arXiv subjects

Anran Zhang

Publications and source records attributed to Anran Zhang.

At least 19 recordsLinked to original sources

arXiv2026

Give the Long-tail More SPACE: Promoting Provider Fairness in Next POI Recommendation

Next point-of-interest (POI) recommendation predicts users' future destinations from historical mobility sequences and has become a key component of location-based services. However, mainstream models often concentrate exposure on a small set of popular POIs, leaving long-tail merchants systematically under-exposed. While provider fairness has recently attracted increasing attention, directly applying existing provider-fairness techniques to POI recommendation is problematic: (i) users face execution constraints; and (ii) POIs face resource supply constraints. To address this, we propose SPACE (Supply- and Physics-Aware Conditional Embedding generation), a model-agnostic framework that improves long-tail POI exposure via virtual user generation under explicit feasibility and supply control. SPACE consists of three stages: (1) community inference to capture heterogeneous user execution constraints; (2) unbalanced optimal-transport allocation to decide how many virtual users each tail POI should receive from which communities under POI-specific supply budgets; and (3) constraint-guided latent diffusion to generate POI-conditional, community-consistent virtual user embeddings. The generated user-POI pairs can be seamlessly used to train existing recommenders without modifying their architectures. Extensive experiments on three real-world datasets demonstrate that SPACE substantially improves provider fairness while maintaining and often improving recommendation accuracy across multiple backbone models. Our code is publicly available at https://github.com/Anniran1/SPACE-main.

cs.IR↗

arXiv2026

HyMobileAgent: Data-Environment Co-Scaling for Efficient GUI Agents

As large multimodal models move from understanding content to operating on digital environments, mobile GUI has emerged as a challenging and consequential testbed for digital embodied intelligence. Mobile agents operate under three coupled constraints: precise perception of complex interfaces, scalable acquisition of high-quality interaction data, and robust long-horizon decision making under compounding execution errors. This report presents HyMobileAgent, a mobile GUI agent built on Hy3.0-VL-A3B, a vision-native foundation model featuring native any-resolution input, an A3B-scale deployment budget, and a 32K context window to model extended interaction histories. Rather than relying solely on model scaling, we develop a joint data and environment centric scaling framework to address the key bottlenecks of mobile interaction. Our framework integrates a GUI perception flywheel combining mock-interface synthesis, rejection sampling, and icon-specific augmentation; a knowledge pipeline that transforms tutorial videos into structured interaction data; a million-scale action data pipeline deployed across more than 2000 sandbox and real-device instances with automated failure attribution; the PhoneWorld Mock App Factory, providing a resettable training environment with 34 mock applications and over 34000 tasks; and a structured Planning-and-Reflection mechanism with explicit dead-loop detection for reliable long-horizon execution. We also introduce a progressive training recipe consisting of mid-training, supervised fine-tuning, and reinforcement learning with task-specific reward designs.

cs.CV↗

arXiv2026

PhoneBuddy: Training Open Models for Agentic Phone Use

Phones are becoming an important execution surface for general-purpose agents, but training open models for reliable phone use remains difficult because the environment that matters at deployment, real devices running real apps, is slow, stateful, side-effectful, and hard to reset or verify, while scalable mock environments only approximate real behavior. We present PhoneBuddy, a training recipe and open-model line for agentic phone use that combines a real-app environment with a mock-app environment, PhoneWorld, which reconstructs runnable mock apps from real GUI usage structure. PhoneBuddy first builds a shared supervised fine-tuning stage from trajectories collected in both environments, then compares real-app RL against mixed RL across both environments. Across a 150-task human evaluation on real phones spanning apps, mini-apps, and cross-app workflows, task success rate improves from 36.67\% after supervised fine-tuning to 40.67\% after real-app RL and 45.33\% after mixed RL. On AndroidWorld, the same progression rises from 60.3\% to 77.2\% to 83.2\%. These results show that mock-app training is not a replacement for real-app RL, but a complementary source of scalable, resettable, and automatically checked interaction. The gains are strongest on app and mini-app tasks, while long-horizontal cross-app workflows remain an important open challenge.

