❌

Normal view

Received — 6 April 2026 ⏭

Spliceosomal component SNRPE drives cell proliferation by regulating CTP synthase 1 mRNA splicing in ovarian cancer

✇Oncogene - Issue - nature.com science feeds
By: Yingying Pu · Zhongshao Chen · Qianqian Gao · Yanling Liu · Ning Yang · Yingwei Li · Beihua Kong
4 April 2026 at 08:00

Oncogene, Published online: 04 April 2026; doi:10.1038/s41388-026-03764-2

Spliceosomal component SNRPE drives cell proliferation by regulating CTP synthase 1 mRNA splicing in ovarian cancer

Multi-ancestry transcriptome prediction with functionally informed variants in TOPMed MESA improves performance of transcriptome-wide association studies

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Xiaowei Hu · Daniel S Araujo · Chachrit Khunsriraksakul · Lida Wang · Quan Sun · Jia Wen · Lingbo Zhou · Lynette Ekunwe · Leslie A Lange · Ethan M Lange · Stephen B Montgomery · Alexander P Reiner · Francois Aguet · Kristin G Ardlie · Tuuli Lappalainen · Christopher R Gignoux · Esteban G Burchard · Kent D Taylor · Xiuqing Guo · Jerome I Rotter · Stephen S Rich · Elaine Cornell · Peter Durda · Russell P Tracy · Yongmei Liu · W Craig Johnson · George P Papanicolaou · Minoli A Perera · Michael H Cho · Dajiang J Liu · Laura M Raffield · Yun Li · TOPMed Multi-Omics Working Group · Heather E Wheeler · Hae Kyung Im · Ani Manichaikul
3 April 2026 at 18:00

Am J Hum Genet. 2026 Apr 2;113(4):828-841. doi: 10.1016/j.ajhg.2026.03.008.

ABSTRACT

Reliable reference transcriptome prediction models are key to accurate multi-ancestry transcriptome-wide association studies (TWASs). We propose three methods leveraging functionally informed variants (FIVs) for transcriptome prediction models to improve multi-ancestry TWASs. We trained models on 1,287 multi-ancestry participants from the Trans-Omics for Precision Medicine (TOPMed) program Multi-Ethnic Study of Atherosclerosis (MESA) with RNA sequencing (RNA-seq) data from peripheral blood mononuclear cells (PBMCs). We validated models' prediction accuracy on two external independent datasets, Geuvadis and Jackson Heart Study. To test robustness of our methods for TWASs, we integrated models with three multi-ancestry GWASs from blood cell, lipid, and pulmonary function traits, respectively. Our methods presented similar prediction accuracy while using a smaller and functionally informed set of variants compared to the benchmark method, elastic net (EN). Overall, our methods achieved higher power and accuracy (with average improved accuracy of 24% over EN) for TWASs. However, no single proposed method outperformed all GWAS traits. To further improve TWAS performance, we propose an omnibus approach that aggregates TWAS summary statistics from our methods. The omnibus approach yielded the highest number of Bonferroni-significant TWAS genes for all GWAS traits, and it further improved TWAS power and accuracy for blood cell traits. Additionally, the omnibus approach detected some trait-relevant important genes that the EN missed. Our study demonstrates the value of including FIVs in multi-ancestry transcriptome prediction models for improving TWAS performance. Further, the observed TWAS improvement depends on the GWAS trait's relevance to the PBMCs used to build our transcriptome prediction models.

PMID:41932314 | DOI:10.1016/j.ajhg.2026.03.008

Received — 4 April 2026 ⏭

Multi-omics and experimental validation identify USP54 as a prognostic deubiquitinase promoting pancreatic ductal adenocarcinoma progression within the immune microenvironment

✇(Multiomics OR Omics) AND (Pancreatic)
By: Zibo Yuan · Zhiwei Yu · Qiuran Xu · Dongsheng Huang · Di Cui
3 April 2026 at 18:00

Front Immunol. 2026 Mar 18;17:1791707. doi: 10.3389/fimmu.2026.1791707. eCollection 2026.

ABSTRACT

BACKGROUND: Pancreatic ductal adenocarcinoma (PDAC) is a highly lethal malignancy with a complex tumor ecosystem that contributes to its progression. Deubiquitinases (DUBs) are vital regulators in cancer. However, the overall activity of DUBs and their role in driving PDAC progression within immune microenvironment remain largely unknown.

