Yang Wang

Modern mobile GUI agents can perceive visible screens and execute local actions, but they still lack persistent app-specific navigation know… (see more)ledge: where functions live, which pages contain them, and which screens are equivalent across repeated visits. We introduce TAG-Nav, a Task-Agnostic Graph Navigation framework that wraps existing GUI-agent backbones with reusable destination memory. Offline exploration is distilled into compact records of app functions, target pages, and waypoint routes before any evaluated instruction is seen. When a future task's destination is covered, TAG-Nav retrieves the destination and provides route guidance without task-specific demonstrations. This separates mobile GUI destination navigation from full task completion: many tasks share the prefix of reaching the right page, while final actions may enter content, send data, make purchases, delete information, or change sensitive settings. To evaluate route finding without downstream execution confounds, we introduce DestBench, a navigation-only protocol that asks whether an agent reaches the correct pre-action destination screen. DestBench enables a controlled graph-memory study comparing no-memory agents with random, automated BFS, and clean graph memory. Graph-derived memory improves strict navigation success rate of UI-TARS-1.5-7B from 52.4% without graph memory to 58.3% with automated BFS memory, and improves Qwen-VL-Max success rate from 59.5% to 71.4% on the same conditions. Together, TAG-Nav and DestBench show that destination coverage and route cleanliness strongly shape graph-memory value, making graph quality a measured variable rather than an assumed benefit of exploration.

2026-10-14

arXiv (preprint)

arxiv.org

Masked Feature Encoding for Large-Scale Whole Slide Image Representation

Haoyu He

Basile Tessier-Cloutier

Mahdi S. Hosseini

Whole slide image (WSI) analysis in computational pathology follows a multiple instance learning (MIL) pipeline where patch embeddings are e… (see more)xtracted independently and aggregated for slide-level prediction, but within-slide variance from staining, scanner, and local texture can overwhelm the discriminative signal. We propose Masked Feature Encoding for Multiple Instance Learning (MFE-MIL), a feature-space masking framework that trains a lightweight MLP adapter jointly with a window-based masked reconstruction branch and a MIL classification head. The two objectives are complementary. Classification guides the adapter to suppress within-slide patch variance, while window-based masked reconstruction provides an auxiliary regularizer for the adapted features without using patch coordinates, coordinate graphs, or segmentation preprocessing. The raster patch-extraction order is used only as a weak implicit prior. At inference, the decoder is removed, leaving only the adapter and MIL head. Across CAMELYON16/17, PANDA, and TCGA-BRCA with four diverse encoders, MFE-MIL improves ACC/F1 for nearly all tested aggregator-encoder settings and AUC in most, outperforms coordinate-based spatial methods (CAMIL), and achieves higher AUC than 2DMamba on three of four datasets (UNI). On five TCGA survival cohorts it improves the average concordance index for every aggregator tested, its most consistent gain. Code is available at https://github.com/AtlasAnalyticsLab/MFE-MIL.

2026-10-06

arXiv (preprint)

arxiv.org

Credible Information Subset Decomposition: An End-to-End Multi-fidelity Learning Model by Modeling Label Information

Sihan Wang

Wenjie Du

In the AI4Chemistry scenario, utilizing heterogeneous data at different fidelity levels is a common and core issue. High-fidelity data is ac… (see more)curate but scarce, while low-fidelity data is abundant but biased. Traditional multi-fidelity methods typically identify cross-fidelity biases based on paired samples under different fidelity labels. However, due to the mismatch in dataset input distribution and the complexity of the biases themselves, these methods are difficult to implement in real-world scientific environments. To address this, we propose a trusted information subset decomposition framework that can efficiently utilize multi-fidelity data without requiring paired samples. Multi-fidelity label supervision is decomposed into three complementary subsets: a trusted information subset based on the absolute value of high-fidelity labels; a trusted subset that captures the reliability of the high-fidelity and medium-fidelity label intervals through adaptive constraints; and an ordered trusted subset representing the numerical relationships within the same fidelity level. These subsets are then integrated into a unified end-to-end model, enabling the reasonable utilization of medium- and low-fidelity information. Extensive experiments on various molecular and material property benchmarks demonstrate that our method consistently outperforms state-of-the-art multifidelity and singlefidelity baseline methods, and exhibits good robustness under real-world unpaired multifidelity conditions.

