❌

Normal view

Received — 27 May 2026 ⏭

Back to Parsimonious Latents: Learning Task-Centric World Models from Visual Foundations

✇cs.AI, q-bio.NC updates on arXiv.org
By: Minghao Fu · Fan Feng · Nicklas Hansen · Biwei Huang
26 May 2026 at 12:00
arXiv:2605.25620v1 Announce Type: new Abstract: World models enable agents to predict future dynamics conditioned on actions, making the choice of latent representation central to planning and control. Such representations are often either learned directly from pixels with limited semantic structure or inherited from frozen visual foundation models with excessive task-irrelevant detail, yielding state spaces that are poorly matched to downstream planning and control. This is especially challenging in reward-free offline settings, where the model must learn from fixed trajectories without reward supervision or online interaction. To address this, we propose TC-WM, a framework for turning foundation-model embeddings into compact, task-sufficient world representations. The key design is to treat the pretrained embedding space as a semantic scaffold rather than as the final state space: TC-WM linearly projects high-dimensional visual embeddings into a compact latent as the dynamic space, aligns a subspace with the agent's physical state via contrastive learning, and reconstructs embeddings to preserve useful visual structure. This combines the generality of foundation features with the controllability of task-centric dynamics. Theoretically, we show that TC-WM suffices to identify the underlying task-centric latent factors up to a simple transformation. Empirically, TC-WM enables test-time planning across diverse environments (e.g., Robomimic and D4RL), achieving better world-modeling quality and more precise control than state-of-the-art approaches.

Human pancreatic progenitor organoids define genetic and epigenetic barriers to early PDAC transformation

✇(Multiomics OR Omics) AND (Pancreatic)
By: Xian Zhang · Wilfred Wong · Hyein S Cho · Dapeng Yang · Gary Dixon · Renhe Luo · Dingyu Liu · Denis Torre · Shigeaki Umeda · Federico González · Gokce Askan · Aslihan Yavas · Jeyaram Ravichandran Damodaran · Robert W Rickert · Rajya Kappagantula · Fong Cheng Pan · Victoria G Aveson · Adrien Grimont · William B Fall · Xianming Wang · Julian Pulecio · Samuel J Kaplan · Heng Pan · Xianlu Laura Peng · Jen Jen Yeh · Steven D Leach · Christine A Iacobuzio-Donahue · Rohit Chandwani · Christina S Leslie · Danwei Huangfu
20 May 2026 at 18:00

Dev Cell. 2026 May 19:S1534-5807(26)00159-0. doi: 10.1016/j.devcel.2026.04.012. Online ahead of print.

ABSTRACT

The lack of accurate human models that recapitulate pancreatic ductal adenocarcinoma (PDAC) initiation has hindered therapeutic development. Using pluripotent stem cell-derived pancreatic progenitor organoids, we established a human PDAC model that faithfully reproduces the genetic, epigenetic, and transcriptomic trajectories of tumor initiation and progression, validated against clinical datasets and tumor histopathology. We demonstrate that CDKN2A loss, which is nearly universal in patients but dispensable in mouse models, is essential for neoplastic transformation when combined with KRAS and TP53 mutations, whereas SMAD4 loss promotes tumor progression. Multi-omics profiling reveals epigenetic repression of the pancreatic lineage program during PDAC initiation, alongside AP-1-driven chromatin remodeling. We identify TET1 suppression as a mechanistic link between oncogenic ERK signaling and hypermethylation of essential pancreatic transcription factors. This model captures genetic and epigenetic determinants of human PDAC, reveals antagonism between oncogenic and lineage restriction programs, and supports TET-based lineage restoration as a potential early intervention strategy.

PMID:42161274 | PMC:PMC13196429 | DOI:10.1016/j.devcel.2026.04.012

De novo design of quasisymmetric two-component protein cages

✇Nature - Issue - nature.com science feeds
By: Shunzhi Wang · Ying Xie · David Chemielewski · Connor Weidle · Tong Shu · Green Ahn · Ryan D. Kibler · Cindy Hernandez · Wei Chen · David Camilo Duran · Ann Carr · Asim K. Bera · Sangmin Lee · Justin Decarreau · Alex Kang · Evans Brackenbrough · Emily Joyce · Kejia Wu · Andrew J. Borst · Andrew Favor · Buwei Huang · Frank DiMaio · Liam J. Holt · David Baker
20 May 2026 at 08:00

