FLOPs by 403.5x relative to Virchow2, enabling deployment on low-power edge hardware such as the NVIDIA Jetson Orin Nano Super. On this device, LitePath processes 208 slides per hour, 104.5x faster than Virchow2, and consumes 0.36 kWh per 3,000 slides, 171x lower than Virchow2 on an RTX3090 GPU. We validated accuracy using 37 cohorts across four organs and 26 tasks (26 internal, 9 external, and 2 prospective), comprising 15,672 slides from 9,808 patients disjoint from the pretraining data. LitePath ranks second among 19 evaluated models and outperforms larger models including H-Optimus-1, mSTAR, UNI2 and GPFM, while retaining 99.71% of the AUC of Virchow2 on average. To quantify the balance between accuracy and efficiency, we propose the Deployability Score (D-Score), defined as the weighted geometric mean of normalized AUC and normalized FLOP, where LitePath achieves the highest value, surpassing Virchow2 by 10.64%. These results demonstrate that LitePath enables rapid, cost-effective and energy-efficient pathology image analysis on accessible hardware while maintaining accuracy comparable to state-of-the-art PFMs and reducing the carbon footprint of AI deployment.

RRPO: Robust Reward Policy Optimization for LLM-based Emotional TTS

✇cs.AI, q-bio.NC updates on arXiv.org
By: Cong Wang · Changfeng Gao · Yang Xiang · Zhihao Du · Keyu An · Han Zhao · Qian Chen · Xiangang Li · Yingming Gao · Ya Li
17 February 2026 at 13:00
arXiv:2512.04552v3 Announce Type: replace-cross Abstract: Differentiable reinforcement learning (RL) frameworks like DiffRO offer a powerful approach for controllable text-to-speech (TTS), but are vulnerable to reward hacking, particularly for nuanced tasks like emotion control. The policy model can exploit a vanilla Reward Model (RM) by generating acoustic artifacts to achieve spurious rewards, but at the cost of degrading perceptual quality. To address this, we propose Robust Reward Policy Optimization (RRPO), a novel framework that employs a hybrid regularization scheme. This scheme develops a robust RM whose reward signal is more reliably aligned with human perception, compelling the policy to abandon detrimental shortcuts and instead learn the complex features of genuine emotions. Our ablation study confirms the enhanced robustness of our RM, as evidenced by its strong cross-lingual generalization. The subjective evaluation demonstrates that this robust RM effectively mitigates reward hacking, leading to significant improvements in both emotional expressiveness and naturalness over all baselines. Demo page: https://lrwinr.github.io/RRPO-CosyVoice.
There are no more articles
❌