Researcher profile

Yuhao Zhou

Yuhao Zhou contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate

Artificial Intelligence Computer Vision Computation and Language astro-ph.SR eess.SY Machine Learning Systems and Control Distributed, Parallel, and Cluster Computing eess.AS math.OC Robotics

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author

17works

0followers

11topics

4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

COCONUT: A coronal model with an energy decomposition strategy

In this paper, we propose an energy decomposition method combined with an HLL Riemann solver that includes an additional dissipation term in the energy equation to improve the numerical stability of the fully implicit, time-evolving coronal model COCONUT and extend its applicability to solar-maximum phases. In MHD simulations that evolve conservative variables in time, the thermal pressure is typically computed by subtracting the magnetic and kinetic energies from the total energy. In low-beta (the ratio of thermal to magnetic pressure; $< 10^{-3}$) regions, discretization errors of magnetic energy can be comparable to the thermal pressure, potentially leading to negative thermal pressure and causing the simulation to crash. Therefore, we update the decomposed energy, excluding the magnetic energy, at each time step. It avoids subtracting a large magnetic energy from the total energy to obtain a very small thermal pressure in low-$β$ regions, thereby improving the numerical stability of MHD models. We validate the algorithm using a time-evolving solar-maximum Carrington rotation simulation in 2025, which the previous code failed to run to completion. We also perform quasi-steady-state coronal simulations and 2D benchmark tests to further assess the algorithm's performance. The simulation results show that the algorithm produces results nearly identical to those obtained using the traditional full energy equation during solar minimum, while significantly improving COCONUT's ability to simulate coronal evolution under strong magnetic fields, even including fields exceeding 100 Gauss with $β<10^{-3}$. This method provides a promising approach for performing quasi-realistic coronal simulations during solar maxima.

preprint2026arXiv

FlowSearch: Advancing deep research with dynamic structured knowledge flow

Deep research is an inherently challenging task that demands both breadth and depth of thinking. It involves navigating diverse knowledge spaces and reasoning over complex, multi-step dependencies, which presents substantial challenges for agentic systems. To address this, we propose FlowSearch, a multi-agent framework that actively constructs and evolves a dynamic structured knowledge flow to drive subtask execution and reasoning. FlowSearch is capable of strategically planning and expanding the knowledge flow to enable parallel exploration and hierarchical task decomposition, while also adjusting the knowledge flow in real time based on feedback from intermediate reasoning outcomes and insights. FlowSearch achieves competitive performance on both general and scientific benchmarks, including GAIA, HLE, GPQA and TRQA, demonstrating its effectiveness in multi-disciplinary research scenarios and its potential to advance scientific discovery. The code is available at https://github.com/InternScience/InternAgent.

preprint2026arXiv

ForgeVLA: Federated Vision-Language-Action Learning without Language Annotations

Vision-Language-Action (VLA) models hold great promise for general-purpose robotic intelligence, yet scaling up such models is severely bottlenecked by the high cost of acquiring annotated training data. Fortunately, vision-equipped robots deployed across various domains already produce abundant vision-action pairs that can be leveraged to scale up VLA training more efficiently. However, these raw data cannot be centrally aggregated due to various constraints and also exhibit severe heterogeneity. To address these challenges, in this paper, we propose ForgeVLA, a federated VLA training framework that learns VLA models from distributed vision-action pairs without centralizing raw data or requiring manual annotations. Specifically, each client in ForgeVLA is equipped with an embodied instruction classifier that maps vision-action pairs to a predefined instruction set, recovering the missing language modality and forming complete vision-language-action triplets. Beyond triplet construction, we also identify vision-language feature collapse as a critical challenge that has been largely overlooked in prior federated VLA research. To mitigate this issue, ForgeVLA combines a client-side contrastive planning loss with a server-side adaptive aggregation strategy to learn task-discriminative representations efficiently. Extensive experiments across multiple benchmarks show that ForgeVLA significantly outperforms other baselines, and ablation studies further validate the contribution of each component.

preprint2026arXiv

NICE FACT: Diagnosing and Calibrating VLMs in Quantitative Reasoning for Kinematic Physics

