arXiv subjects

Bowei Zhang

Publications and source records attributed to Bowei Zhang.

34 records · Page 2Linked to original sources

arXiv2025

MineStudio: A Streamlined Package for Minecraft AI Agent Development

Minecraft's complexity and diversity as an open world make it a perfect environment to test if agents can learn, adapt, and tackle a variety of unscripted tasks. However, the development and validation of novel agents in this setting continue to face significant engineering challenges. This paper presents MineStudio, an open-source software package designed to streamline the development of autonomous agents in Minecraft. MineStudio represents the first comprehensive integration of seven critical engineering components: simulator, data, model, offline pre-training, online fine-tuning, inference, and benchmark, thereby allowing users to concentrate their efforts on algorithm innovation. We provide a user-friendly API design accompanied by comprehensive documentation and tutorials. Our project is released at https://github.com/CraftJarvis/MineStudio.

cs.AI↗

arXiv2025

Bootstrapping the Cosmological Collider with Resonant Features

Signatures of heavy particles during inflation are exponentially suppressed by the Boltzmann factor when the masses are far above the Hubble scale. In more realistic scenarios, however, scale-dependent features may change this conventional picture and boost the cosmological collider signals. In this paper, we compute cosmological correlators of the primordial curvature perturbations exchanging an intermediate heavy field with periodically varying couplings. The basic setup corresponds to inflation scenarios with globally oscillating features that enjoy a discrete shift symmetry. Adopting the bootstrap approach, we derive and solve the boundary differential equations that are satisfied by the massive-exchange three-point functions. The presence of the oscillatory couplings leads to resonance-enhanced cosmological collider signals for heavy fields when the oscillating frequency exceeds the field masses. Meanwhile, the forms of these differential equations are modified, which generates new shapes of primordial non-Gaussianity as a combination of resonant features and collider signals. Based on these computations, we revisit the string-inspired model of axion monodromy inflation and point out that the cosmological correlators can become sensitive to heavy moduli fields of flux compactifications. This finding suggests a breakdown of the conventional single-field description, as the heavy moduli may not be simply integrated out but yield detectably large signals in the primordial bispectrum.

hep-th↗

arXiv2025

DCEvo: Discriminative Cross-Dimensional Evolutionary Learning for Infrared and Visible Image Fusion

Infrared and visible image fusion integrates information from distinct spectral bands to enhance image quality by leveraging the strengths and mitigating the limitations of each modality. Existing approaches typically treat image fusion and subsequent high-level tasks as separate processes, resulting in fused images that offer only marginal gains in task performance and fail to provide constructive feedback for optimizing the fusion process. To overcome these limitations, we propose a Discriminative Cross-Dimension Evolutionary Learning Framework, termed DCEvo, which simultaneously enhances visual quality and perception accuracy. Leveraging the robust search capabilities of Evolutionary Learning, our approach formulates the optimization of dual tasks as a multi-objective problem by employing an Evolutionary Algorithm (EA) to dynamically balance loss function parameters. Inspired by visual neuroscience, we integrate a Discriminative Enhancer (DE) within both the encoder and decoder, enabling the effective learning of complementary features from different modalities. Additionally, our Cross-Dimensional Embedding (CDE) block facilitates mutual enhancement between high-dimensional task features and low-dimensional fusion features, ensuring a cohesive and efficient feature integration process. Experimental results on three benchmarks demonstrate that our method significantly outperforms state-of-the-art approaches, achieving an average improvement of 9.32% in visual quality while also enhancing subsequent high-level tasks. The code is available at https://github.com/Beate-Suy-Zhang/DCEvo.

cs.CV↗

arXiv2025

QUILL: Quotation Generation Enhancement of Large Language Models

While Large language models (LLMs) have become excellent writing assistants, they still struggle with quotation generation. This is because they either hallucinate when providing factual quotations or fail to provide quotes that exceed human expectations. To bridge the gap, we systematically study how to evaluate and improve LLMs' performance in quotation generation tasks. We first establish a holistic and automatic evaluation system for quotation generation task, which consists of five criteria each with corresponding automatic metric. To improve the LLMs' quotation generation abilities, we construct a bilingual knowledge base that is broad in scope and rich in dimensions, containing up to 32,022 quotes. Moreover, guided by our critiria, we further design a quotation-specific metric to rerank the retrieved quotations from the knowledge base. Extensive experiments show that our metrics strongly correlate with human preferences. Existing LLMs struggle to generate desired quotes, but our quotation knowledge base and reranking metric help narrow this gap. Our dataset and code are publicly available at https://github.com/GraceXiaoo/QUILL.

