Searcharxiv⌕ Search

arXiv subjects

Peng Gao

Publications and source records attributed to Peng Gao.

At least 127 records · Page 7Linked to original sources
arXiv2025

Non-Overlap-Aware Egocentric Pose Estimation for Collaborative Perception in Connected Autonomy

Egocentric pose estimation is a fundamental capability for multi-robot collaborative perception in connected autonomy, such as connected autonomous vehicles. During multi-robot operations, a robot needs to know the relative pose between itself and its teammates with respect to its own coordinates. However, different robots usually observe completely different views that contains similar objects, which leads to wrong pose estimation. In addition, it is unrealistic to allow robots to share their raw observations to detect overlap due to the limited communication bandwidth constraint. In this paper, we introduce a novel method for Non-Overlap-Aware Egocentric Pose Estimation (NOPE), which performs egocentric pose estimation in a multi-robot team while identifying the non-overlap views and satifying the communication bandwidth constraint. NOPE is built upon an unified hierarchical learning framework that integrates two levels of robot learning: (1) high-level deep graph matching for correspondence identification, which allows to identify if two views are overlapping or not, (2) low-level position-aware cross-attention graph learning for egocentric pose estimation. To evaluate NOPE, we conduct extensive experiments in both high-fidelity simulation and real-world scenarios. Experimental results have demonstrated that NOPE enables the novel capability for non-overlapping-aware egocentric pose estimation and achieves state-of-art performance compared with the existing methods. Our project page at https://hongh0.github.io/NOPE/.

cs.RO↗
arXiv2025

CodeEdu: A Multi-Agent Collaborative Platform for Personalized Coding Education

Large Language Models (LLMs) have demonstrated considerable potential in improving coding education by providing support for code writing, explanation, and debugging. However, existing LLM-based approaches generally fail to assess students' abilities, design learning plans, provide personalized material aligned with individual learning goals, and enable interactive learning. Current work mostly uses single LLM agents, which limits their ability to understand complex code repositories and schedule step-by-step tutoring. Recent research has shown that multi-agent LLMs can collaborate to solve complicated problems in various domains like software engineering, but their potential in the field of education remains unexplored. In this work, we introduce CodeEdu, an innovative multi-agent collaborative platform that combines LLMs with tool use to provide proactive and personalized education in coding. Unlike static pipelines, CodeEdu dynamically allocates agents and tasks to meet student needs. Various agents in CodeEdu undertake certain functions specifically, including task planning, personalized material generation, real-time QA, step-by-step tutoring, code execution, debugging, and learning report generation, facilitated with extensive external tools to improve task efficiency. Automated evaluations reveal that CodeEdu substantially enhances students' coding performance.

cs.MA↗
arXiv2025

Resurrect Mask AutoRegressive Modeling for Efficient and Scalable Image Generation

AutoRegressive (AR) models have made notable progress in image generation, with Masked AutoRegressive (MAR) models gaining attention for their efficient parallel decoding. However, MAR models have traditionally underperformed when compared to standard AR models. This study refines the MAR architecture to improve image generation quality. We begin by evaluating various image tokenizers to identify the most effective one. Subsequently, we introduce an improved Bidirectional LLaMA architecture by replacing causal attention with bidirectional attention and incorporating 2D RoPE, which together form our advanced model, MaskGIL. Scaled from 111M to 1.4B parameters, MaskGIL achieves a FID score of 3.71, matching state-of-the-art AR models in the ImageNet 256x256 benchmark, while requiring only 8 inference steps compared to the 256 steps of AR models. Furthermore, we develop a text-driven MaskGIL model with 775M parameters for generating images from text at various resolutions. Beyond image generation, MaskGIL extends to accelerate AR-based generation and enable real-time speech-to-image conversion. Our codes and models are available at https://github.com/synbol/MaskGIL.

cs.CV↗
arXiv2025

Mean squares of quadratic twists of the Fourier coefficients of modular forms

In this paper, we evaluate asymptotically a smoothed version of the sum \[ \displaystyle \sideset{}{^*}\sum_{d \leq X} \left( \sum_{n \leq Y} λ_f(n)\Big(\frac{8d}{n}\Big)\right)^2, \] where $\Big ( \frac{8d}{\cdot}\Big )$ is the Kronecker symbol, $\sideset{}{^*}\sum$ denotes a sum over positive odd square-free integers and $λ_f(n)$ are Fourier coefficients of a given modular form $f$.

math.NT↗
arXiv2025

Single-dislocation phonons: atomic-scale measurement and their thermal properties

