BAF60A governs beta cell identity to control systemic glucose homeostasis

By: Shuaishuai Zhu · Ziyin Zhang · Ruo-Ran Wang · Wei Chen · Qiyao Xu · Xinyuan Qiu · Xiuyu Ji · Rui Zhang · Rui Wei · Hongxing Fu · Sheng Yan · Zhuo-Xian Meng

3 October 2026 at 18:00

Diabetologia. 2026 Oct 3. doi: 10.1007/s00125-026-06884-2. Online ahead of print.

ABSTRACT

AIMS/HYPOTHESIS: Chromatin remodelling is critical for maintaining pancreatic beta cell identity and function, yet the key regulatory mechanisms remain incompletely defined. This study aimed to investigate the role of the switch/sucrose non-fermentable (SWI/SNF) complex subunit BAF60A in preserving beta cell fate and glucose homeostasis.

METHODS: Pdx1-Cre-mediated BAF60A-knockout (BaBKO) and BAF60A-overexpressing (BaBOE) mice, together with tamoxifen-inducible adult beta cell-specific Smarcd1 knockout (BaBKO^TM) and Isl1 knockout (Isl1BKO^TM) mice, were generated to evaluate the role of BAF60A in vivo. Glucose homeostasis was assessed through glucose tolerance tests, insulin tolerance tests and glucose-stimulated insulin secretion (GSIS) assays. Multiomic analyses, including RNA-seq, ATAC-seq, Cleavage Under Targets and Tagmentation (CUT&Tag) and single-cell RNA-seq, were performed to characterise chromatin accessibility and transcriptional changes. BAF60A-interacting proteins were identified with biotin identification (BioID) and GST pull-down assays. Beta cell lineage tracing was used to assess changes in cell identity. In addition, BAF60A and the dedifferentiation marker ALDH1A3 were examined in pancreatic islets from individuals with and without type 2 diabetes.

RESULTS: BaBKO mice exhibited significant glucose intolerance, impaired GSIS and pronounced loss of beta cell identity, accompanied by the acquisition of non-beta endocrine features. Inducible deletion of Smarcd1 in adult beta cells similarly impaired beta cell maturation and promoted dedifferentiation, as confirmed by lineage tracing. BAF60A deficiency reduced enhancer accessibility and downregulated beta cell identity genes. Mechanistically, BAF60A physically interacts with the transcription factor islet-1 (ISL1) to regulate transcription of target genes. Adult beta cell-specific Isl1 deletion recapitulated key features of BAF60A deficiency and abolished the beneficial effect of BAF60A overexpression on insulin secretion. Conversely, BaBOE mice exhibited improved glucose tolerance and enhanced GSIS under high-fat diet conditions. Adeno-associated virus-mediated BAF60A overexpression markedly reduced beta cell dedifferentiation in BKS-db/db mice. In human type 2 diabetes islets, BAF60A expression was significantly reduced and inversely correlated with ALDH1A3.

CONCLUSIONS/INTERPRETATION: This work establishes BAF60A-ISL1-dependent chromatin remodelling as a key mechanism that preserves beta cell identity and function under metabolic stress, providing mechanistic insight into beta cell failure in type 2 diabetes.

PMID:42829354 | DOI:10.1007/s00125-026-06884-2

VLA-Precision: Asymmetric Co-Bootstrapping for Efficient Real-World Online RL of Vision-Language-Action Models

cs.AI, q-bio.NC updates on arXiv.org

By: Chenyu Su · Zhaolong Shen · Yuan Qian · Chen Qian · Rui Zhang · Feng Yan · Weixing Chen · Fei Zhang · Jiamin Wang · Shuang Cong · Weiwei Shang