cs.CL↗

arXiv2025

ChemHTS: Hierarchical Tool Stacking for Enhancing Chemical Agents

Large Language Models (LLMs) have demonstrated remarkable potential in scientific research, particularly in chemistry-related tasks such as molecular design, reaction prediction, and property estimation. While tool-augmented LLMs have been introduced to enhance reasoning and computation in these domains, existing approaches suffer from tool invocation errors and lack effective collaboration among diverse tools, limiting their overall performance. To address these challenges, we propose ChemHTS (Chemical Hierarchical Tool Stacking), a novel method that optimizes tool invocation pathways through a hierarchical stacking strategy. ChemHTS consists of two key stages: tool self-stacking warmup and multi-layer decision optimization, enabling LLMs to refine tool usage dynamically. We evaluate ChemHTS across four classical chemistry tasks and demonstrate its superiority over strong baselines, including GPT-4o, DeepSeek-R1, and chemistry-specific models, including ChemDFM. Furthermore, we define four distinct tool-stacking behaviors to enhance interpretability, providing insights into the effectiveness of tool collaboration. Our dataset and code are publicly available at \url{https://github.com/Chang-pw/ChemHTS}.

cs.CE↗

arXiv2025

Residual Learning towards High-fidelity Vehicle Dynamics Modeling with Transformer

The vehicle dynamics model serves as a vital component of autonomous driving systems, as it describes the temporal changes in vehicle state. In a long period, researchers have made significant endeavors to accurately model vehicle dynamics. Traditional physics-based methods employ mathematical formulae to model vehicle dynamics, but they are unable to adequately describe complex vehicle systems due to the simplifications they entail. Recent advancements in deep learning-based methods have addressed this limitation by directly regressing vehicle dynamics. However, the performance and generalization capabilities still require further enhancement. In this letter, we address these problems by proposing a vehicle dynamics correction system that leverages deep neural networks to correct the state residuals of a physical model instead of directly estimating the states. This system greatly reduces the difficulty of network learning and thus improves the estimation accuracy of vehicle dynamics. Furthermore, we have developed a novel Transformer-based dynamics residual correction network, DyTR. This network implicitly represents state residuals as high-dimensional queries, and iteratively updates the estimated residuals by interacting with dynamics state features. The experiments in simulations demonstrate the proposed system works much better than physics model, and our proposed DyTR model achieves the best performances on dynamics state residual correction task, reducing the state prediction errors of a simple 3 DoF vehicle model by an average of 92.3% and 59.9% in two dataset, respectively.

cs.RO↗

arXiv2025

MSCViT: A Small-size ViT architecture with Multi-Scale Self-Attention Mechanism for Tiny Datasets

Vision Transformer (ViT) has demonstrated significant potential in various vision tasks due to its strong ability in modelling long-range dependencies. However, such success is largely fueled by training on massive samples. In real applications, the large-scale datasets are not always available, and ViT performs worse than Convolutional Neural Networks (CNNs) if it is only trained on small scale dataset (called tiny dataset), since it requires large amount of training data to ensure its representational capacity. In this paper, a small-size ViT architecture with multi-scale self-attention mechanism and convolution blocks is presented (dubbed MSCViT) to model different scales of attention at each layer. Firstly, we introduced wavelet convolution, which selectively combines the high-frequency components obtained by frequency division with our convolution channel to extract local features. Then, a lightweight multi-head attention module is developed to reduce the number of tokens and computational costs. Finally, the positional encoding (PE) in the backbone is replaced by a local feature extraction module. Compared with the original ViT, it is parameter-efficient and is particularly suitable for tiny datasets. Extensive experiments have been conducted on tiny datasets, in which our model achieves an accuracy of 84.68% on CIFAR-100 with 14.0M parameters and 2.5 GFLOPs, without pre-training on large datasets.

cs.CV↗

arXiv2024

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents

Developing agents that can follow multimodal instructions remains a fundamental challenge in robotics and AI. Although large-scale pre-training on unlabeled datasets (no language instruction) has enabled agents to learn diverse behaviors, these agents often struggle with following instructions. While augmenting the dataset with instruction labels can mitigate this issue, acquiring such high-quality annotations at scale is impractical. To address this issue, we frame the problem as a semi-supervised learning task and introduce GROOT-2, a multimodal instructable agent trained using a novel approach that combines weak supervision with latent variable models. Our method consists of two key components: constrained self-imitating, which utilizes large amounts of unlabeled demonstrations to enable the policy to learn diverse behaviors, and human intention alignment, which uses a smaller set of labeled demonstrations to ensure the latent space reflects human intentions. GROOT-2's effectiveness is validated across four diverse environments, ranging from video games to robotic manipulation, demonstrating its robust multimodal instruction-following capabilities.