Nature, Published online: 20 May 2026; doi:10.1038/s41586-026-10464-0

Researchers designed two-component proteins forming quasisymmetric cages via geometric frustration, enabling tunable virus-like assemblies for cargo delivery, cellular uptake and studying intracellular diffusion and protein localization.
Received — 13 April 2026 ⏭

A Genetically Engineered Human Organoid Model Reveals Distinct Genetic and Epigenetic Barriers of Lineage Plasticity in Early PDAC Transformation

✇(Multiomics OR Omics) AND (Pancreatic)
By: Xian Zhang · Wilfred Wong · Hyein S Cho · Dapeng Yang · Gary Dixon · Renhe Luo · Dingyu Liu · Denis Torre · Shigeaki Umeda · Federico González · Gokce Askan · Aslihan Yavas · Jeyaram Ravichandran Damodaran · Robert W Rickert · Rajya Kappagantula · Fong Cheng Pan · Victoria G Aveson · Adrien Grimont · Julian Pulecio · Samuel J Kaplan · Heng Pan · Steven D Leach · Christine A Iacobuzio-Donahue · Rohit Chandwani · Christina S Leslie · Danwei Huangfu
10 April 2026 at 18:00

bioRxiv [Preprint]. 2026 Mar 11:2026.03.09.710586. doi: 10.64898/2026.03.09.710586.

ABSTRACT

The lack of accurate, human-based models recapitulating early-stage pancreatic ductal adenocarcinoma (PDAC) has hindered therapeutic development. Using pluripotent stem cell-derived pancreatic progenitor organoids, we established a human PDAC model that faithfully reproduces the genetic, epigenetic, and transcriptomic trajectory of tumor initiation and progression in vitro , validated against clinical datasets and histopathology. We demonstrate that CDKN2A loss, nearly universal in patients but dispensable in mouse models, is essential for neoplastic transformation when combined with KRAS and TP53 mutations, while SMAD4 loss promotes tumor progression. Multi-omics profiling reveals epigenetic repression of pancreatic lineage program during PDAC initiation, alongside oncogenic AP-1-driven chromatin remodeling. Notably, we identify TET1 suppression as a mechanistic link between oncogenic ERK signaling and the hypermethylation and silencing of essential pancreatic transcription factors. This model captures the genetic and epigenetic determinants of human PDAC, reveals antagonism between oncogenic and lineage restriction programs, and supports TET-based lineage restoration as a promising early intervention strategy for high-risk individuals.

PMID:41959451 | PMC:PMC13060829 | DOI:10.64898/2026.03.09.710586

Received — 8 April 2026 ⏭

Low-Bitrate Video Compression through Semantic-Conditioned Diffusion

✇cs.AI, q-bio.NC updates on arXiv.org
By: Lingdong Wang · Guan-Ming Su · Divya Kothandaraman · Tsung-Wei Huang · Mohammad Hajiesmaili · Ramesh K. Sitaraman
7 April 2026 at 12:00
arXiv:2512.00408v2 Announce Type: replace-cross Abstract: Traditional video codecs optimized for pixel fidelity collapse at ultra-low bitrates and produce severe artifacts. This failure arises from a fundamental misalignment between pixel accuracy and human perception. We propose a semantic video compression framework named DiSCo that transmits only the most meaningful information while relying on generative priors for detail synthesis. The source video is decomposed into three compact modalities: a textual description, a spatiotemporally degraded video, and optional sketches or poses that respectively capture semantic, appearance, and motion cues. A conditional video diffusion model then reconstructs high-quality, temporally coherent videos from these compact representations. Temporal forward filling, token interleaving, and modality-specific codecs are proposed to improve multimodal generation and modality compactness. Experiments show that our method outperforms baseline semantic and traditional codecs by 2-10X on perceptual metrics at low bitrates.
Received — 2 April 2026 ⏭

KEditVis: A Visual Analytics System for Knowledge Editing of Large Language Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhenning Chen · Hanbei Zhan · Yanwei Huang · Xin Wu · Dazhen Deng · Di Weng · Yingcai Wu
1 April 2026 at 12:00
arXiv:2603.29689v1 Announce Type: cross Abstract: Large Language Models (LLMs) demonstrate exceptional capabilities in factual question answering, yet they sometimes provide incorrect responses. To address this issue, knowledge editing techniques have emerged as effective methods for correcting factual information in LLMs. However, typical knowledge editing workflows struggle with identifying the optimal set of model layers for editing and rely on summary indicators that provide insufficient guidance. This lack of transparency hinders effective comparison and identification of optimal editing strategies. In this paper, we present KEditVis, a novel visual analytics system designed to assist users in gaining a deeper understanding of knowledge editing through interactive visualizations, improving editing outcomes, and discovering valuable insights for the future development of knowledge editing algorithms. With KEditVis, users can select appropriate layers as the editing target, explore the reasons behind ineffective edits, and perform more targeted and effective edits. Our evaluation, including usage scenarios, expert interviews, and a user study, validates the effectiveness and usability of the system.