2026-09-28

International Conference on Machine Learning (published)

Fast Spectrally Sparse Signal Reconstruction via Jacobi-Preconditioned Gradient Descent

Jian-Feng Cai

Xueyang Quan

Jiaxi Ying

Spectrally sparse signal reconstruction arises in a wide range of applications and can be formulated as a low-rank Hankel matrix completion … (see more)problem. We develop a Jacobi-preconditioned gradient descent method that preserves the low per-iteration complexity of first-order algorithms while achieving linear convergence at a rate independent of the condition number. By introducing a generator that maps factor-based iterates to matrix space, we establish equivalence with manifold-based methods, enabling direct convergence analysis while avoiding the need to define distances under complex-symmetric factorization ambiguity. Extensive experiments demonstrate that the proposed algorithm outperforms state-of-the-art methods in both iteration count and computational time across a broad range of problem settings.

2026-09-28

International Conference on Machine Learning (published)

Improving LLM-Based Recommenders with Conservative Generative Flow Networks

Xuan Yu

Feng Niu

Rui Zhu

Yudong Zhang

Xu Wang

Generative Flow Networks (GFlowNets) have recently been used to improve diversity and mitigate popularity bias in LLM-based recommender syst… (see more)ems, yet most objectives are developed under online-style assumptions. In offline LLM-based recommendation, learning is constrained to a fixed logged dataset, yielding partial support over token transitions on the dataset-induced token-prefix DAG. Naively applying Sub-Trajectory Balance (SubTB) becomes non-identifiable and can arbitrarily allocate probability mass to unsupported regions. We formalize this failure and identify three sources of non-identifiability that induce distributional shift between the dataset-implied policy and the learned policy: (i) flow overestimation, (ii) forward mass leakage, and (iii) backward compensation. To address it, we propose CFlower, which introduces a conservative SubTB objective that explicitly penalizes unsupported forward flow mass, and combines it with dataset-constrained policy learning with on-policy sampling on the dataset-induced DAG for efficient training under offline constraints. Experiments on three Amazon recommendation datasets show that CFlower improves distributional matching and delivers a stronger accuracy–exposure trade-off than prior GFlowNet and SFT baselines, while serving as a more reliable reference policy for downstream RL fine-tuning.

2026-09-28

International Conference on Machine Learning (published)

Scaling Transformers for End-to-End Discrete Audio Tokenization

Yitian Gong

Kuangwei Chen

Zhaoye Fei

Xiaogui Yang

Ke Chen

Kexin Huang

Mingshu Chen

Ruixiao Li

Qinyuan Cheng

Shimin Li

Xipeng Qiu

Discrete audio tokenizers are fundamental to empowering large language models with native audio processing and generation capabilities. Desp… (see more)ite recent progress, existing approaches often rely on pretrained encoders, semantic distillation, or heterogeneous CNN-based architectures. These designs introduce fixed inductive biases that limit reconstruction fidelity and hinder effective scaling. In this paper, we argue that discrete audio tokenization should be learned fully end-to-end using a homogeneous and scalable architecture. Based on this perspective, we propose

2026-09-28

International Conference on Machine Learning (published)

SymSpectra: Symmetric Information Bottleneck Framework for Molecular Structure Recognition under Imbalanced Settings

Xiaohan Qin

Wenjie Du

Identifying molecular structures from spectral data is essential for early-stage chemical analysis, yet it remains a difficult task due to s… (see more)evere functional group imbalance and complex inter-group dependencies, which often cause existing methods to overfit frequent groups while underperforming on rare ones. To address these issues, we present SymSpectra, a Symmetric Conditional Information Bottleneck (SCIB) framework designed to seamlessly integrate multi-modal Spectra features. Our model employs the SCIB framework to fuse multi-modal spectroscopic data into a unified representation, effectively preserving discriminative signals while mitigating redundancy. To enhance robustness against data imbalance, we incorporate conditional mutual information into the training objective, increasing the model’s sensitivity to rare functional groups and challenging molecular cases. Additionally, a specialized module captures the dependencies among functional groups, improving both prediction accuracy and chemically meaningful interpretability. Experiments on multimodal spectral datasets show that SymSpectra outperforms state-of-the-art methods, achieving an F1-score of 0.970 in substructure classification and demonstrating strong robustness under various imbalance settings.