cs.CL↗

arXiv2026

Robot Self-Improvement via Human-Video Dynamics Models

A central question in robot learning is how to acquire skills from the kinds of data that humans learn from: passive observation, embodied practice, and the experience of failure. Human videos provide the first of these in abundance, and prior work has shown they can initialize useful policies. Far less clear is whether they can support the second and third: whether priors extracted from human videos can ground a robot's own attempts well enough to evaluate them, correct them, and improve from them. In this work, we show that human videos can be used to learn embodiment-agnostic action, dynamics, and value representations that transfer across robot embodiments, providing the predictive foundation required for robots to autonomously improve from their own rollouts and failures. We introduce Dynamics-Guided Action Correction (DGAC), a training-free approach that leverages these adapted models to repair failed states: each failure becomes a query for which the learned models propose and rank corrective actions, turning failures into supervision for the next policy update. Across seven real-world manipulation tasks spanning both a mobile manipulator and a static manipulator arm, our approach improves success rates from 40% to 81% across multiple policy backbones, demonstrating cross-embodiment robot self-improvement from human-video priors. These results show that human priors and robot failures can be combined to enable scalable autonomous policy improvement. Project page: https://ethz-mrl.github.io/robot-self-improvement-website/.

cs.RO↗

arXiv2026

PhoneHarness: Harnessing Phone-Use Agents through Mixed GUI, CLI, and Tool Actions

Phone agents are increasingly expected to complete real mobile workflows rather than merely predict the next screen action. However, much of the current mobile-agent literature still evaluates agents primarily as GUI controllers that observe a screen, emit taps and swipes, and are scored by target app state. Real phone-use tasks are broader: they require deciding when to use app GUIs, device-side commands, or structured tools, while leaving evidence that the intended side effect actually occurred. We introduce PhoneHarness, a mixed-action benchmark and execution harness for studying phone-use agents on verifiable mobile workflows. PhoneHarness runs a device-side agent loop over GUI, CLI, and host-side tool actions, combining deterministic action routing with bounded GUI delegation and auditable execution traces. Its benchmark, PhoneHarness Bench, evaluates whether agents complete tasks with observable side effects, not only whether they produce plausible final answers. On the annotated evaluation split, PhoneHarness reaches a 75.0% pass rate, outperforming the strongest non-PhoneHarness settings by 12.9 percentage points. PhoneHarness and PhoneHarness Bench therefore play distinct but mutually dependent roles: the harness makes mixed phone workflows executable, while the benchmark measures whether agents can use that harness reliably and safely. Our findings suggest that reliable phone automation depends on action-surface routing and verifiable execution, not only visual GUI control.

cs.CL↗

arXiv2026

PhoneWorld: Scaling Phone-Use Agent Environments

A central bottleneck for phone-use agents is that controllable, reproducible environments covering real mobile behavior are hard to build at scale. Existing mobile-agent benchmarks have made important progress on evaluation, but they do not by themselves provide a scalable way to construct many new phone-use environments. We present PhoneWorld, a reusable pipeline that converts real GUI trajectories and screenshots into controllable phone-use environments, executable tasks, automatic verifiers, and training rollouts. Rather than hand-building one mobile benchmark at a time, PhoneWorld uses real trajectories to recover which screens matter, how screens connect, which interactions must change environment state, and which user goals admit automatic verification. From these signals, it builds runnable mock Android apps backed by read-only app content and mutable state, then derives executable tasks, rule-based verifiers, and training rollouts from the same environments. In its current instantiation, PhoneWorld covers 34 apps across 16 domains, spanning common consumer mobile behaviors such as search, browsing, shopping, booking, media, and social interaction. Under a fixed training budget, replacing 10K steps from an auxiliary AndroidWorld corpus in an AndroidWorld-based baseline with broad PhoneWorld supervision improves all four evaluation benchmarks at once, raising HYMobileBench by 17.7 points, AndroidControl by 6.0 points, AndroidWorld by 14.7 points, and PhoneWorld by 52.5 points. We then study two additional scaling questions: increasing the amount of PhoneWorld supervision strongly improves PhoneWorld performance, and under a fixed PhoneWorld budget, expanding app coverage yields even larger gains. Overall, PhoneWorld shifts the focus from building one mobile benchmark at a time to scaling the supply of phone-use environments themselves.