LPNSR: Prior-Enhanced Diffusion Image Super-Resolution via LR-Guided Noise Prediction

✇cs.AI, q-bio.NC updates on arXiv.org
By: Shuwei Huang · Shizhuo Liu · Zijun Wei
1 April 2026 at 12:00
arXiv:2603.21045v3 Announce Type: replace-cross Abstract: Diffusion-based image super-resolution (SR), which aims to reconstruct high-resolution (HR) images from corresponding low-resolution (LR) observations, faces a fundamental trade-off between inference efficiency and reconstruction quality. The state-of-the-art residual-shifting diffusion framework achieves efficient 4-step inference, yet suffers from severe performance degradation in compact sampling trajectories. This is mainly attributed to two core limitations: the inherent suboptimality of unconstrained random Gaussian noise in intermediate steps, which leads to error accumulation and insufficient LR prior guidance, and the initialization bias caused by naive bicubic upsampling. In this paper, we propose LPNSR, a prior-enhanced efficient diffusion framework to address these issues. We first mathematically derive the closed-form analytical solution of the optimal intermediate noise for the residual-shifting diffusion paradigm, and accordingly design an LR-guided multi-input-aware noise predictor to replace random Gaussian noise, embedding LR structural priors into the reverse process while fully preserving the framework's core efficient residual-shifting mechanism. We further mitigate initial bias with a high-quality pre-upsampling network to optimize the diffusion starting point. With a compact 4-step trajectory, LPNSR can be optimized in an end-to-end manner. Extensive experiments demonstrate that LPNSR achieves state-of-the-art perceptual performance on both synthetic and real-world datasets, without relying on any large-scale text-to-image priors. The source code of our method can be found at https://github.com/Faze-Hsw/LPNSR.
Received — 26 March 2026 ⏭

LPNSR: Prior-Enhanced Diffusion Image Super-Resolution via LR-Guided Noise Prediction

✇cs.AI, q-bio.NC updates on arXiv.org
By: Shuwei Huang · Shizhuo Liu · Zijun Wei
25 March 2026 at 12:00
arXiv:2603.21045v2 Announce Type: replace-cross Abstract: Diffusion-based image super-resolution (SR), which aims to reconstruct high-resolution (HR) images from corresponding low-resolution (LR) observations, faces a fundamental trade-off between inference efficiency and reconstruction quality. The state-of-the-art residual-shifting diffusion framework achieves efficient 4-step inference, yet suffers from severe performance degradation in compact sampling trajectories. This is mainly attributed to two core limitations: the inherent suboptimality of unconstrained random Gaussian noise in intermediate steps, which leads to error accumulation and insufficient LR prior guidance, and the initialization bias caused by naive bicubic upsampling. In this paper, we propose LPNSR, a prior-enhanced efficient diffusion framework to address these issues. We first mathematically derive the closed-form analytical solution of the optimal intermediate noise for the residual-shifting diffusion paradigm, and accordingly design an LR-guided multi-input-aware noise predictor to replace random Gaussian noise, embedding LR structural priors into the reverse process while fully preserving the framework's core efficient residual-shifting mechanism. We further mitigate initial bias with a high-quality pre-upsampling network to optimize the diffusion starting point. With a compact 4-step trajectory, LPNSR can be optimized in an end-to-end manner. Extensive experiments demonstrate that LPNSR achieves state-of-the-art perceptual performance on both synthetic and real-world datasets, without relying on any large-scale text-to-image priors. The source code of our method can be found at https://github.com/Faze-Hsw/LPNSR.
Received — 14 March 2026 ⏭

Multimodal electron microscopy of halide perovskite interfacial dynamics

✇Nature - Issue - nature.com science feeds
By: Xinjuan Li · Qichun Gu · Wei Huang · Simon M. Fairclough · Richard H. Friend · Samuel D. Stranks · Tianjun Liu · Caterina Ducati
11 March 2026 at 08:00

Nature, Published online: 11 March 2026; doi:10.1038/s41586-026-10238-8

A multimodal in situ electron microscopy approach enables direct visualization of structural and chemical evolution in a working halide perovskite light-emitting diode with nanometre precision.
Received — 11 March 2026 ⏭