METHODS: We employed an integrative multi-omics strategy combining machine learning (ML) on bulk transcriptomic data, single-cell RNA sequencing and spatial transcriptomic profiling. We applied Coxnet and Fuzzy SVM for prognostic modeling, inferCNV for malignant cell identification, SCENIC for transcription factor regulon analysis, LIANA+ for inferring inter-cellular communication networks and cell2location for spatial deconvolution. USP54 expression was detected by real-time quantitative PCR, western blotting and immunohistochemistry. USP54 function was validated through in vitro and in vivo assays.

RESULTS: ML-based pathway analysis revealed post-translational modification as a major prognostic category, within which elevated DUBs activity emerged as an independent adverse prognostic factor. At the single-cell level, USP54 was upregulated along the trajectory of malignant ductal cells and correlated with an inflamed tumor microenvironment. Cell-cell communication analysis predicted signaling from monocytes/macrophages to tumor cells via the THBS1-integrin ligand-receptor pair. This immune-derived signaling potentially converged on KLF5-positive tumor cells, with KLF5 identified as a putative transcriptional activator of USP54. Spatial transcriptomics validated the co-localization of USP54 expression, elevated DUB activity, and KRAS signaling within specific tumor niches adjacent to THBS1-enriched immune regions. High USP54 expression was frequently observed in PDAC tissues and associated with poor patient survival. More importantly, in both BxPC-3 and PANC-1 cell lines, USP54 knockdown suppressed cell proliferation and metastasis, whereas its overexpression enhanced these malignant phenotypes. Subcutaneous xenograft growth and tail vein injection experiments validated these findings in vivo.

CONCLUSIONS: Our comprehensive multi-omics analysis and experimental validation identify the deubiquitinase USP54 as a novel promoter of PDAC progression within a spatially organized tumor-immune microenvironment. These findings suggest USP54 as both a candidate prognostic biomarker and a potential therapeutic target for this lethal malignancy.

PMID:41929495 | PMC:PMC13038871 | DOI:10.3389/fimmu.2026.1791707

Interpretable Machine Learning to Understand Wildfire Toxicity: Bridging Chemicals, Omics, and Toxicological Outcomes via Symbolic Regression with Novel Feature Scoring

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Jessie R Chappel · Yong Ho Kim · M Ian Gilmour · Erin S Baker · Ilona Jaspers · Timothy M Weigand · Julia E Rager
3 April 2026 at 18:00

Chem Res Toxicol. 2026 Apr 3. doi: 10.1021/acs.chemrestox.5c00440. Online ahead of print.

ABSTRACT

Wildfire smoke exposures are increasingly common, consisting of complex mixtures of gases and particulates known to cause diverse pulmonary health effects. While health outcomes are regularly studied, quantitative links between smoke chemical composition and toxicological outcomes remain poorly defined, limiting interpretation of wildfire smoke health risks. This study explores symbolic regression (SR) as an interpretable artificial intelligence/machine learning method to generate closed-form mathematical models linking chemical exposure to biological responses relevant to wildfire smoke. Prior to application on wildfire-relevant data sets, we benchmarked three Python-based SR packages on simulated data, assessing performance across varying noise levels and operator complexities. Insights from these simulation tests, such as the importance of including necessary operators, were incorporated when applying SR to lab-generated wildland fire exposure-toxicity data. This data set included chemical characterizations of biomass smoke exposures and corresponding pulmonary responses in female CD-1 mice (n = 60). Specifically, we evaluated the ability to predict a lung injury marker using (1) targeted measures of over 80 chemicals measured in smoke (RMSE = 17.57 mg/mL) and (2) lung tissue measures of hundreds of transcripts (RMSE = 15.12 mg/mL). Resulting error metrics were comparable to Random Forest and XGBoost models. To aid model interpretation, we developed directional ensemble contribution scores (DECS), a novel feature importance scoring method that quantifies the direction and magnitude of predictor contributions across top-performing models. Expert toxicologists also contributed to model prioritization, integrating a "biologists-in-the-loop" approach. Results highlighted polycyclic aromatic hydrocarbons as drivers of lung injury and methoxyphenols as suppressors. Transcriptomic analyses highlighted a small set of genes, which have roles in metabolism, cell proliferation, immune regulation, and oncogenic processes, with MYC proto-oncogene (Myc) showing the strongest association. Overall, this study demonstrates SR and associated DECS as practical, interpretable tools for modeling environmental mixtures, such as wildfire smoke, and their toxicological effects.