cs.CL↗

arXiv2026

Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents

When a phone-use agent avoids harm, does that show safety, or simply inability to act? Existing evaluations often cannot tell. A harmful outcome may be avoided because the agent recognized the risk and chose the safe action, or because it failed to understand the screen or execute any relevant action at all. These cases have different causes and call for different fixes, yet current benchmarks often merge them under task success, refusal, or final harmful outcome. We address this problem with PhoneSafety, a benchmark of 700 safety-critical moments drawn from real phone interactions across more than 130 apps. Each instance isolates the next decision at a risky moment and asks a simple question: does the model take the safe action, take the unsafe action, or fail to do anything useful? We evaluate eight representative phone-use agents under this framework. Our results reveal two main patterns. First, stronger general phone-use ability does not reliably imply safer choices at risky moments. Models that perform better on ordinary app tasks are not always the ones that behave more safely when the next action matters. Second, failures to do anything useful behave like a capability signal rather than a safety signal: they are concentrated in more visually and operationally demanding settings and remain stable when the evaluation protocol changes. Across models, failures split into two recurring patterns: unsafe choices in settings where the model can act but chooses wrongly, and inability to act in more visually and operationally demanding screens. Overall, a harmless outcome is not enough to count as evidence of safety. Evaluating phone-use agents requires separating unsafe judgment from inability to act.

cs.CL↗

arXiv2026

AOCI: Symbolic-Semantic Indexing for Practical Repository-Scale Code Understanding with LLMs

Large language models struggle with understanding codebases beyond a certain scale -- repositories with hundreds of thousands of lines of code. Existing methods -- retrieval, summarization, agent exploration -- each construct a different view at query time. The view varies between runs, and what persists is typically ad-hoc rather than systematic. This paper introduces AOCI (AI-Oriented Code Indexing): a symbolic-semantic repository representation -- a structured blueprint that an LLM can read in a single pass to gain a complete repository-level picture of the system's architecture, dependencies, and key design decisions before any task. An AOCI index consists of encoding rules followed by entries, with one entry per code unit (file or database table). Each entry pairs a symbolic tag with semantic content. The symbolic component provides architectural coordinates; the semantic component carries function, dependencies, and constraints. Together they form a consistent, stable representation of the entire system. Index maintenance is incremental: when code changes, only affected entries are regenerated under protocol rules. The AOCI Platform automates this process, keeping the blueprint aligned with the code. We evaluated AOCI on four projects across three LLMs and six context conditions (2,160 evaluations). AOCI outperforms all deployable baselines and ranks second only to the Oracle upper bound in overall accuracy. On 19 industrial tasks across five systems, AOCI produced zero final-state defects, while three mainstream agent-based tools introduced defects in 12 tasks and consumed 4--130$\times$ more tokens ($p < 0.001$). The advantage grows with task complexity.

cs.SE↗

arXiv2025

GOPLA: Generalizable Object Placement Learning via Synthetic Augmentation of Human Arrangement

Robots are expected to serve as intelligent assistants, helping humans with everyday household organization. A central challenge in this setting is the task of object placement, which requires reasoning about both semantic preferences (e.g., common-sense object relations) and geometric feasibility (e.g., collision avoidance). We present GOPLA, a hierarchical framework that learns generalizable object placement from augmented human demonstrations. A multi-modal large language model translates human instructions and visual inputs into structured plans that specify pairwise object relationships. These plans are then converted into 3D affordance maps with geometric common sense by a spatial mapper, while a diffusion-based planner generates placement poses guided by test-time costs, considering multi-plan distributions and collision avoidance. To overcome data scarcity, we introduce a scalable pipeline that expands human placement demonstrations into diverse synthetic training data. Extensive experiments show that our approach improves placement success rates by 30.04 percentage points over the runner-up, evaluated on positioning accuracy and physical plausibility, demonstrating strong generalization across a wide range of real-world robotic placement scenarios.

cs.RO↗

arXiv2025

Actron3D: Learning Actionable Neural Functions from Videos for Transferable Robotic Manipulation

We present Actron3D, a framework that enables robots to acquire transferable 6-DoF manipulation skills from just a few monocular, uncalibrated, RGB-only human videos. At its core lies the Neural Affordance Function, a compact object-centric representation that distills actionable cues from diverse uncalibrated videos-geometry, visual appearance, and affordance-into a lightweight neural network, forming a memory bank of manipulation skills. During deployment, we adopt a pipeline that retrieves relevant affordance functions and transfers precise 6-DoF manipulation policies via coarse-to-fine optimization, enabled by continuous queries to the multimodal features encoded in the neural functions. Experiments in both simulation and the real world demonstrate that Actron3D significantly outperforms prior methods, achieving a 14.9 percentage point improvement in average success rate across 13 tasks while requiring only 2-3 demonstration videos per task.