DreamSAC: Learning Hamiltonian World Models via Symmetry Exploration

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jinzhou Tang · Fan Feng · Minghao Fu · Wenjun Lin · Biwei Huang · Keze Wang
10 March 2026 at 12:00
arXiv:2603.07545v1 Announce Type: cross Abstract: Learned world models excel at interpolative generalization but fail at extrapolative generalization to novel physical properties. This limitation arises because they learn statistical correlations rather than the environment's underlying generative rules, such as physical invariances and conservation laws. We argue that learning these invariances is key to robust extrapolation. To achieve this, we first introduce \textbf{Symmetry Exploration}, an unsupervised exploration strategy where an agent is intrinsically motivated by a Hamiltonian-based curiosity bonus to actively probe and challenge its understanding of conservation laws, thereby collecting physically informative data. Second, we design a Hamiltonian-based world model that learns from the collected data, using a novel self-supervised contrastive objective to identify the invariant physical state from raw, view-dependent pixel observations. Our framework, \textbf{DreamSAC}, trained on this actively curated data, significantly outperforms state-of-the-art baselines in 3D physics simulations on tasks requiring extrapolation.

Solution to the 10th ABAW Expression Recognition Challenge: A Robust Multimodal Framework with Safe Cross-Attention and Modality Dropout

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jun Yu · Naixiang Zheng · Guoyuan Wang · Yunxiang Zhang · Lingsi Zhu · Jiaen Liang · Wei Huang · Shengping Liu
10 March 2026 at 12:00
arXiv:2603.08034v1 Announce Type: cross Abstract: Emotion recognition in real-world environments is hindered by partial occlusions, missing modalities, and severe class imbalance. To address these issues, particularly for the Affective Behavior Analysis in-the-wild (ABAW) Expression challenge, we propose a multimodal framework that dynamically fuses visual and audio representations. Our approach uses a dual-branch Transformer architecture featuring a safe cross-attention mechanism and a modality dropout strategy. This design allows the network to rely on audio-based predictions when visual cues are absent. To mitigate the long-tail distribution of the Aff-Wild2 dataset, we apply focal loss optimization, combined with a sliding-window soft voting strategy to capture dynamic emotional transitions and reduce frame-level classification jitter. Experiments demonstrate that our framework effectively handles missing modalities and complex spatiotemporal dependencies, achieving an accuracy of 60.79% and an F1-score of 0.5029 on the Aff-Wild2 validation set.
Received — 5 March 2026 ⏭

RADAR: Learning to Route with Asymmetry-aware DistAnce Representations

✇cs.AI, q-bio.NC updates on arXiv.org
By: Hang Yi · Ziwei Huang · Yining Ma · Zhiguang Cao
5 March 2026 at 13:00
arXiv:2603.03388v1 Announce Type: cross Abstract: Recent neural solvers have achieved strong performance on vehicle routing problems (VRPs), yet they mainly assume symmetric Euclidean distances, restricting applicability to real-world scenarios. A core challenge is encoding the relational features in asymmetric distance matrices of VRPs. Early attempts directly encoded these matrices but often failed to produce compact embeddings and generalized poorly at scale. In this paper, we propose RADAR, a scalable neural framework that augments existing neural VRP solvers with the ability to handle asymmetric inputs. RADAR addresses asymmetry from both static and dynamic perspectives. It leverages Singular Value Decomposition (SVD) on the asymmetric distance matrix to initialize compact and generalizable embeddings that inherently encode the static asymmetry in the inbound and outbound costs of each node. To further model dynamic asymmetry in embedding interactions during encoding, it replaces the standard softmax with Sinkhorn normalization that imposes joint row and column distance awareness in attention weights. Extensive experiments on synthetic and real-world benchmarks across various VRPs show that RADAR outperforms strong baselines on both in-distribution and out-of-distribution instances, demonstrating robust generalization and superior performance in solving asymmetric VRPs.
Received — 17 February 2026 ⏭

DeepFusion: Accelerating MoE Training via Federated Knowledge Distillation from Heterogeneous Edge Devices