PMID:41928614 | DOI:10.1021/acs.chemrestox.5c00440

ClawSafety: "Safe" LLMs, Unsafe Agents

✇cs.AI, q-bio.NC updates on arXiv.org
By: Bowen Wei · Yunbei Zhang · Jinhao Pan · Kai Mei · Xiao Wang · Jihun Hamm · Ziwei Zhu · Yingqiang Ge
3 April 2026 at 12:00
arXiv:2604.01438v1 Announce Type: new Abstract: Personal AI agents like OpenClaw run with elevated privileges on users' local machines, where a single successful prompt injection can leak credentials, redirect financial transactions, or destroy files. This threat goes well beyond conventional text-level jailbreaks, yet existing safety evaluations fall short: most test models in isolated chat settings, rely on synthetic environments, and do not account for how the agent framework itself shapes safety outcomes. We introduce CLAWSAFETY, a benchmark of 120 adversarial test scenarios organized along three dimensions (harm domain, attack vector, and harmful action type) and grounded in realistic, high-privilege professional workspaces spanning software engineering, finance, healthcare, law, and DevOps. Each test case embeds adversarial content in one of three channels the agent encounters during normal work: workspace skill files, emails from trusted senders, and web pages. We evaluate five frontier LLMs as agent backbones, running 2,520 sandboxed trials across all configurations. Attack success rates (ASR) range from 40\% to 75\% across models and vary sharply by injection vector, with skill instructions (highest trust) consistently more dangerous than email or web content. Action-trace analysis reveals that the strongest model maintains hard boundaries against credential forwarding and destructive actions, while weaker models permit both. Cross-scaffold experiments on three agent frameworks further demonstrate that safety is not determined by the backbone model alone but depends on the full deployment stack, calling for safety evaluation that treats model and framework as joint variables.

ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement

✇cs.AI, q-bio.NC updates on arXiv.org
By: Difan Jiao · Qianfeng Wen · Blair Yang · Zhenwei Tang · Ashton Anderson
3 April 2026 at 12:00
arXiv:2604.01591v1 Announce Type: new Abstract: We introduce ThinkTwice, a simple two-phase framework that jointly optimizes LLMs to solve reasoning problems and refine the answers, based on Group Relative Policy Optimization (GRPO). In each pair of training steps, ThinkTwice first optimizes the model on solving reasoning problems, then optimizes it on refining its own solutions to the same problems, using the same binary correctness reward in both phases without correctness signals or critique annotations. Across five mathematical reasoning benchmarks and two model families including Qwen3-4B and Olmo3-7B, ThinkTwice substantially improves both reasoning and refinement performance over competitive online policy optimization baselines. Specifically, on Qwen3-4B, ThinkTwice outperforms GRPO on AIME by 5 percentage points before refinement and by 11.5 points after one self-refinement step, measured by pass@4. Analysis of the training dynamics of ThinkTwice reveals an implicit rectify-then-fortify curriculum: refinement predominantly corrects errors early in training and naturally shifts toward preserving already-correct solutions as the model improves, yielding a more rectified reward signal. Our work establishes joint training of reasoning and self-refinement as a principled and effective methodology for RLVR.

CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery

✇cs.AI, q-bio.NC updates on arXiv.org
By: Ao Qu · Han Zheng · Zijian Zhou · Yihao Yan · Yihong Tang · Shao Yong Ong · Fenglu Hong · Kaichen Zhou · Chonghe Jiang · Minwei Kong · Jiacheng Zhu · Xuan Jiang · Sirui Li · Cathy Wu · Bryan Kian Hsiang Low · Jinhua Zhao · Paul Pu Liang
3 April 2026 at 12:00
arXiv:2604.01658v1 Announce Type: new Abstract: Large language model (LLM)-based evolution is a promising approach for open-ended discovery, where progress requires sustained search and knowledge accumulation. Existing methods still rely heavily on fixed heuristics and hard-coded exploration rules, which limit the autonomy of LLM agents. We present CORAL, the first framework for autonomous multi-agent evolution on open-ended problems. CORAL replaces rigid control with long-running agents that explore, reflect, and collaborate through shared persistent memory, asynchronous multi-agent execution, and heartbeat-based interventions. It also provides practical safeguards, including isolated workspaces, evaluator separation, resource management, and agent session and health management. Evaluated on diverse mathematical, algorithmic, and systems optimization tasks, CORAL sets new state-of-the-art results on 10 tasks, achieving 3-10 times higher improvement rates with far fewer evaluations than fixed evolutionary search baselines across tasks. On Anthropic's kernel engineering task, four co-evolving agents improve the best known score from 1363 to 1103 cycles. Mechanistic analyses further show how these gains arise from knowledge reuse and multi-agent exploration and communication. Together, these results suggest that greater agent autonomy and multi-agent evolution can substantially improve open-ended discovery. Code is available at https://github.com/Human-Agent-Society/CORAL.

M3D-BFS: a Multi-stage Dynamic Fusion Strategy for Sample-Adaptive Multi-Modal Brain Network Analysis

✇cs.AI, q-bio.NC updates on arXiv.org
By: Rui Dong · Xiaotong Zhang · Jiaxing Li · Yueying Li · Jiayin Wei · Youyong Kong
3 April 2026 at 12:00
arXiv:2604.01667v1 Announce Type: new Abstract: Multi-modal fusion is of great significance in neuroscience which integrates information from different modalities and can achieve better performance than uni-modal methods in downstream tasks. Current multi-modal fusion methods in brain networks, which mainly focus on structural connectivity (SC) and functional connectivity (FC) modalities, are static in nature. They feed different samples into the same model with identical computation, ignoring inherent difference between input samples. This lack of sample adaptation hinders model's further performance. To this end, we innovatively propose a multi-stage dynamic fusion strategy (M3D-BFS) for sample-adaptive multi-modal brain network analysis. Unlike other static fusion methods, we design different mixture-of-experts (MoEs) for uni- and multi-modal representations where modules can adaptively change as input sample changes during inference. To alleviate issue of MoE where training of experts may be collapsed, we divide our method into 3 stages. We first train uni-modal encoders respectively, then pretrain single experts of MoEs before finally finetuning the whole model. A multi-modal disentanglement loss is designed to enhance the final representations. To the best of our knowledge, this is the first work for dynamic fusion for multi-modal brain network analysis. Extensive experiments on different real-world datasets demonstrates the superiority of M3D-BFS.

Hierarchical Memory Orchestration for Personalized Persistent Agents

✇cs.AI, q-bio.NC updates on arXiv.org
By: Junming Liu · Yifei Sun · Weihua Cheng · Haodong Lei · Yuqi Li · Yirong Chen · Ding Wang
3 April 2026 at 12:00
arXiv:2604.01670v1 Announce Type: new Abstract: While long-term memory is essential for intelligent agents to maintain consistent historical awareness, the accumulation of extensive interaction data often leads to performance bottlenecks. Naive storage expansion increases retrieval noise and computational latency, overwhelming the reasoning capacity of models deployed on constrained personal devices. To address this, we propose Hierarchical Memory Orchestration (HMO), a framework that organizes interaction history into a three-tiered directory driven by user-centric contextual relevance. Our system maintains a compact primary cache, coupling recent and pivotal memories with an evolving user profile to ensure agent reasoning remains aligned with individual behavioral traits. This primary cache is complemented by a high-priority secondary layer, both of which are managed within a global archive of the full interaction history. Crucially, the user persona dictates memory redistribution across this hierarchy, promoting records mapped to long-term patterns toward more active tiers while relegating less relevant information. This targeted orchestration surfaces historical knowledge precisely when needed while maintaining a lean and efficient active search space. Evaluations on multiple benchmarks achieve state-of-the-art performance. Real-world deployments in ecosystems like OpenClaw demonstrate that HMO significantly enhances agent fluidity and personalization.

EvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification

✇cs.AI, q-bio.NC updates on arXiv.org
By: Hanrong Zhang · Shicheng Fan · Henry Peng Zou · Yankai Chen · Zhenting Wang · Jiayu Zhou · Chengze Li · Wei-Chieh Huang · Yifei Yao · Kening Zheng · Xue Liu · Xiaoxiao Li · Philip S. Yu
3 April 2026 at 12:00
arXiv:2604.01687v1 Announce Type: new Abstract: Anthropic proposes the concept of skills for LLM agents to tackle multi-step professional tasks that simple tool invocations cannot address. A tool is a single, self-contained function, whereas a skill is a structured bundle of interdependent multi-file artifacts. Currently, skill generation is not only label-intensive due to manual authoring, but also may suffer from human--machine cognitive misalignment, which can lead to degraded agent performance, as evidenced by evaluations on SkillsBench. Therefore, we aim to enable agents to autonomously generate skills. However, existing self-evolving methods designed for tools cannot be directly applied to skills due to their increased complexity. To address these issues, we propose EvoSkills, a self-evolving skills framework that enables agents to autonomously construct complex, multi-file skill packages. Specifically, EvoSkills couples a Skill Generator that iteratively refines skills with a Surrogate Verifier that co-evolves to provide informative and actionable feedback without access to ground-truth test content. On SkillsBench, EvoSkills achieves the highest pass rate among five baselines on both Claude Code and Codex, and also exhibits strong generalization capabilities to six additional LLMs.

LiteInception: A Lightweight and Interpretable Deep Learning Framework for General Aviation Fault Diagnosis

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhihuan Wei · Xinhang Chen · Danyang Han · Yang Hu · Jie Liu · Xuewen Miao · Guijiang Li
3 April 2026 at 12:00
arXiv:2604.01725v1 Announce Type: new Abstract: General aviation fault diagnosis and efficient maintenance are critical to flight safety; however, deploying deep learning models on resource-constrained edge devices poses dual challenges in computational capacity and interpretability. This paper proposes LiteInception--a lightweight interpretable fault diagnosis framework designed for edge deployment. The framework adopts a two-stage cascaded architecture aligned with standard maintenance workflows: Stage 1 performs high-recall fault detection, and Stage 2 conducts fine-grained fault classification on anomalous samples, thereby decoupling optimization objectives and enabling on-demand allocation of computational resources. For model compression, a multi-method fusion strategy based on mutual information, gradient analysis, and SE attention weights is proposed to reduce the input sensor channels from 23 to 15, and a 1+1 branch LiteInception architecture is introduced that compresses InceptionTime parameters by 70%, accelerates CPU inference by over 8x, with less than 3% F1 loss. Furthermore, knowledge distillation is introduced as a precision-recall regulation mechanism, enabling the same lightweight model to adapt to different scenarios--such as safety-critical and auxiliary diagnosis--by switching training strategies. Finally, a dual-layer interpretability framework integrating four attribution methods is constructed, providing traceable evidence chains of "which sensor x which time period." Experiments on the NGAFID dataset demonstrate a fault detection accuracy of 81.92% with 83.24% recall, and a fault identification accuracy of 77.00%, validating the framework's favorable balance among efficiency, accuracy, and interpretability.

ATBench: A Diverse and Realistic Trajectory Benchmark for Long-Horizon Agent Safety

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yu Li · Haoyu Luo · Yuejin Xie · Yuqian Fu · Zhonghao Yang · Shuai Shao · Qihan Ren · Wanying Qu · Yanwei Fu · Yujiu Yang · Jing Shao · Xia Hu · Dongrui Liu
3 April 2026 at 12:00
arXiv:2604.02022v1 Announce Type: new Abstract: Evaluating the safety of LLM-based agents is increasingly important because risks in realistic deployments often emerge over multi-step interactions rather than isolated prompts or final responses. Existing trajectory-level benchmarks remain limited by insufficient interaction diversity, coarse observability of safety failures, and weak long-horizon realism. We introduce ATBench, a trajectory-level benchmark for structured, diverse, and realistic evaluation of agent safety. ATBench organizes agentic risk along three dimensions: risk source, failure mode, and real-world harm. Based on this taxonomy, we construct trajectories with heterogeneous tool pools and a long-context delayed-trigger protocol that captures realistic risk emergence across multiple stages. The benchmark contains 1,000 trajectories (503 safe and 497 unsafe), averaging 9.01 turns and 3.95k tokens, with 1,954 invoked tools drawn from pools spanning 2,084 available tools. Data quality is supported by rule-based and LLM-based filtering plus full human audit. Experiments on frontier LLMs, open-source models, and specialized guard systems show that ATBench is challenging even for strong evaluators, while enabling taxonomy-stratified analysis, cross-benchmark comparison, and diagnosis of long-horizon failure patterns.