10 September 2026 at 12:00

arXiv:2609.04355v2 Announce Type: replace-cross Abstract: Pretrained vision-language-action (VLA) models enable broad manipulation but remain unreliable in tasks demanding precision and repeatability. Applying real-world online reinforcement learning (RL) to VLA post-training enables autonomous trial-and-error improvement beyond demonstrations alone, but exposes two bottlenecks: 1) unreliable value signals can induce policy drift; 2) large-VLA overhead constrains throughput and sample efficiency. To address these challenges, we present VLA-Precision, an efficient real-world online RL framework featuring the Asymmetric Co-Bootstrapping (ACoB) algorithm and the ACoB-Stream architecture. Specifically, ACoB establishes asymmetric co-bootstrapping across timescales: early intervention-guided behavioral learning rapidly improves policy performance while enhancing online experience quality. As autonomous experience accumulates, global return propagation and local preference ranking progressively calibrate value estimates, yielding relative action advantages for reference-regularized policy improvement while suppressing drift. To enable ACoB on large VLAs, we develop ACoB-Stream, a closed-loop experience--policy architecture that establishes invariant-state decoupling and on-demand streaming as design principles, delivering up to 10.9$\times$ improvements in throughput and computational efficiency. Extensive evaluations on nine high-precision chemistry tasks across four categories and four robot embodiments show that VLA-Precision achieves 98.3\% mean success rate in 45.8 min/task, with 27.6 s episodes running at 1.2$\times$ and 1.8$\times$ the speeds of VLA and RL baselines. Resources are available at https://vla-precision.github.io.

ST-BiBench: Benchmarking Multi-Stream Multimodal Coordination in Bimanual Embodied Tasks for MLLMs

cs.AI, q-bio.NC updates on arXiv.org

By: Xin Wu · Zhixuan Liang · Yue Ma · Mengkang Hu · Zhiyuan Qin · Xiu Li

7 April 2026 at 12:00

arXiv:2602.08392v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have significantly advanced the landscape of embodied AI, yet transitioning to synchronized bimanual coordination introduces formidable challenges in multi-stream multimodal integration. We introduce ST-BiBench, a comprehensive multi-tier framework for evaluating spatio-temporal multimodal coordination. Our approach centers on Strategic Coordination Planning, assessing high-level cross-modal reasoning over multiple action and perception streams. To investigate the "proximity paradox"-where semantically coherent plans fail to align with spatially grounded visual inputs-we incorporate Foundational Spatial Grounding to verify workspace awareness and arm-selection logic. Furthermore, we probe model frontiers through Fine-Grained Action Control, investigating whether MLLMs can directly synthesize high-dimensional continuous action modalities (16-Dim) from complex multimodal metadata. Evaluating 30+ state-of-the-art MLLMs, we uncover a persistent and pervasive "coordination paradox"-a significant gap between high-level strategic reasoning and fine-grained physical execution. Results reveal that while frontier MLLMs excel at logic-driven strategy, they frequently suffer from perception-logic disconnection and multi-stream interference during multimodal fusion. ST-BiBench provides a platform for identifying critical bottlenecks in multi-stream multimodal fusion and cross-modal alignment for complex embodied tasks.

Deciphering functional intra-tumoral heterogeneity in BRAF<sup>V600E</sup>-driven mouse thyroid cancer reveals EMT trajectory and metabolic remodeling

Oncogene - Issue - nature.com science feeds

By: Jing Yu · Siyi Shen · Rongkui Luo · Tianyuan Qiu · Jingjing Chen · Wenqing Kong · Ruisen Ma · Ying Yan · Zhoumin Niu · Mei Ma · Zhuoyang Li · Yuting Wu · Yuying Li · Ling Zhang · Hao Ying

4 April 2026 at 08:00

Oncogene, Published online: 04 April 2026; doi:10.1038/s41388-026-03742-8

Deciphering functional intra-tumoral heterogeneity in BRAF^V600E-driven mouse thyroid cancer reveals EMT trajectory and metabolic remodeling

Moir\'e Video Authentication: A Physical Signature Against AI Video Generation

cs.AI, q-bio.NC updates on arXiv.org

By: Yuan Qing · Kunyu Zheng · Lingxiao Li · Boqing Gong · Chang Xiao

3 April 2026 at 12:00

arXiv:2604.01654v1 Announce Type: cross Abstract: Recent advances in video generation have made AI-synthesized content increasingly difficult to distinguish from real footage. We propose a physics-based authentication signature that real cameras produce naturally, but that generative models cannot faithfully reproduce. Our approach exploits the Moir\'e effect: the interference fringes formed when a camera views a compact two-layer grating structure. We derive the Moir\'e motion invariant, showing that fringe phase and grating image displacement are linearly coupled by optical geometry, independent of viewing distance and grating structure. A verifier extracts both signals from video and tests their correlation. We validate the invariant on both real-captured and AI-generated videos from multiple state-of-the-art generators, and find that real and AI-generated videos produce significantly different correlation signatures, suggesting a robust means of differentiating them. Our work demonstrates that deterministic optical phenomena can serve as physically grounded, verifiable signatures against AI-generated video.