cs.AI↗

arXiv2023

JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models

Achieving human-like planning and control with multimodal observations in an open world is a key milestone for more functional generalist agents. Existing approaches can handle certain long-horizon tasks in an open world. However, they still struggle when the number of open-world tasks could potentially be infinite and lack the capability to progressively enhance task completion as game time progresses. We introduce JARVIS-1, an open-world agent that can perceive multimodal input (visual observations and human instructions), generate sophisticated plans, and perform embodied control, all within the popular yet challenging open-world Minecraft universe. Specifically, we develop JARVIS-1 on top of pre-trained multimodal language models, which map visual observations and textual instructions to plans. The plans will be ultimately dispatched to the goal-conditioned controllers. We outfit JARVIS-1 with a multimodal memory, which facilitates planning using both pre-trained knowledge and its actual game survival experiences. JARVIS-1 is the existing most general agent in Minecraft, capable of completing over 200 different tasks using control and observation space similar to humans. These tasks range from short-horizon tasks, e.g., "chopping trees" to long-horizon tasks, e.g., "obtaining a diamond pickaxe". JARVIS-1 performs exceptionally well in short-horizon tasks, achieving nearly perfect performance. In the classic long-term task of $\texttt{ObtainDiamondPickaxe}$, JARVIS-1 surpasses the reliability of current state-of-the-art agents by 5 times and can successfully complete longer-horizon and more challenging tasks. The project page is available at https://craftjarvis.org/JARVIS-1

cs.AI↗

arXiv2023

GROOT: Learning to Follow Instructions by Watching Gameplay Videos

We study the problem of building a controller that can follow open-ended instructions in open-world environments. We propose to follow reference videos as instructions, which offer expressive goal specifications while eliminating the need for expensive text-gameplay annotations. A new learning framework is derived to allow learning such instruction-following controllers from gameplay videos while producing a video instruction encoder that induces a structured goal space. We implement our agent GROOT in a simple yet effective encoder-decoder architecture based on causal transformers. We evaluate GROOT against open-world counterparts and human players on a proposed Minecraft SkillForge benchmark. The Elo ratings clearly show that GROOT is closing the human-machine gap as well as exhibiting a 70% winning rate over the best generalist agent baseline. Qualitative analysis of the induced goal space further demonstrates some interesting emergent properties, including the goal composition and complex gameplay behavior synthesis. The project page is available at https://craftjarvis-groot.github.io.

cs.AI↗

arXiv2022

Efficient Algorithms for Obnoxious Facility Location on a Line Segment or Circle

We study different restricted variations of the obnoxious facility location problem on a plane. The first is the constrained obnoxious facility location on a line segment (COFL-Line) problem. We provide an efficient algorithm for this problem that executes in $O(n ^ 2 \log k + n \log k \log (n^2 + k))$ time. Our result improves on the best known result of $O((nk)^2 \log(nk) + (n + k) \log (nk))$ time obtained by Singireddy and Basappa\cite{singireddy2022dispersing}. We also study the same problem where the facilities must be placed on a given circle (the constrained obnoxious facility location on a circle (COFL-Circ) problem). We provide an efficient algorithm for this problem that executes in $O(n ^ 2 \log k + n \log k \log (n^2 + k))$ time. Our result improves on the best known result of $O((nk)^2 \log(nk) + (n + k) \log (nk))$ time obtained by Singireddy and Basappa\cite{singireddy2022dispersing}. The third problem we study is the min-sum obnoxious facility location (MOFL) problem.We provide an efficient algorithm that executes in $O(nk\cdot α(nk) \log^3 {nk})$ time, where $α(.)$ is the inverse Ackermann function. The best known previous result is an $O(n^3k)$ time obtained by Singireddy and Basappa\cite{singireddy2022dispersing}.

cs.DS↗

arXiv2021

The Three Hundred: Cluster Dynamical States and Relaxation Time Scale

Using the galaxy clusters from The Three Hundred Project, we define a new parameter: $λ_{DS}$ to describe the dynamical state of clusters, which assumes a double-Gaussian distribution in logarithm scale for our mass-complete cluster sample at $z=0$ from the dark-matter-only (DMO) run. Therefore, the threshold for distinguishing relaxed and unrelaxed clusters is naturally determined by the crossing point of the double-Gaussian fitting which has a value of $λ_{DS} = 3.424$. By applying $λ_{DS}$ with the same parameters from the DMO run to the hydro-dynamically simulated clusters (Gadget-X run and GIZMO-SIMBA run), we investigate the effect of baryons on the cluster dynamical state. We find a weak baryon-model dependence for the $λ_{DS}$ parameter. Finally, we study the evolution of $λ_{DS}$ along with clusters mass accretion history. We notice an upper limit of halo mass change $\frac{ΔM_{200}}{M_{200}} \sim 0.12$ that don't alter the cluster dynamical state, i.e. from relaxed to unrelaxed. We define relaxation period (from the most relaxed state to disturb and relaxed again) which reflects how long the dynamical state of a cluster restores its relaxation state, and propose a correlation between this relaxation period and the strength of halo mass change $\frac{ΔM_{200}}{M_{200}}$. With the proposed fitting to such correlation, we verify the relaxation period can be estimated from $\frac{ΔM_{200}}{M_{200}}$ (including multi mass change peaks) with considerably small error.