2026-09-28

International Conference on Machine Learning (published)

Topology-Aware Contrastive Learning: Regulating Representation Connectivity via Persistent Homology

Jiaxin Sun

Yuhua Qian

Standard contrastive learning minimizes geometric distance between positive pairs, implicitly assuming that strict compactness optimizes dis… (see more)crimination. However, this topology-agnostic confusion neglects intrinsic data structures and topological complexity, leading to class confusion—particularly when aggressive augmentations induce semantic drift. To address this, we propose Topology-Aware Contrastive Learning, a framework that shifts the objective from geometric singularity to topological connectivity. Leveraging Persistent Homology, we explicitly regulate the connectivity of the latent space, ensuring positive pairs maintain an

2026-09-28

International Conference on Machine Learning (published)

One Rollout Is All You Get: Fully Test-Time Adaptation for GUI Agents

Ziqiang Wang

Li Gu

Zhixiang Chi

Linlian Jiang

Zihuan Jiang

Linqiang Guo

Siobhan Reid

Zhi Liu

GUI agents are deployed with frozen weights and discard everything they experience on the job. Existing ways to update an agent's weights as… (see more)sume something deployment withholds: ground truth, rollouts beyond the single attempt (retries, samples, practice runs), or a learning phase other than deployment. Because GUI actions can be irreversible, a deployed agent gets one attempt per task occurrence, in arrival order, and every attempt counts. No ground truth is available at any point. We define fully test-time adaptation for GUI agents by these constraints and pair it with a minimal weight-space method, SOLO. Auxiliary models read each episode: a judge selects the episodes it deems successful, and a proposer-verifier pair relabels a failed episode's prefix with the subtask that prefix completed. Admitted episodes enter a short sliding window, and each admission updates a small adapter by top-K self-distillation on the agent's own predictions, provided the window holds a judged success. On recurring task streams built from WebArena, VisualWebArena and MobileWorld, SOLO improves on the frozen agent with both UI-TARS-7B and Qwen3-VL-8B, by three to six points of success rate, and exceeds two in-setting memory methods on the web streams.

2026-09-27

arXiv (preprint)

arxiv.org

FACT-GS: Frequency-Aligned Complexity-Aware Texture Reparameterization for 2D Gaussian Splatting

Tianhao Xie

Linlian Jiang

Xinxin Zuo

Tiberiu Popa

Realistic scene appearance modeling has advanced rapidly with Gaussian Splatting, which enables real-time, high-quality rendering. Recent ad… (see more)vances introduced per-primitive textures that incorporate spatial color variations within each Gaussian, improving their expressiveness. However, texture-based Gaussians parameterize appearance with a uniform per-Gaussian sampling grid, allocating equal sampling density regardless of local visual complexity, which leads to inefficient texture space utilization. We introduce FACT-GS, a Frequency-Aligned Complexity-Aware Texture Gaussian Splatting framework that allocates texture sampling density according to local visual frequency. Grounded in adaptive sampling theory, FACT-GS reformulates texture parameterization as a differentiable sampling-density allocation problem, replacing the uniform textures with a learnable frequency-aware allocation strategy implemented via a deformation field whose Jacobian modulates local sampling density. Built on 2D Gaussian Splatting, FACT-GS performs non-uniform sampling on fixed-resolution texture grids, preserving real-time performance while recovering sharper high-frequency details under the same parameter budget.

2026-09-20

IEEE/CVF Conference on Computer Vision and Pattern Recognition (published)

openreview.net

Learning Through Creation: A Hash-Free Framework for On-the-Fly Category Discovery

Bohan Zhang

Weidong Tang

Zhixiang Chi

Yi Jin

Zhenbo Li

Yanan Wu

On-the-Fly Category Discovery (OCD) aims to recognize known classes while simultaneously discovering emerging novel categories during infere… (see more)nce, using supervision only from known classes during offline training. Existing approaches rely either on fixed label supervision or on diffusion-based augmentations to enhance the backbone, yet none of them explicitly train the model to perform the discovery task required at test time. It is fundamentally unreasonable to expect a model optimized on limited labeled data to carry out a qualitatively different discovery objective during inference. This mismatch creates a clear optimization misalignment between the offline learning stage and the online discovery stage. In addition, prior methods often depend on hash-based encodings or severe feature compression, which further limits representational capacity. To address these issues, we propose Learning through Creation (LTC), a fully feature-based and hash-free framework that injects novel-category awareness directly into offline learning. At its core is a lightweight, online pseudo-unknown generator driven by kernel-energy minimization and entropy maximization (MKEE). Unlike previous methods that generate synthetic samples once before training, our generator evolves jointly with the model's dynamics and synthesizes pseudo-novel instances on-the-fly at negligible cost. These samples are incorporated through a dual max-margin objective with adaptive thresholding, strengthening the model's ability to delineate and detect unknown regions through explicit creation. Extensive experiments across seven benchmarks show that LTC consistently outperforms prior work, achieving improvements ranging from 1.5% to 13.1% in all-class accuracy.

2026-09-20

IEEE/CVF Conference on Computer Vision and Pattern Recognition (published)

openreview.net

Bridging the Modality Gap in Compositional Zero-Shot Learning via Sparse Alignment and Unimodal Memory Bank

Yang Zhang

Zhixiang Chi

Xudong Yan