The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xinlei Yu · Zhangquan Chen · Yongbo He · Tianyu Fu · Cheng Yang · Chengming Xu · Yue Ma · Xiaobin Hu · Zhe Cao · Jie Xu · Guibin Zhang · Jiale Tao · Jiayi Zhang · Siyuan Ma · Kaituo Feng · Haojie Huang · Youxing Li · Ronghao Chen · Huacan Wang · Chenglin Wu · Zikun Su · Xiaogang Xu · Kelu Yao · Kun Wang · Chen Gao · Yue Liao · Ruqi Huang · Tao Jin · Cheng Tan · Jiangning Zhang · Wenqi Ren · Yanwei Fu · Yong Liu · Yu Wang · Xiangyu Yue · Yu-Gang Jiang · Shuicheng Yan
3 April 2026 at 12:00
arXiv:2604.02029v1 Announce Type: new Abstract: Latent space is rapidly emerging as a native substrate for language-based models. While modern systems are still commonly understood through explicit token-level generation, an increasing body of work shows that many critical internal processes are more naturally carried out in continuous latent space than in human-readable verbal traces. This shift is driven by the structural limitations of explicit-space computation, including linguistic redundancy, discretization bottlenecks, sequential inefficiency, and semantic loss. This survey aims to provide a unified and up-to-date landscape of latent space in language-based models. We organize the survey into five sequential perspectives: Foundation, Evolution, Mechanism, Ability, and Outlook. We begin by delineating the scope of latent space, distinguishing it from explicit or verbal space and from the latent spaces commonly studied in generative visual models. We then trace the field's evolution from early exploratory efforts to the current large-scale expansion. To organize the technical landscape, we examine existing work through the complementary lenses of mechanism and ability. From the perspective of Mechanism, we identify four major lines of development: Architecture, Representation, Computation, and Optimization. From the perspective of Ability, we show how latent space supports a broad capability spectrum spanning Reasoning, Planning, Modeling, Perception, Memory, Collaboration, and Embodiment. Beyond consolidation, we discuss the key open challenges, and outline promising directions for future research. We hope this survey serves not only as a reference for existing work, but also as a foundation for understanding latent space as a general computational and systems paradigm for next-generation intelligence.

Do Emotions in Prompts Matter? Effects of Emotional Framing on Large Language Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Minda Zhao · Yutong Yang · Chufei Peng · Rachel Gonsalves · Weiyue Li · Ruyi Yang · Zhixi Liu · Mengyu Wang
3 April 2026 at 12:00
arXiv:2604.02236v1 Announce Type: new Abstract: Emotional tone is pervasive in human communication, yet its influence on large language model (LLM) behaviour remains unclear. Here, we examine how first-person emotional framing in user-side queries affect LLM performance across six benchmark domains, including mathematical reasoning, medical question answering, reading comprehension, commonsense reasoning and social inference. Across models and tasks, static emotional prefixes usually produce only small changes in accuracy, suggesting that affective phrasing is typically a mild perturbation rather than a reliable general-purpose intervention. This stability is not uniform: effects are more variable in socially grounded tasks, where emotional context more plausibly interacts with interpersonal reasoning. Additional analyses show that stronger emotional wording induces only modest extra change, and that human-written prefixes reproduce the same qualitative pattern as LLM-generated ones. We then introduce EmotionRL, an adaptive emotional prompting framework that selects emotional framing adaptively for each query. Although no single emotion is consistently beneficial, adaptive selection yields more reliable gains than fixed emotional prompting. Together, these findings show that emotional tone is neither a dominant driver of LLM performance nor irrelevant noise, but a weak and input-dependent signal that can be exploited through adaptive control.