astro-ph.CO↗

arXiv2019

Electrically Tunable Wafer-Sized Three-Dimensional Topological Insulator Thin Films Grown by Magnetron Sputtering

Three-dimensional (3D) topological insulators (TIs) are candidate materials for various electronic and spintronic devices due to their strong spin-orbit coupling and unique surface electronic structure. Rapid, low-cost preparation of large-area TI thin films compatible with conventional semiconductor technology is key to the practical applications of TIs. Here, we show that wafer-sized Bi2Te3 family TI and magnetic TI films with decent quality and well-controlled composition and properties can be prepared on amorphous SiO2/Si substrates by magnetron cosputtering. The SiO2/Si substrates enable us to electrically tune (Bi1-xSbx)2Te3 and Cr-doped (Bi1-xSbx)2Te3 TI films between p-type and n-type behavior and thus study the phenomena associated with topological surface states, such as the quantum anomalous Hall effect (QAHE). This work significantly facilitates the fabrication of TI-based devices for electronic and spintronic applications.

physics.app-ph↗

arXiv2017

Linear Time Approximation Schemes for Geometric Maximum Coverage

We study approximation algorithms for the following geometric version of the maximum coverage problem: Let $\mathcal{P}$ be a set of $n$ weighted points in the plane. Let $D$ represent a planar object, such as a rectangle, or a disk. We want to place $m$ copies of $D$ such that the sum of the weights of the points in $\mathcal{P}$ covered by these copies is maximized. For any fixed $\varepsilon>0$, we present efficient approximation schemes that can find a $(1-\varepsilon)$-approximation to the optimal solution. In particular, for $m=1$ and for the special case where $D$ is a rectangle, our algorithm runs in time $O(n\log (\frac{1}{\varepsilon}))$, improving on the previous result. For $m>1$ and the rectangular case, our algorithm runs in $O(\frac{n}{\varepsilon}\log (\frac{1}{\varepsilon})+\frac{m}{\varepsilon}\log m +m(\frac{1}{\varepsilon})^{O(\min(\sqrt{m},\frac{1}{\varepsilon}))})$ time. For a more general class of shapes (including disks, polygons with $O(1)$ edges), our algorithm runs in $O(n(\frac{1}{\varepsilon})^{O(1)}+\frac{m}ε\log m + m(\frac{1}{\varepsilon})^{O(\min(m,\frac{1}{\varepsilon^2}))})$ time.

cs.CG↗

arXiv2016

Large-area and high-quality 2D transition metal telluride

Atomically thin transitional metal ditellurides like WTe2 and MoTe2 have triggered tremendous research interests because of their intrinsic nontrivial band structure. They are also predicted to be 2D topological insulators and type-II Weyl semimetals. However, most of the studies on ditelluride atomic layers so far rely on the low-yield and time-consuming mechanical exfoliation method. Direct synthesis of large-scale monolayer ditellurides has not yet been achieved. Here, using the chemical vapor deposition (CVD) method, we demonstrate controlled synthesis of high-quality and atom-thin tellurides with lateral size over 300 μm. We found that the as-grown WTe2 maintains two different stacking sequences in the bilayer, where the atomic structure of the stacking boundary is revealed by scanning transmission electron microscope (STEM). The low-temperature transport measurements revealed a novel semimetal-to-insulator transition in WTe2 layers and an enhanced superconductivity in few-layer MoTe2. This work paves the way to the synthesis of atom-thin tellurides and also quantum spin Hall devices.

cond-mat.mtrl-sci↗

arXiv2015

Linear Time Approximation Schemes for Geometric Maximum Coverage

We study approximation algorithms for the following geometric version of the maximum coverage problem: Let P be a set of n weighted points in the plane. We want to place m a * b rectangles such that the sum of the weights of the points in P covered by these rectangles is maximized.For any fixed > 0, we present efficient approximation schemes that can find (1-ε)-approximation to the optimal solution.In particular, for m = 1, our algorithm runs in linear time O(n log( 1/ε)), improving over the previous result. For m > 1, we present an algorithm that runs in O(n/εlog(1/ε)+m(1/ε)^(O(min(sqrt(m),1/ε))) time.

cs.CG↗