Nanoscale defects such as dislocations, have a significant impact on the phonon thermal transport properties in non-metallic materials. To unravel these effects, understanding of defect phonon modes is essential. Herein, at the atomic scale, the localized phonons of individual dislocation at a Si/Ge interface are measured via monochromated electron energy loss spectroscopy in a scanning transmission electron microscope. These modes are then correlated with the local microstructure, further revealing the dislocation effects on the local thermal transport properties. The dislocation causes phonon redshift in several milli-electron-volts within about two to four nanometers of the core, where both of the strain field and Ge-segregation play roles. With the presence of dislocation, the local interfacial thermal conductance can be either enhanced or reduced, depending on the complex interaction and competition between lattice-disorder (dislocation) and element-disorder (heterointerface mixing and Ge-segregation) at the interface. These findings provide valuable insights to improve the thermal properties of thermoelectric generators and thermal management systems through proper defect engineering.

cond-mat.mtrl-sci↗
arXiv2025

Resolving Phonons in Superconductor Bi2Sr2CaCu2O8+δ at Sub-Unit-Cell Resolution

The role of phonons in cuprates remains controversial, with their complex lattice structure complicating the investigation. Here, we identify phonon modes originating from charge reservoir and superconducting layers of Bi2Sr2CaCu2O8+δ using sub-unit-cell resolved electron energy loss spectroscopy in a scanning transmission electron microscope. We reveal several phonon modes exhibiting layer-specific localization: ~78 meV in-plane modes localized in the CuO2 planes, ~42 meV hybrid (in-plane and out-of-plane) modes in the CuO2 planes, and ~38 meV hybrid modes in the BiO layers. We also observe a periodic modulation of phonon frequencies induced by the superstructure, spatially correlating with the superconducting gap variation. Our findings offer new insights into the electron-phonon coupling in cuprates, fostering deeper exploration of the microscopic linkage between lattice dynamics and superconductivity.

cond-mat.supr-con↗
arXiv2025

MLOmics: Cancer Multi-Omics Database for Machine Learning

Framing the investigation of diverse cancers as a machine learning problem has recently shown significant potential in multi-omics analysis and cancer research. Empowering these successful machine learning models are the high-quality training datasets with sufficient data volume and adequate preprocessing. However, while there exist several public data portals, including The Cancer Genome Atlas (TCGA) multi-omics initiative or open-bases such as the LinkedOmics, these databases are not off-the-shelf for existing machine learning models. In this paper, we introduce MLOmics, an open cancer multi-omics database aiming at serving better the development and evaluation of bioinformatics and machine learning models. MLOmics contains 8,314 patient samples covering all 32 cancer types with four omics types, stratified features, and extensive baselines. Complementary support for downstream analysis and bio-knowledge linking are also included to support interdisciplinary analysis.

q-bio.GN↗
arXiv2025

MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention

We introduce MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model. MiniMax-M1 is powered by a hybrid Mixture-of-Experts (MoE) architecture combined with a lightning attention mechanism. The model is developed based on our previous MiniMax-Text-01 model, which contains a total of 456 billion parameters with 45.9 billion parameters activated per token. The M1 model natively supports a context length of 1 million tokens, 8x the context size of DeepSeek R1. Furthermore, the lightning attention mechanism in MiniMax-M1 enables efficient scaling of test-time compute. These properties make M1 particularly suitable for complex tasks that require processing long inputs and thinking extensively. MiniMax-M1 is trained using large-scale reinforcement learning (RL) on diverse problems including sandbox-based, real-world software engineering environments. In addition to M1's inherent efficiency advantage for RL training, we propose CISPO, a novel RL algorithm to further enhance RL efficiency. CISPO clips importance sampling weights rather than token updates, outperforming other competitive RL variants. Combining hybrid-attention and CISPO enables MiniMax-M1's full RL training on 512 H800 GPUs to complete in only three weeks, with a rental cost of just $534,700. We release two versions of MiniMax-M1 models with 40K and 80K thinking budgets respectively, where the 40K model represents an intermediate phase of the 80K training. Experiments on standard benchmarks show that our models are comparable or superior to strong open-weight models such as the original DeepSeek-R1 and Qwen3-235B, with particular strengths in complex software engineering, tool utilization, and long-context tasks. We publicly release MiniMax-M1 at https://github.com/MiniMax-AI/MiniMax-M1.

cs.CL↗
arXiv2025

Soliton eigenvalue control by interaction of circularly polarized lights in a nonlinear fiber

We propose a physical method for controlling soliton eigenvalues in optical fibers, which is realized through the interaction between circularly polarized lights. Using this method, we not only achieve the decomposition of high-order solitons (HOSs) with different orders, but also realize physical processes of reconstructing HOSs for the first time. Compared with existing methods, our approach ensures accurate measurement of the discrete eigenvalues of HOSs while exhibiting higher decomposition efficiency. It is worth noting that the probe soliton, which induces these phenomena, plays a key role. The requirement for a moderate steepness of the probe suggests the presence of an uncertainty principle in the measurement of soliton eigenvalues, similar to the detection of microscopic particles. Our results can deepen the understanding of microscopic properties of solitons and their interaction mechanisms, and moreover provide a promising all-optical solution for the design of eigenvalue-based multiplexers and demultiplexers.