Low-Burden LLM-Based Preference Learning: Personalizing Assistive Robots from Natural Language Feedback for Users with Paralysis

✇cs.AI, q-bio.NC updates on arXiv.org
By: Keshav Shankar · Dan Ding · Wei Gao
3 April 2026 at 12:00
arXiv:2604.01463v1 Announce Type: cross Abstract: Physically Assistive Robots (PARs) require personalized behaviors to ensure user safety and comfort. However, traditional preference learning methods, like exhaustive pairwise comparisons, cause severe physical and cognitive fatigue for users with profound motor impairments. To solve this, we propose a low-burden, offline framework that translates unstructured natural language feedback directly into deterministic robotic control policies. To safely bridge the gap between ambiguous human speech and robotic code, our pipeline uses Large Language Models (LLMs) grounded in the Occupational Therapy Practice Framework (OTPF). This clinical reasoning decodes subjective user reactions into explicit physical and psychological needs, which are then mapped into transparent decision trees. Before deployment, an automated "LLM-as-a-Judge" verifies the code's structural safety. We validated this system in a simulated meal preparation study with 10 adults with paralysis. Results show our natural language approach significantly reduces user workload compared to traditional baselines. Additionally, independent clinical experts confirmed the generated policies are safe and accurately reflect user preferences.
  • ✇cs.AI, q-bio.NC updates on arXiv.org
  • The Newton-Muon Optimizer Zhehang Du · Weijie Su
    arXiv:2604.01472v1 Announce Type: cross Abstract: The Muon optimizer has received considerable attention for its strong performance in training large language models, yet the design principle behind its matrix-gradient orthogonalization remains largely elusive. In this paper, we introduce a surrogate model that not only sheds new light on the design of Muon, but more importantly leads to a new optimizer. In the same spirit as the derivation of Newton's method, the surrogate approximates the los
     
  • 🏷️
  • ↗️

The Newton-Muon Optimizer

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhehang Du · Weijie Su
3 April 2026 at 12:00
arXiv:2604.01472v1 Announce Type: cross Abstract: The Muon optimizer has received considerable attention for its strong performance in training large language models, yet the design principle behind its matrix-gradient orthogonalization remains largely elusive. In this paper, we introduce a surrogate model that not only sheds new light on the design of Muon, but more importantly leads to a new optimizer. In the same spirit as the derivation of Newton's method, the surrogate approximates the loss as a quadratic function of the perturbation to a weight matrix $W$ using only three matrices: the gradient $G$, an output-space curvature matrix $H$, and the data matrix $Z$ that stacks the layer inputs. By minimizing this surrogate in one step and adopting a certain isotropic assumption on the weights, we obtain the closed-form update rule (up to momentum and weight decay) $W \leftarrow W - \eta \cdot \mathrm{msgn}(G(ZZ^\top)^{-1})$, where $\eta$ is the learning rate and $\mathrm{msgn}(X)=UV^\top$ if $X=USV^\top$ is a compact singular value decomposition. This new optimization method, which we refer to as Newton-Muon, shows that standard Muon can be interpreted as an implicit Newton-type method that neglects the right preconditioning induced by the input second moment. Empirically, on a reproduction of the earliest publicly released Modded-NanoGPT speedrun configuration using Muon for GPT-2 pretraining, Newton-Muon reaches the target validation loss in 6\% fewer iteration steps and reduces wall-clock training time by about 4\%.

Acoustic and perceptual differences between standard and accented Chinese speech and their voice clones

✇cs.AI, q-bio.NC updates on arXiv.org
By: Tianle Yang · Chengzhe Sun · Phil Rose · Siwei Lyu
3 April 2026 at 12:00
arXiv:2604.01562v1 Announce Type: cross Abstract: Voice cloning is often evaluated in terms of overall quality, but less is known about accent preservation and its perceptual consequences. We compare standard and heavily accented Mandarin speech and their voice clones using a combined computational and perceptual design. Embedding-based analyses show no reliable accented-standard difference in original-clone distances across systems. In the perception study, clones are rated as more similar to their originals for standard than for accented speakers, and intelligibility increases from original to clone, with a larger gain for accented speech. These results show that accent variation can shape perceived identity match and intelligibility in voice cloning even when it is not reflected in an off-the-shelf speaker-embedding distance, and they motivate evaluating speaker identity preservation and accent preservation as separable dimensions.

