GANDR: Claim Auditing for Verifiable Legal Answer Generation

By: Chen Qian · Yimeng Wang · Yu Chen · Lingfei Wu · Andreas Stathopoulos

10 September 2026 at 12:00

arXiv:2609.10293v1 Announce Type: cross Abstract: In high-stakes domains such as legal practice, a language-model answer is only useful to the extent that a reader can verify each claim against the source the system cites. Current grounded-generation pipelines score the answer as a whole, so a correct conclusion can rest on fabricated or loosely matched citations and still score well. Closing this gap requires both a system built for per-claim verification and an evaluation that measures it. We introduce GANDR (Grounded ANswer DRafter), a two-agent system in which a Drafter writes an answer in a structured legal-reasoning format and a separate Critic, with the same view as a human verifier, audits each claim against its cited source and emits a per-claim audit trace on every round. We pair it with a strict correctness criterion requiring every citation to resolve to a passage the retriever returned. On a 185-item legal benchmark where all six systems share one backbone, one retrieval surface, and one citation instruction, GANDR ranks first on every primary metric, reaching 70.8% strict accuracy and leading the strongest baseline by 11.3 points (p

DGCPath: Distribution-Aware Generative Contrastive Framework for Self-supervised Path Representation Learning -- Extended Version

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

By: Sean Bin Yang · Hao Miao · Zongyi Xu · Jilin Hu · Xiangmeng Wang · Hua Lu · Bin Yang · Christian S. Jensen

10 September 2026 at 12:00

arXiv:2609.07316v2 Announce Type: replace Abstract: Due to the proliferation of vehicle trajectory data enabled by advanced sensing technologies, path representation learning has become a pivotal task in intelligent transportation systems. Although existing self-supervised approaches have achieved promising performance, their dependence on deterministic contrastive learning paradigms and handcrafted view augmentation strategies inherently restricts their cross-scenario generalization capabilities. To address these limitations, we present DGCPath, an innovative Distribution-aware Generative Contrastive learning framework for Path representation. This framework establishes a synergistic connection between generative modeling and distributional contrastive learning, enabling the acquisition of robust and transferable feature embeddings. Specifically, our framework incorporates: (1) a diffusion-based view generator that autonomously produces semantically coherent yet diverse trajectory views from Gaussian noise; (2) a variational contrastive mechanism that enforces latent feature alignment at the distribution level, transcending conventional instance-wise consistency; and (3) a novel generative cross-supervision module that reinforces view-level consistency through cross-view reconstruction learning. Comprehensive evaluations on three real-world trajectory datasets demonstrate that DGCPath outperforms state-of-the-art baselines on two distinct downstream tasks, validating its enhanced generalization capability and representation effectiveness.

DHCR24<sup>+</sup> tumor epithelial cells drive cisplatin resistance in bladder cancer by enhancing cholesterol metabolism to activate lipid raft-associated MAPK signaling

Oncogene - Issue - nature.com science feeds

By: Yuanqiao Zhao · Zhuo Xing · Mengmeng Wang · Liangmin Fu · Ruilin Liu · Zexian Ding · Yuan Li · Yinhuai Wang · Bin Yan · Xueqiang Zhu

29 August 2026 at 08:00

Oncogene, Published online: 29 August 2026; doi:10.1038/s41388-026-03967-7

DHCR24⁺ tumor epithelial cells drive cisplatin resistance in bladder cancer by enhancing cholesterol metabolism to activate lipid raft-associated MAPK signaling

Integrating clinical and multiomics evidence based on disease module theory: deciphering the comorbidity network of psoriasis vulgaris via the Ising model for mechanistic insights

Pulmonary nodule

By: Dongwen Shi · Yuan Luo · Ping Zhang · Bin Liang · Mengmeng Wang · Hong Cai · Xiaowen Pang

30 April 2026 at 18:00

Front Immunol. 2026 Apr 14;17:1744789. doi: 10.3389/fimmu.2026.1744789. eCollection 2026.