physics.optics↗
arXiv2025

OmniCaptioner: One Captioner to Rule Them All

We propose OmniCaptioner, a versatile visual captioning framework for generating fine-grained textual descriptions across a wide variety of visual domains. Unlike prior methods limited to specific image types (e.g., natural images or geometric visuals), our framework provides a unified solution for captioning natural images, visual text (e.g., posters, UIs, textbooks), and structured visuals (e.g., documents, tables, charts). By converting low-level pixel information into semantically rich textual representations, our framework bridges the gap between visual and textual modalities. Our results highlight three key advantages: (i) Enhanced Visual Reasoning with LLMs, where long-context captions of visual modalities empower LLMs, particularly the DeepSeek-R1 series, to reason effectively in multimodal scenarios; (ii) Improved Image Generation, where detailed captions improve tasks like text-to-image generation and image transformation; and (iii) Efficient Supervised Fine-Tuning (SFT), which enables faster convergence with less data. We believe the versatility and adaptability of OmniCaptioner can offer a new perspective for bridging the gap between language and visual modalities.

cs.CV↗
arXiv2025

Towards Effective and Efficient Adversarial Defense with Diffusion Models for Robust Visual Tracking

Although deep learning-based visual tracking methods have made significant progress, they exhibit vulnerabilities when facing carefully designed adversarial attacks, which can lead to a sharp decline in tracking performance. To address this issue, this paper proposes for the first time a novel adversarial defense method based on denoise diffusion probabilistic models, termed DiffDf, aimed at effectively improving the robustness of existing visual tracking methods against adversarial attacks. DiffDf establishes a multi-scale defense mechanism by combining pixel-level reconstruction loss, semantic consistency loss, and structural similarity loss, effectively suppressing adversarial perturbations through a gradual denoising process. Extensive experimental results on several mainstream datasets show that the DiffDf method demonstrates excellent generalization performance for trackers with different architectures, significantly improving various evaluation metrics while achieving real-time inference speeds of over 30 FPS, showcasing outstanding defense performance and efficiency. Codes are available at https://github.com/pgao-lab/DiffDf.

cs.CV↗
arXiv2025

Ratios conjecture of cubic $L$-functions of prime moduli

We develop $L$-functions ratios conjecture with one shift in the numerator and denominator in certain ranges for the family of cubic Hecke $L$-functions of prime moduli over the Eisenstein field using multiple Dirichlet series under the generalized Riemann hypothesis. As applications, we evaluate asymptotically the first moment of central values as well as the one-level density of the same family of $L$-functions.

math.NT↗
arXiv2025

ScalingNoise: Scaling Inference-Time Search for Generating Infinite Videos

Video diffusion models (VDMs) facilitate the generation of high-quality videos, with current research predominantly concentrated on scaling efforts during training through improvements in data quality, computational resources, and model complexity. However, inference-time scaling has received less attention, with most approaches restricting models to a single generation attempt. Recent studies have uncovered the existence of "golden noises" that can enhance video quality during generation. Building on this, we find that guiding the scaling inference-time search of VDMs to identify better noise candidates not only evaluates the quality of the frames generated in the current step but also preserves the high-level object features by referencing the anchor frame from previous multi-chunks, thereby delivering long-term value. Our analysis reveals that diffusion models inherently possess flexible adjustments of computation by varying denoising steps, and even a one-step denoising approach, when guided by a reward signal, yields significant long-term benefits. Based on the observation, we proposeScalingNoise, a plug-and-play inference-time search strategy that identifies golden initial noises for the diffusion sampling process to improve global content consistency and visual diversity. Specifically, we perform one-step denoising to convert initial noises into a clip and subsequently evaluate its long-term value, leveraging a reward model anchored by previously generated content. Moreover, to preserve diversity, we sample candidates from a tilted noise distribution that up-weights promising noises. In this way, ScalingNoise significantly reduces noise-induced errors, ensuring more coherent and spatiotemporally consistent video generation. Extensive experiments on benchmark datasets demonstrate that the proposed ScalingNoise effectively improves long video generation.