✇cs.AI, q-bio.NC updates on arXiv.org
By: Songyuan Li · Jia Hu · Ahmed M. Abdelmoniem · Geyong Min · Haojun Huang · Jiwei Huang
17 February 2026 at 13:00
arXiv:2602.14301v1 Announce Type: cross Abstract: Recent Mixture-of-Experts (MoE)-based large language models (LLMs) such as Qwen-MoE and DeepSeek-MoE are transforming generative AI in natural language processing. However, these models require vast and diverse training data. Federated learning (FL) addresses this challenge by leveraging private data from heterogeneous edge devices for privacy-preserving MoE training. Nonetheless, traditional FL approaches require devices to host local MoE models, which is impractical for resource-constrained devices due to large model sizes. To address this, we propose DeepFusion, the first scalable federated MoE training framework that enables the fusion of heterogeneous on-device LLM knowledge via federated knowledge distillation, yielding a knowledge-abundant global MoE model. Specifically, DeepFusion features each device to independently configure and train an on-device LLM tailored to its own needs and hardware limitations. Furthermore, we propose a novel View-Aligned Attention (VAA) module that integrates multi-stage feature representations from the global MoE model to construct a predictive perspective aligned with on-device LLMs, thereby enabling effective cross-architecture knowledge distillation. By explicitly aligning predictive perspectives, VAA resolves the view-mismatch problem in traditional federated knowledge distillation, which arises from heterogeneity in model architectures and prediction behaviors between on-device LLMs and the global MoE model. Experiments with industry-level MoE models (Qwen-MoE and DeepSeek-MoE) and real-world datasets (medical and finance) demonstrate that DeepFusion achieves performance close to centralized MoE training. Compared with key federated MoE baselines, DeepFusion reduces communication costs by up to 71% and improves token perplexity by up to 5.28%.

Governing AI Forgetting: Auditing for Machine Unlearning Compliance

✇cs.AI, q-bio.NC updates on arXiv.org
By: Qinqi Lin · Ningning Ding · Lingjie Duan · Jianwei Huang
17 February 2026 at 13:00
arXiv:2602.14553v1 Announce Type: cross Abstract: Despite legal mandates for the right to be forgotten, AI operators routinely fail to comply with data deletion requests. While machine unlearning (MU) provides a technical solution to remove personal data's influence from trained models, ensuring compliance remains challenging due to the fundamental gap between MU's technical feasibility and regulatory implementation. In this paper, we introduce the first economic framework for auditing MU compliance, by integrating certified unlearning theory with regulatory enforcement. We first characterize MU's inherent verification uncertainty using a hypothesis-testing interpretation of certified unlearning to derive the auditor's detection capability, and then propose a game-theoretic model to capture the strategic interactions between the auditor and the operator. A key technical challenge arises from MU-specific nonlinearities inherent in the model utility and the detection probability, which create complex strategic couplings that traditional auditing frameworks do not address and that also preclude closed-form solutions. We address this by transforming the complex bivariate nonlinear fixed-point problem into a tractable univariate auxiliary problem, enabling us to decouple the system and establish the equilibrium existence, uniqueness, and structural properties without relying on explicit solutions. Counterintuitively, our analysis reveals that the auditor can optimally reduce the inspection intensity as deletion requests increase, since the operator's weakened unlearning makes non-compliance easier to detect. This is consistent with recent auditing reductions in China despite growing deletion requests. Moreover, we prove that although undisclosed auditing offers informational advantages for the auditor, it paradoxically reduces the regulatory cost-effectiveness relative to disclosed auditing.

ESPO: Entropy Importance Sampling Policy Optimization

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yuepeng Sheng · Yuwei Huang · Shuman Liu · Anxiang Zeng · Haibo Zhang
17 February 2026 at 13:00
arXiv:2512.00499v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become a central component of post-training for large language models (LLMs), particularly for complex reasoning tasks that require stable optimization over long generation horizons. However, achieving performance at scale often introduces a fundamental trade-off between training stability and training efficiency. Token-level optimization applies fine-grained updates at the individual units, but is prone to high variance in gradient estimation, which can result in unstable training dynamics. In contrast, Sequence-level optimization often relies on aggressive clipping mechanisms to ensure stable updates. However, such design may discard a large fraction of valid training samples, leading to inefficient gradient utilization and reduced training efficiency. We refer to this phenomenon as gradient underutilization. In this work, we propose Entropy Importance Sampling Policy Optimization (ESPO), a novel framework that aims to combine fine-grained updates with stable training. ESPO decomposes sequences into groups based on predictive entropy, enabling (1) Entropy Grouping Importance Sampling to capture intra-sequence heterogeneity, and (2) Entropy Adaptive Clipping to dynamically allocate trust regions based on model uncertainty. Extensive experiments on mathematical reasoning benchmarks demonstrate that ESPO not only accelerates convergence but also achieves state-of-the-art performance, notably improving accuracy on the challenging mathematical benchmarks.
There are no more articles
❌