Tex3D: Objects as Attack Surfaces via Adversarial 3D Textures for Vision-Language-Action Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jiawei Chen · Simin Huang · Jiawei Du · Shuaihang Chen · Yu Tian · Mingjie Wei · Chao Yu · Zhaoxia Yin
3 April 2026 at 12:00
arXiv:2604.01618v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have shown strong performance in robotic manipulation, yet their robustness to physically realizable adversarial attacks remains underexplored. Existing studies reveal vulnerabilities through language perturbations and 2D visual attacks, but these attack surfaces are either less representative of real deployment or limited in physical realism. In contrast, adversarial 3D textures pose a more physically plausible and damaging threat, as they are naturally attached to manipulated objects and are easier to deploy in physical environments. Bringing adversarial 3D textures to VLA systems is nevertheless nontrivial. A central obstacle is that standard 3D simulators do not provide a differentiable optimization path from the VLA objective function back to object appearance, making it difficult to optimize through an end-to-end manner. To address this, we introduce Foreground-Background Decoupling (FBD), which enables differentiable texture optimization through dual-renderer alignment while preserving the original simulation environment. To further ensure that the attack remains effective across long-horizon and diverse viewpoints in the physical world, we propose Trajectory-Aware Adversarial Optimization (TAAO), which prioritizes behaviorally critical frames and stabilizes optimization with a vertex-based parameterization. Built on these designs, we present Tex3D, the first framework for end-to-end optimization of 3D adversarial textures directly within the VLA simulation environment. Experiments in both simulation and real-robot settings show that Tex3D significantly degrades VLA performance across multiple manipulation tasks, achieving task failure rates of up to 96.7\%. Our empirical results expose critical vulnerabilities of VLA systems to physically grounded 3D adversarial attacks and highlight the need for robustness-aware training.

OpenGo: An OpenClaw-Based Robotic Dog with Real-Time Skill Switching

✇cs.AI, q-bio.NC updates on arXiv.org
By: Hanbing Li · Xuewei Cao · Zhiwen Zeng · Yuhan Wu · Yanyong Zhang · Yan Xia
3 April 2026 at 12:00
arXiv:2604.01708v1 Announce Type: cross Abstract: Adaptation to complex tasks and multiple scenarios remains a significant challenge for a single robot agent. The ability to acquire organize, and switch between a wide range of skills in real time, particularly in dynamic environments, has become a fundamental requirement for embodied intelligence. We introduce OpenGo, an OpenClaw-powered embodied robotic dog capable of switching skills in real time according to the scene and task instructions. Specifically, the agent is equipped with (1) a customizable skill library with easy skill import and autonomous skill validation, (2) a dispatcher that selects and invokes different skills according to task prompts or language instructions, and (3) a self-learning framework that fine-tunes skills based on task completion and human feedback. We deploy the agent in Unitree's Go2 robotic dog and validate its capabilities in self-checking and switching of skills autonomously. In addition, by integrating Feishu-platform communication, we enable natural-language guidance and human feedback, allowing inexperienced users to control the robotic dog through simple instructions.

Lifting Unlabeled Internet-level Data for 3D Scene Understanding

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yixin Chen · Yaowei Zhang · Huangyue Yu · Junchao He · Yan Wang · Jiangyong Huang · Hongyu Shen · Junfeng Ni · Shaofei Wang · Baoxiong Jia · Song-Chun Zhu · Siyuan Huang
3 April 2026 at 12:00
arXiv:2604.01907v1 Announce Type: cross Abstract: Annotated 3D scene data is scarce and expensive to acquire, while abundant unlabeled videos are readily available on the internet. In this paper, we demonstrate that carefully designed data engines can leverage web-curated, unlabeled videos to automatically generate training data, to facilitate end-to-end models in 3D scene understanding alongside human-annotated datasets. We identify and analyze bottlenecks in automated data generation, revealing critical factors that determine the efficiency and effectiveness of learning from unlabeled data. To validate our approach across different perception granularities, we evaluate on three tasks spanning low-level perception, i.e., 3D object detection and instance segmentation, to high-evel reasoning, i.e., 3D spatial Visual Question Answering (VQA) and Vision-Lanugage Navigation (VLN). Models trained on our generated data demonstrate strong zero-shot performance and show further improvement after finetuning. This demonstrates the viability of leveraging readily available web data as a path toward more capable scene understanding systems.
❌