cs.LG↗
arXiv2025

EfficientQAT: Efficient Quantization-Aware Training for Large Language Models

Large language models (LLMs) are crucial in modern natural language processing and artificial intelligence. However, they face challenges in managing their significant memory requirements. Although quantization-aware training (QAT) offers a solution by reducing memory consumption through low-bit representations with minimal accuracy loss, it is impractical due to substantial training resources. To address this, we propose Efficient Quantization-Aware Training (EfficientQAT), a more feasible QAT algorithm. EfficientQAT involves two consecutive phases: Block-wise training of all parameters (Block-AP) and end-to-end training of quantization parameters (E2E-QP). To the best of our knowledge, Block-AP is the first method to enable direct training of all parameters in a block-wise manner, reducing accuracy loss in low-bit scenarios by enhancing the solution space during optimization. E2E-QP then trains only the quantization parameters (step sizes) end-to-end, further improving the performance of quantized models by considering interactions among all sub-modules. Extensive experiments demonstrate that EfficientQAT outperforms previous quantization methods across a range of models, including base LLMs, instruction-tuned LLMs, and multimodal LLMs, with scales from 7B to 70B parameters at various quantization bits. For instance, EfficientQAT obtains a 2-bit Llama-2-70B model on a single A100-80GB GPU in 41 hours, with less than 3 points accuracy degradation compared to the full precision (69.48 vs. 72.41). Code is available at https://github.com/OpenGVLab/EfficientQAT.

cs.LG↗
arXiv2025

Towards Adaptive Meta-Gradient Adversarial Examples for Visual Tracking

In recent years, visual tracking methods based on convolutional neural networks and Transformers have achieved remarkable performance and have been successfully applied in fields such as autonomous driving. However, the numerous security issues exposed by deep learning models have gradually affected the reliable application of visual tracking methods in real-world scenarios. Therefore, how to reveal the security vulnerabilities of existing visual trackers through effective adversarial attacks has become a critical problem that needs to be addressed. To this end, we propose an adaptive meta-gradient adversarial attack (AMGA) method for visual tracking. This method integrates multi-model ensembles and meta-learning strategies, combining momentum mechanisms and Gaussian smoothing, which can significantly enhance the transferability and attack effectiveness of adversarial examples. AMGA randomly selects models from a large model repository, constructs diverse tracking scenarios, and iteratively performs both white- and black-box adversarial attacks in each scenario, optimizing the gradient directions of each model. This paradigm minimizes the gap between white- and black-box adversarial attacks, thus achieving excellent attack performance in black-box scenarios. Extensive experimental results on large-scale datasets such as OTB2015, LaSOT, and GOT-10k demonstrate that AMGA significantly improves the attack performance, transferability, and deception of adversarial examples. Codes and data are available at https://github.com/pgao-lab/AMGA.

cs.CV↗
arXiv2025

Phase-based stimulated emission depletion (pSTED) magnetic particle imaging

Magnetic particle imaging (MPI) is an in vivo method to detect magnetic nanoparticles for cell tracking, vascular imaging, and molecular target imaging without ionizing radiation. Current magnetic particle imaging is accomplished by forming an field-free line (FFL) through a gradient selection field. By translating and rotating FFL under excitation and drive fields, the harmonic complex signal of a point source forms a Lorentzian-shape point spread function on the plane perpendicular to FFL. The Lorentzian PSF has a finite size and limited resolution due to the non-sharp Langevin function and weak selection field. This study proposes a donut-shaped focal spot by borrowing the stimulated emission depletion (STED) fluorescence microscopy principle. The influence of the gradient selection field on the relaxation time of magnetic particles determines the nonlinear phase shift of the harmonic complex signals, resulting in the formation of a donut-shaped focal spot. By subtracting the donut-shaped focal spot from the Lorentzian focal spot, the STED focal spot size was reduced by up to 4 times beyond the Langevin magnetization resolution barrier. In human brain FFL-based MPI scanner, the donut-shaped focal spot can be used to reconstruct images with super-resolution and super-sensitivity through the deconvoution of the STED focal spot and filtered backprojection algorithm.

physics.med-ph↗
arXiv2025

Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding

Visual Document Understanding has become essential with the increase of text-rich visual content. This field poses significant challenges due to the need for effective integration of visual perception and textual comprehension, particularly across diverse document types with complex layouts. Moreover, existing fine-tuning datasets for this domain often fall short in providing the detailed contextual information for robust understanding, leading to hallucinations and limited comprehension of spatial relationships among visual elements. To address these challenges, we propose an innovative pipeline that utilizes adaptive generation of markup languages, such as Markdown, JSON, HTML, and TiKZ, to build highly structured document representations and deliver contextually-grounded responses. We introduce two fine-grained structured datasets: DocMark-Pile, comprising approximately 3.8M pretraining data pairs for document parsing, and DocMark-Instruct, featuring 624k fine-tuning data annotations for grounded instruction following. Extensive experiments demonstrate that our proposed model significantly outperforms existing state-of-theart MLLMs across a range of visual document understanding benchmarks, facilitating advanced reasoning and comprehension capabilities in complex visual scenarios. Our code and models are released at https://github. com/Euphoria16/DocMark.

cs.CV↗