ABSTRACT

Psoriasis vulgaris (PV), a chronic immune-mediated inflammatory dermatosis, is associated with a significant burden of systemic comorbidities. Traditional comorbidity research methods struggle to reveal its complex interconnectedness. Based on large-scale retrospective cohort data, we constructed a PV comorbidity network using the Ising model from statistical physics. Weighted network centrality analysis was used to identify core and hub nodes and elucidate shared molecular mechanisms at the multiomics level (nontargeted proteomics and lipid peroxidation metabolomics). Finally, the impact of IL-17A inhibition (IL-17Ai) on PV and atherosclerosis (assessed by carotid Doppler color ultrasound) was evaluated using a prospective intervention study. The Ising model identified atherosclerosis- coronary heart disease (CHD) as the core comorbidity (degree centrality >10), with pulmonary nodules, hypertension, and fatty liver serving as key hub nodes (betweenness centrality >60). Multiomics analysis revealed a core molecular mechanism in PV, involving immune inflammation, oxidative stress, lipid metabolism disorder, and coagulation abnormalities, where the oxidative stress molecule GPX3 acts as a critical hub. Following IL-17Ai intervention, both skin lesions and early atherosclerosis markers significantly improved, accompanied by downregulation of the proinflammatory peripheral blood factor S100A9 and upregulation of anti-inflammatory lipid peroxidation metabolites (e.g., 17(R)-RVD1). This study systematically revealed the modular hierarchical structure of PV comorbidities at the network topology and molecular mechanism levels, confirming the central role of the IL-17 signaling pathway in driving the comorbidity network. This conclusion was further clinically validated by IL-17Ai intervention outcomes. This research provides theoretical and clinical evidence for early identification, prioritized management, and "one drug, multiple targets" therapeutic strategies for treating PV comorbidities.

PMID:42058202 | PMC:PMC13121148 | DOI:10.3389/fimmu.2026.1744789

AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models

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

By: Zheda Mai · Arpita Chowdhury · Zihe Wang · Sooyoung Jeon · Lemeng Wang · Jiacheng Hou · Wei-Lun Chao

1 April 2026 at 12:00

arXiv:2506.09082v4 Announce Type: replace-cross Abstract: The rise of vision foundation models (VFMs) calls for systematic evaluation. A common approach pairs VFMs with large language models (LLMs) as general-purpose heads, followed by evaluation on broad Visual Question Answering (VQA) benchmarks. However, this protocol has two key blind spots: (i) the instruction tuning data may not align with VQA test distributions, meaning a wrong prediction can stem from such data mismatch rather than a VFM' visual shortcomings; (ii) VQA benchmarks often require multiple visual abilities, making it hard to tell whether errors stem from lacking all required abilities or just a single critical one. To address these gaps, we introduce AVA-Bench, the first benchmark that explicitly disentangles 14 Atomic Visual Abilities (AVAs) -- foundational skills like localization, depth estimation, and spatial understanding that collectively support complex visual reasoning tasks. By decoupling AVAs and matching training and test distributions within each, AVA-Bench pinpoints exactly where a VFM excels or falters. Applying AVA-Bench to leading VFMs thus reveals distinctive "ability fingerprints," turning VFM selection from educated guesswork into principled engineering. Notably, we find that a 0.5B LLM yields similar VFM rankings as a 7B LLM while cutting GPU hours by 8x, enabling more efficient evaluation. By offering a comprehensive and transparent benchmark, we hope AVA-Bench lays the foundation for the next generation of VFMs.

Variation-aware Flexible 3D Gaussian Editing

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

By: Hao Qin · Yukai Sun · Meng Wang · Ming Kong · Mengxu Lu · Qiang Zhu

16 March 2026 at 12:00

arXiv:2602.11638v3 Announce Type: replace-cross Abstract: Indirect editing methods for 3D Gaussian Splatting (3DGS) have recently witnessed significant advancements. These approaches operate by first applying edits in the rendered 2D space and subsequently projecting the modifications back into 3D. However, this paradigm inevitably introduces cross-view inconsistencies and constrains both the flexibility and efficiency of the editing process. To address these challenges, we present VF-Editor, which enables native editing of Gaussian primitives by predicting attribute variations in a feedforward manner. To accurately and efficiently estimate these variations, we design a novel variation predictor distilled from 2D editing knowledge. The predictor encodes the input to generate a variation field and employs two learnable, parallel decoding functions to iteratively infer attribute changes for each 3D Gaussian. Thanks to its unified design, VF-Editor can seamlessly distill editing knowledge from diverse 2D editors and strategies into a single predictor, allowing for flexible and effective knowledge transfer into the 3D domain. Extensive experiments on both public and private datasets reveal the inherent limitations of indirect editing pipelines and validate the effectiveness and flexibility of our approach.