The ability to derive precise spatial and physical insights is a cornerstone of vision-language models (VLMs), yet their poor performances in related spatial intelligence tasks such as physical reasoning remain a fundamental barrier. The community critically lacks a scientific analysis revealing whether VLMs faithfully reach answers or plausibly make guesses. This work aims to provide a fundamental understanding of how VLMs perceive the physical world, and utilize physical laws, while assessing the reliability of model confidence. We propose NICE and FACT, a dual-diagnostic paradigm that explicitly decomposes quantitative reasoning for kinematic physics: FACT diagnoses visual fidelity, physical law comprehension, and temporal grounding. NICE studies our novel neighborhood-informed calibration method and novel metrics to evaluate and calibrate confidence reliability. Evaluated across 6 latest state-of-the-art VLMs, we uncover that models fail to identify visual preconditions or utilize necessary physical laws to reach answers. This work highlights and establishes a standardized diagnostic paradigm to guide the development of faithful, physically-grounded VLMs.

preprint2026arXiv

ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning

Large language models can fail in critic interaction not only by answering incorrectly, but also by abandoning an initially correct scientific solution after user criticism. This is especially risky in scientific reasoning, where user criticism can turn a valid answer into an incorrect one. We frame critic interaction as an inter-turn correctness-transition problem rather than a final-answer accuracy problem, and identify three challenges: transition awareness, decoupling useful correction from harmful sycophancy, and scalable rollout. We propose ReCrit, a transition-aware reinforcement learning framework that decomposes Initial-to-Critic behavior into four quadrants: Correction, Sycophancy, Robustness, and Boundary. ReCrit rewards correction and robustness, penalizes sycophancy, and treats persistent errors as weak boundary signals. To make interaction training practical, ReCrit further uses dynamic asynchronous rollout with tail-adaptive completion to reduce rollout waiting. On three scientific reasoning benchmarks, ChemBench, TRQA, and EarthSE, ReCrit improves average Critic accuracy from 38.15 to 51.49 on Qwen3.5-4B and from 45.40 to 55.59 on Qwen3.5-9B. Ablations show that final-answer rewards provide little interaction-level gain, while transition-aware rewards and quadrant weighting produce more distinguishable training signals and larger net Critic-stage improvement. The code is available at https://github.com/black-yt/ReCrit .

preprint2026arXiv

SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence

We introduce SciEvalKit, a unified benchmarking toolkit designed to evaluate AI models for science across a broad range of scientific disciplines and task capabilities. Unlike general-purpose evaluation platforms, SciEvalKit focuses on the core competencies of scientific intelligence, including Scientific Multimodal Perception, Scientific Multimodal Reasoning, Scientific Multimodal Understanding, Scientific Symbolic Reasoning, Scientific Code Generation, Science Hypothesis Generation and Scientific Knowledge Understanding. It supports six major scientific domains, spanning from physics and chemistry to astronomy and materials science. SciEvalKit builds a foundation of expert-grade scientific benchmarks, curated from real-world, domain-specific datasets, ensuring that tasks reflect authentic scientific challenges. The toolkit features a flexible, extensible evaluation pipeline that enables batch evaluation across models and datasets, supports custom model and dataset integration, and provides transparent, reproducible, and comparable results. By bridging capability-based evaluation and disciplinary diversity, SciEvalKit offers a standardized yet customizable infrastructure to benchmark the next generation of scientific foundation models and intelligent agents. The toolkit is open-sourced and actively maintained to foster community-driven development and progress in AI4Science.

preprint2026arXiv

What Makes a Good Speech Tokenizer for LLM-Centric Speech Generation? A Systematic Study

Speech-language models (SLMs) offer a promising path toward unifying speech and text understanding and generation. However, challenges remain in achieving effective cross-modal alignment and high-quality speech generation. In this work, we systematically investigate the role of speech tokenizer designs in LLM-centric SLMs, augmented by speech heads and speaker modeling. We compare coupled, semi-decoupled, and fully decoupled speech tokenizers under a fair SLM framework and find that decoupled tokenization significantly improves alignment and synthesis quality. To address the information density mismatch between speech and text, we introduce multi-token prediction (MTP) into SLMs, enabling each hidden state to decode multiple speech tokens. This leads to up to 12$\times$ faster decoding and a substantial drop in word error rate (from 6.07 to 3.01). Furthermore, we propose a speaker-aware generation paradigm and introduce RoleTriviaQA, a large-scale role-playing knowledge QA benchmark with diverse speaker identities. Experiments demonstrate that our methods enhance both knowledge understanding and speaker consistency.

preprint2022arXiv

A Semismooth Newton based Augmented Lagrangian Method for Nonsmooth Optimization on Matrix Manifolds