cs.RO↗

arXiv2025

ASRL:A robust loss function with potential for development

In this article, we proposed a partition:wise robust loss function based on the previous robust loss function. The characteristics of this loss function are that it achieves high robustness and a wide range of applicability through partition-wise design and adaptive parameter adjustment. Finally, the advantages and development potential of this loss function were verified by applying this loss function to the regression question and using five different datasets (with different dimensions, different sample numbers, and different fields) to compare with the other loss functions. The results of multiple experiments have proven the advantages of our loss function .

cs.LG↗

arXiv2025

Beyond Intermediate States: Explaining Visual Redundancy through Language

Multi-modal Large Langue Models (MLLMs) often process thousands of visual tokens, which consume a significant portion of the context window and impose a substantial computational burden. Prior work has empirically explored visual token pruning methods based on MLLMs' intermediate states (e.g., attention scores). However, they have limitations in precisely defining visual redundancy due to their inability to capture the influence of visual tokens on MLLMs' visual understanding (i.e., the predicted probabilities for textual token candidates). To address this issue, we manipulate the visual input and investigate variations in the textual output from both token-centric and context-centric perspectives, achieving intuitive and comprehensive analysis. Experimental results reveal that visual tokens with low ViT-[cls] association and low text-to-image attention scores can contain recognizable information and significantly contribute to images' overall information. To develop a more reliable method for identifying and pruning redundant visual tokens, we integrate these two perspectives and introduce a context-independent condition to identify redundant prototypes from training images, which probes the redundancy of each visual token during inference. Extensive experiments on single-image, multi-image and video comprehension tasks demonstrate the effectiveness of our method, notably achieving 90% to 110% of the performance while pruning 80% to 90% of visual tokens.

cs.CV↗

arXiv2025

VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation

Future robots are envisioned as versatile systems capable of performing a variety of household tasks. The big question remains, how can we bridge the embodiment gap while minimizing physical robot learning, which fundamentally does not scale well. We argue that learning from in-the-wild human videos offers a promising solution for robotic manipulation tasks, as vast amounts of relevant data already exist on the internet. In this work, we present VidBot, a framework enabling zero-shot robotic manipulation using learned 3D affordance from in-the-wild monocular RGB-only human videos. VidBot leverages a pipeline to extract explicit representations from them, namely 3D hand trajectories from videos, combining a depth foundation model with structure-from-motion techniques to reconstruct temporally consistent, metric-scale 3D affordance representations agnostic to embodiments. We introduce a coarse-to-fine affordance learning model that first identifies coarse actions from the pixel space and then generates fine-grained interaction trajectories with a diffusion model, conditioned on coarse actions and guided by test-time constraints for context-aware interaction planning, enabling substantial generalization to novel scenes and embodiments. Extensive experiments demonstrate the efficacy of VidBot, which significantly outperforms counterparts across 13 manipulation tasks in zero-shot settings and can be seamlessly deployed across robot systems in real-world environments. VidBot paves the way for leveraging everyday human videos to make robot learning more scalable.

cs.RO↗

arXiv2024

HACD: Harnessing Attribute Semantics and Mesoscopic Structure for Community Detection

Community detection plays a pivotal role in uncovering closely connected subgraphs, aiding various real-world applications such as recommendation systems and anomaly detection. With the surge of rich information available for entities in real-world networks, the community detection problem in attributed networks has attracted widespread attention. While previous research has effectively leveraged network topology and attribute information for attributed community detection, these methods overlook two critical issues: (i) the semantic similarity between node attributes within the community, and (ii) the inherent mesoscopic structure, which differs from the pairwise connections of the micro-structure. To address these limitations, we propose HACD, a novel attributed community detection model based on heterogeneous graph attention networks. HACD treats node attributes as another type of node, constructs attributed networks into heterogeneous graph structures and employs attribute-level attention mechanisms to capture semantic similarity. Furthermore, HACD introduces a community membership function to explore mesoscopic community structures, enhancing the robustness of detected communities. Extensive experiments demonstrate the effectiveness and efficiency of HACD, outperforming state-of-the-art methods in attributed community detection tasks. Our code is publicly available at https://github.com/Anniran1/HACD1-wsdm.

cs.SI↗

arXiv2024

Visuo-Tactile Exploration of Unknown Rigid 3D Curvatures by Vision-Augmented Unified Force-Impedance Control