Lysine attenuates acute lung injury by restoring α-tubulin acetylation and ciliary activity

Cell Death Discovery nature.com science feeds

By: Wenyu Yang · Xiaoxiao Meng · Yong Zhu · Xinrun Ma · Zhuoran Cao · Mengmeng Wang · Wentao Dai · Yiming Tao · Xiangdong Jian · Rui Tian · Zhengfeng Yang · Ruilan Wang

16 March 2026 at 08:00

Cell Death Discovery, Published online: 16 March 2026; doi:10.1038/s41420-026-03025-x

Lysine attenuates acute lung injury by restoring α-tubulin acetylation and ciliary activity

Deep Expert Injection for Anchoring Retinal VLMs with Domain-Specific Knowledge

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

By: Shuai Lu · Meng Wang · Jia Guo · Jiawei Du · Bo Liu · Shengzhu Yang · Weihang Zhang · Huazhu Fu · Huiqi Li

10 March 2026 at 12:00

arXiv:2603.07131v1 Announce Type: cross Abstract: Large Vision Language Models (LVLMs) show immense potential for automated ophthalmic diagnosis. However, their clinical deployment is severely hindered by lacking domain-specific knowledge. In this work, we identify two structural deficiencies hindering reliable medical reasoning: 1) the Perception Gap, where general-purpose visual encoders fail to resolve fine-grained pathological cues (e.g., microaneurysms); and 2) the Reasoning Gap, where sparse visual evidence is progressively overridden by massive language priors in deeper transformer layers, leading to ungrounded hallucinations. To bridge these gaps, we propose EyExIn, a data-efficient framework designed to anchor retinal VLMs with expert knowledge via a Deep Expert Injection mechanism. Our architecture employs an Expert-Aware Dual-Stream encoding strategy that decouples visual representation into a general stream for anatomical context and a specialized expert stream for pathological semantics. To ensure high-fidelity integration, we design a Semantic-Adaptive Gated Fusion module, which dynamically amplifies subtle lesion signals while filtering irrelevant background noise. Furthermore, we introduce Adaptive Deep Expert Injection to embed persistent "Vision Anchors" by integrating fused visual features as residual biases directly into intermediate LLM layers. This mechanism creates a visual shortcut that forces the reasoning stack to remain strictly grounded in visual evidence. Extensive experiments across four benchmarks demonstrate that our model consistently outperforms massive proprietary systems. EyExIn significantly enhances domain-specific knowledge embedding and achieves state-of-the-art precision in ophthalmic visual question answering, advancing the development of trustworthy ophthalmic AI.

Kaleido: Open-Sourced Multi-Subject Reference Video Generation Model

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

By: Zhenxing Zhang · Jiayan Teng · Zhuoyi Yang · Tiankun Cao · Cheng Wang · Xiaotao Gu · Jie Tang · Dan Guo · Meng Wang

5 March 2026 at 13:00

arXiv:2510.18573v2 Announce Type: replace-cross Abstract: We present Kaleido, a subject-to-video~(S2V) generation framework, which aims to synthesize subject-consistent videos conditioned on multiple reference images of target subjects. Despite recent progress in S2V generation models, existing approaches remain inadequate at maintaining multi-subject consistency and at handling background disentanglement, often resulting in lower reference fidelity and semantic drift under multi-image conditioning. These shortcomings can be attributed to several factors. Primarily, the training dataset suffers from a lack of diversity and high-quality samples, as well as cross-paired data, i.e., paired samples whose components originate from different instances. In addition, the current mechanism for integrating multiple reference images is suboptimal, potentially resulting in the confusion of multiple subjects. To overcome these limitations, we propose a dedicated data construction pipeline, incorporating low-quality sample filtering and diverse data synthesis, to produce consistency-preserving training data. Moreover, we introduce Reference Rotary Positional Encoding (R-RoPE) to process reference images, enabling stable and precise multi-image integration. Extensive experiments across numerous benchmarks demonstrate that Kaleido significantly outperforms previous methods in consistency, fidelity, and generalization, marking an advance in S2V generation.

Robust Heterogeneous Analog-Digital Computing for Mixture-of-Experts Models with Theoretical Generalization Guarantees

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

By: Mohammed Nowaz Rabbani Chowdhury · Hsinyu Tsai · Geoffrey W. Burr · Kaoutar El Maghraoui · Liu Liu · Meng Wang

4 March 2026 at 13:00

arXiv:2603.02633v1 Announce Type: cross Abstract: Sparse Mixture-of-Experts (MoE) models enable efficient scalability by activating only a small sub-set of experts per input, yet their massive parameter counts lead to substantial memory and energy inefficiency during inference. Analog in-memory computing (AIMC) offers a promising solution by eliminating frequent data movement between memory and compute units. However, mitigating hardware nonidealities of AIMC typically requires noise-aware retraining, which is infeasible for large MoE models. In this paper, we propose a retraining-free heterogeneous computation framework in which noise-sensitive experts, which are provably identifiable by their maximum neuron norm, are computed digitally while the majority of the experts are executed on AIMC hardware. We further assign densely activated modules, such as attention layers, to digital computation due to their high noise sensitivity despite comprising a small fraction of parameters. Extensive experiments on large MoE language models, including DeepSeekMoE and OLMoE, across multiple benchmark tasks validate the robustness of our approach in maintaining accuracy under analog nonidealities.

Reading view