This paper is devoted to studying an augmented Lagrangian method for solving a class of manifold optimization problems, which have nonsmooth objective functions and nonlinear constraints. Under the constant positive linear dependence condition on manifolds, we show that the proposed method converges to a stationary point of the nonsmooth manifold optimization problem. Moreover, we propose a globalized semismooth Newton method to solve the augmented Lagrangian subproblem on manifolds efficiently. The local superlinear convergence of the manifold semismooth Newton method is also established under some suitable conditions. We also prove that the semismoothness on submanifolds can be inherited from that in the ambient manifold. Finally, numerical experiments on compressed modes and (constrained) sparse principal component analysis illustrate the advantages of the proposed method.

preprint2022arXiv

DeFTA: A Plug-and-Play Decentralized Replacement for FedAvg

Federated learning (FL) is identified as a crucial enabler for large-scale distributed machine learning (ML) without the need for local raw dataset sharing, substantially reducing privacy concerns and alleviating the isolated data problem. In reality, the prosperity of FL is largely due to a centralized framework called FedAvg, in which workers are in charge of model training and servers are in control of model aggregation. However, FedAvg's centralized worker-server architecture has raised new concerns, be it the low scalability of the cluster, the risk of data leakage, and the failure or even defection of the central server. To overcome these problems, we propose Decentralized Federated Trusted Averaging (DeFTA), a decentralized FL framework that serves as a plug-and-play replacement for FedAvg, instantly bringing better security, scalability, and fault-tolerance to the federated learning process after installation. In principle, it fundamentally resolves the above-mentioned issues from an architectural perspective without compromises or tradeoffs, primarily consisting of a new model aggregating formula with theoretical performance analysis, and a decentralized trust system (DTS) to greatly improve system robustness. Note that since DeFTA is an alternative to FedAvg at the framework level, \textit{prevalent algorithms published for FedAvg can be also utilized in DeFTA with ease}. Extensive experiments on six datasets and six basic models suggest that DeFTA not only has comparable performance with FedAvg in a more realistic setting, but also achieves great resilience even when 66% of workers are malicious. Furthermore, we also present an asynchronous variant of DeFTA to endow it with more powerful usability.

preprint2022arXiv

Fuse Local and Global Semantics in Representation Learning

We propose Fuse Local and Global Semantics in Representation Learning (FLAGS) to generate richer representations. FLAGS aims at extract both global and local semantics from images to benefit various downstream tasks. It shows promising results under common linear evaluation protocol. We also conduct detection and segmentation on PASCAL VOC and COCO to show the representations extracted by FLAGS are transferable.

preprint2021arXiv

Coronal rain in randomly heated arcades

Adopting the MPI-AMRVAC code, we present a 2.5-dimensional magnetohydrodynamic (MHD) simulation, which includes thermal conduction and radiative cooling, to investigate the formation and evolution of the coronal rain phenomenon. We perform the simulation in initially linear force-free magnetic fields which host chromospheric, transition region, and coronal plasma, with turbulent heating localized on their footpoints. Due to thermal instability, condensations start to occur at the loop top, and rebound shocks are generated by the siphon inflows. Condensations fragment into smaller blobs moving downwards and as they hit the lower atmosphere, concurrent upflows are triggered. Larger clumps show us clear "coronal rain showers" as dark structures in synthetic EUV hot channels and bright blobs with cool cores in the 304 Å channel, well resembling real observations. Following coronal rain dynamics for more than 10 hours, we carry out a statistical study of all coronal rain blobs to quantify their widths, lengths, areas, velocity distributions, and other properties. The coronal rain shows us continuous heating-condensation cycles, as well as cycles in EUV emissions. Compared to previous studies adopting steady heating, the rain happens faster and in more erratic cycles. Although most blobs are falling downward, upward-moving blobs exist at basically every moment. We also track the movement of individual blobs to study their dynamics and the forces driving their movements. The blobs have a prominence-corona transition-region-like structure surrounding them, and their movements are dominated by the pressure evolution in the very dynamic loop system.