Lense–Thirring precessing magnetar engine drives a superluminous supernova

Nature - Issue - nature.com science feeds

By: Joseph R. Farah · Logan J. Prust · D. Andrew Howell · Yuan Qi Ni · Curtis McCully · Moira Andrews · Harsh Kumar · Daichi Hiramatsu · Sebastian Gomez · Kathryn Wynn · Alexei V. Filippenko · K. Azalee Bostroem · Edo Berger · Peter Blanchard

11 March 2026 at 08:00

Nature, Published online: 11 March 2026; doi:10.1038/s41586-026-10151-0

Observations of a nearby type I superluminous supernova showing oscillating light-curve bumps provide evidence of a centrally located magnetar in the wake of the explosion, surrounded by an infalling accretion disk undergoing Lense–Thirring precession.

The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward

cs.AI, q-bio.NC updates on arXiv.org

By: Long Li · Zhijian Zhou · Jiaran Hao · Jason Klein Liu · Yanting Miao · Wei Pang · Xiaoyu Tan · Wei Chu · Zhe Wang · Shirui Pan · Chao Qu · Yuan Qi

4 March 2026 at 13:00

arXiv:2509.07430v4 Announce Type: replace-cross Abstract: A central paradox in fine-tuning Large Language Models (LLMs) with Reinforcement Learning with Verifiable Reward (RLVR) is the frequent degradation of multi-attempt performance (Pass@k) despite improvements in single-attempt accuracy (Pass@1). This is often accompanied by catastrophic forgetting, where models lose previously acquired skills. While various methods have been proposed, the choice and function of the divergence term have been surprisingly unexamined as a proactive solution. We argue that standard RLVR objectives -- both those using the mode-seeking reverse KL-divergence and those forgoing a divergence term entirely -- lack a crucial mechanism for knowledge retention. The reverse-KL actively accelerates this decay by narrowing the policy, while its absence provides no safeguard against the model drifting from its diverse knowledge base. We propose a fundamental shift in perspective: using the divergence term itself as the solution. Our framework, Diversity-Preserving Hybrid RL (DPH-RL), leverages mass-covering f-divergences (like forward-KL and JS-divergence) to function as a rehearsal mechanism. By continuously referencing the initial policy, this approach forces the model to maintain broad solution coverage. Extensive experiments on math and SQL generation demonstrate that DPH-RL not only resolves the Pass@k degradation but improves both Pass@1 and Pass@k in- and out-of-domain. Additionally, DPH-RL is more training-efficient because it computes f-divergence using generator functions, requiring only sampling from the initial policy and no online reference model. Our work highlights a crucial, overlooked axis for improving RLVR, demonstrating that the proper selection of a divergence measure is a powerful tool for building more general and diverse reasoning models.

No Need For Real Anomaly: MLLM Empowered Zero-Shot Video Anomaly Detection

cs.AI, q-bio.NC updates on arXiv.org

By: Zunkai Dai · Ke Li · Jiajia Liu · Jie Yang · Yuanyuan Qiao

24 February 2026 at 13:00

arXiv:2602.19248v1 Announce Type: cross Abstract: The collection and detection of video anomaly data has long been a challenging problem due to its rare occurrence and spatio-temporal scarcity. Existing video anomaly detection (VAD) methods under perform in open-world scenarios. Key contributing factors include limited dataset diversity, and inadequate understanding of context-dependent anomalous semantics. To address these issues, i) we propose LAVIDA, an end-to-end zero-shot video anomaly detection framework. ii) LAVIDA employs an Anomaly Exposure Sampler that transforms segmented objects into pseudo-anomalies to enhance model adaptability to unseen anomaly categories. It further integrates a Multimodal Large Language Model (MLLM) to bolster semantic comprehension capabilities. Additionally, iii) we design a token compression approach based on reverse attention to handle the spatio-temporal scarcity of anomalous patterns and decrease computational cost. The training process is conducted solely on pseudo anomalies without any VAD data. Evaluations across four benchmark VAD datasets demonstrate that LAVIDA achieves SOTA performance in both frame-level and pixel-level anomaly detection under the zero-shot setting. Our code is available in https://github.com/VitaminCreed/LAVIDA.

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.

Reading view