Despite recent advancements in torque-controlled tactile robots, integrating them into manufacturing settings remains challenging, particularly in complex environments. Simplifying robotic skill programming for non-experts is crucial for increasing robot deployment in manufacturing. This work proposes an innovative approach, Vision-Augmented Unified Force-Impedance Control (VA-UFIC), aimed at intuitive visuo-tactile exploration of unknown 3D curvatures. VA-UFIC stands out by seamlessly integrating vision and tactile data, enabling the exploration of diverse contact shapes in three dimensions, including point contacts, flat contacts with concave and convex curvatures, and scenarios involving contact loss. A pivotal component of our method is a robust online contact alignment monitoring system that considers tactile error, local surface curvature, and orientation, facilitating adaptive adjustments of robot stiffness and force regulation during exploration. We introduce virtual energy tanks within the control framework to ensure safety and stability, effectively addressing inherent safety concerns in visuo-tactile exploration. Evaluation using a Franka Emika research robot demonstrates the efficacy of VA-UFIC in exploring unknown 3D curvatures while adhering to arbitrarily defined force-motion policies. By seamlessly integrating vision and tactile sensing, VA-UFIC offers a promising avenue for intuitive exploration of complex environments, with potential applications spanning manufacturing, inspection, and beyond.

cs.RO↗

arXiv2024

Tactile-Morph Skills: Energy-Based Control Meets Data-Driven Learning

Robotic manipulation is essential for modernizing factories and automating industrial tasks like polishing, which require advanced tactile abilities. These robots must be easily set up, safely work with humans, learn tasks autonomously, and transfer skills to similar tasks. Addressing these needs, we introduce the tactile-morph skill framework, which integrates unified force-impedance control with data-driven learning. Our system adjusts robot movements and force application based on estimated energy levels for the desired trajectory and force profile, ensuring safety by stopping if energy allocated for the control runs out. Using a Temporal Convolutional Network, we estimate the energy distribution for a given motion and force profile, enabling skill transfer across different tasks and surfaces. Our approach maintains stability and performance even on unfamiliar geometries with similar friction characteristics, demonstrating improved accuracy, zero-shot transferable performance, and enhanced safety in real-world scenarios. This framework promises to enhance robotic capabilities in industrial settings, making intelligent robots more accessible and valuable.

cs.RO↗

arXiv2024

Task-Aware Dynamic Transformer for Efficient Arbitrary-Scale Image Super-Resolution

Arbitrary-scale super-resolution (ASSR) aims to learn a single model for image super-resolution at arbitrary magnifying scales. Existing ASSR networks typically comprise an off-the-shelf scale-agnostic feature extractor and an arbitrary scale upsampler. These feature extractors often use fixed network architectures to address different ASSR inference tasks, each of which is characterized by an input image and an upsampling scale. However, this overlooks the difficulty variance of super-resolution on different inference scenarios, where simple images or small SR scales could be resolved with less computational effort than difficult images or large SR scales. To tackle this difficulty variability, in this paper, we propose a Task-Aware Dynamic Transformer (TADT) as an input-adaptive feature extractor for efficient image ASSR. Our TADT consists of a multi-scale feature extraction backbone built upon groups of Multi-Scale Transformer Blocks (MSTBs) and a Task-Aware Routing Controller (TARC). The TARC predicts the inference paths within feature extraction backbone, specifically selecting MSTBs based on the input images and SR scales. The prediction of inference path is guided by a new loss function to trade-off the SR accuracy and efficiency. Experiments demonstrate that, when working with three popular arbitrary-scale upsamplers, our TADT achieves state-of-the-art ASSR performance when compared with mainstream feature extractors, but with relatively fewer computational costs. The code will be publicly released.

cs.CV↗

arXiv2024

Orbit symmetry breaking in MXene implements enhanced soft bioelectronic implants

Bioelectronic implants with soft mechanics, biocompatibility, and excellent electrical performance enable biomedical implants to record electrophysiological signals and execute interventions within internal organs, promising to revolutionize the diagnosing, monitoring, and treatment of various pathological conditions. However, challenges remain in improving excessive impedance at the bioelectronic-tissue interface and thus the efficacy of electrophysiological signaling and intervention. Here, we devise orbit symmetry breaking in MXene (a low-cost scalability, biocompatible, and conductive 2D layered material, that we refer to as OBXene), that exhibits low bioelectronic-tissue impedance, originating from the out-of-plane charge transfer. Furthermore, the Schottky-induced piezoelectricity stemming from the asymmetric orbital configuration of OBXene facilitates interlayered charge transport in the device. In this study, we report an OBXene-based cardiac patch applied on the left ventricular epicardium of both rodent and porcine models to enable spatiotemporal epicardium mapping and pacing, while coupling the wireless and battery-free operation for long-term real-time recording and closed-loop stimulation.

physics.app-ph↗