preprint2021arXiv

Design of a Flying Humanoid Robot Based on Thrust Vector Control

Achieving short-distance flight helps improve the efficiency of humanoid robots moving in complex environments (e.g., crossing large obstacles or reaching high places) for rapid emergency missions. This study proposes a design of a flying humanoid robot named Jet-HR2. The robot has 10 joints driven by brushless motors and harmonic drives for locomotion. To overcome the challenge of the stable-attitude takeoff in small thrust-to-weight conditions, the robot was designed based on the concept of thrust vectoring. The propulsion system consists of four ducted fans, that is, two fixed on the waist of the robot and the other two mounted on the feet, for thrust vector control. The thrust vector is controlled by adjusting the attitude of the foot during the flight. A simplified model and control strategies are proposed to solve the problem of attitude instability caused by mass errors and joint position errors during takeoff. The experimental results show that the robot's spin and dive behaviors during takeoff were effectively suppressed by controlling the thrust vector of the ducted fan on the foot. The robot successfully achieved takeoff at a thrust-to-weight ratio of 1.17 (17 kg / 20 kg) and maintained a stable attitude, reaching a takeoff height of over 1000 mm.

preprint2020arXiv

Deriving AC OPF Solutions via Proximal Policy Optimization for Secure and Economic Grid Operation

Optimal power flow (OPF) is a very fundamental but vital optimization problem in the power system, which aims at solving a specific objective function (ex.: generator costs) while maintaining the system in the stable and safe operations. In this paper, we adopted the start-of-the-art artificial intelligence (AI) techniques to train an agent aiming at solving the AC OPF problem, where the nonlinear power balance equations are considered. The modified IEEE-14 bus system were utilized to validate the proposed approach. The testing results showed a great potential of adopting AI techniques in the power system operations.

preprint2020arXiv

Learning to Simulate Dynamic Environments with GameGAN

Simulation is a crucial component of any robotic system. In order to simulate correctly, we need to write complex rules of the environment: how dynamic agents behave, and how the actions of each of the agents affect the behavior of others. In this paper, we aim to learn a simulator by simply watching an agent interact with an environment. We focus on graphics games as a proxy of the real environment. We introduce GameGAN, a generative model that learns to visually imitate a desired game by ingesting screenplay and keyboard actions during training. Given a key pressed by the agent, GameGAN "renders" the next screen using a carefully designed generative adversarial network. Our approach offers key advantages over existing work: we design a memory module that builds an internal map of the environment, allowing for the agent to return to previously visited locations with high visual consistency. In addition, GameGAN is able to disentangle static and dynamic components within an image making the behavior of the model more interpretable, and relevant for downstream tasks that require explicit reasoning over dynamic elements. This enables many interesting applications such as swapping different components of the game to build new games that do not exist.

preprint2020arXiv

Nonparametric Score Estimators

Estimating the score, i.e., the gradient of log density function, from a set of samples generated by an unknown distribution is a fundamental task in inference and learning of probabilistic models that involve flexible yet intractable densities. Kernel estimators based on Stein's methods or score matching have shown promise, however their theoretical properties and relationships have not been fully-understood. We provide a unifying view of these estimators under the framework of regularized nonparametric regression. It allows us to analyse existing estimators and construct new ones with desirable properties by choosing different hypothesis spaces and regularizers. A unified convergence analysis is provided for such estimators. Finally, we propose score estimators based on iterative regularization that enjoy computational benefits from curl-free kernels and fast convergence.

preprint2020arXiv

Visual Localization Using Semantic Segmentation and Depth Prediction

In this paper, we propose a monocular visual localization pipeline leveraging semantic and depth cues. We apply semantic consistency evaluation to rank the image retrieval results and a practical clustering technique to reject estimation outliers. In addition, we demonstrate a substantial performance boost achieved with a combination of multiple feature extractors. Furthermore, by using depth prediction with a deep neural network, we show that a significant amount of falsely matched keypoints are identified and eliminated. The proposed pipeline outperforms most of the existing approaches at the Long-Term Visual Localization benchmark 2020.

preprint2019arXiv

Optimal Power Flow in Hybrid AC and Multi-terminal HVDC Networks with Offshore Wind Farm Integration Based on Semidefinite Programming

Multi-terminal high voltage direct current (MTHVDC) technology is a promising technology for the offshore wind farm integration, which requires the new control and operation scheme. Therefore, the optimal power flow problem for this system is important to achieve the optimal economic operation. In this paper, convex relaxation model based on semidefinite programming for the MT-HVDC system considering DC/DC converters is proposed to solve the optimal power flow problem. A hybrid AC and MT-HVDC system for offshore wind farm integration is used for the test. The simulation results validate the effectiveness of the proposed model and guarantee that the global optimum solution is achieved.

Institution

Affiliation not imported yet

This author record came from a source that does not expose affiliation metadata. Once the author claims the profile or we enrich the record from another provider, this section will link to the concrete institution.

Topic footprint