arXiv subjects

Peng Xu

Publications and source records attributed to Peng Xu.

At least 127 records · Page 7Linked to original sources

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

SurveillanceVQA-589K: A Benchmark for Comprehensive Surveillance Video-Language Understanding with Large Models

Understanding surveillance video content remains a critical yet underexplored challenge in vision-language research, particularly due to its real-world complexity, irregular event dynamics, and safety-critical implications. In this work, we introduce SurveillanceVQA-589K, the largest open-ended video question answering benchmark tailored to the surveillance domain. The dataset comprises 589,380 QA pairs spanning 12 cognitively diverse question types, including temporal reasoning, causal inference, spatial understanding, and anomaly interpretation, across both normal and abnormal video scenarios. To construct the benchmark at scale, we design a hybrid annotation pipeline that combines temporally aligned human-written captions with Large Vision-Language Model-assisted QA generation using prompt-based techniques. We also propose a multi-dimensional evaluation protocol to assess contextual, temporal, and causal comprehension. We evaluate eight LVLMs under this framework, revealing significant performance gaps, especially in causal and anomaly-related tasks, underscoring the limitations of current models in real-world surveillance contexts. Our benchmark provides a practical and comprehensive resource for advancing video-language understanding in safety-critical applications such as intelligent monitoring, incident analysis, and autonomous decision-making.

cs.CV↗

arXiv2025

Compact Binary Coalescence Gravitational Wave Signals Counting and Separation

As next-generation gravitational-wave (GW) observatories approach unprecedented sensitivities, the need for robust methods to analyze increasingly complex, overlapping signals becomes ever more pressing. Existing matched-filtering approaches and deep-learning techniques can typically handle only one or two concurrent signals, offering limited adaptability to more varied and intricate superimposed waveforms. To overcome these constraints, we present the UnMixFormer, an attention-based architecture that not only identifies the unknown number of concurrent compact binary coalescence GW events but also disentangles their individual waveforms through a multi-decoder architecture, even when confronted with five overlapping signals. Our UnMixFormer is capable of capturing both short- and long-range dependencies by modeling them in a dual-path manner, while also enhancing periodic feature representation by incorporating Fourier Analysis Networks. Our approach adeptly processes binary black hole, binary neutron star, and neutron star-black hole systems over extended time series data (16,384 samples). When evaluating on synthetic data with signal-to-noise ratios (SNR) ranging from 10 to 50, our method achieves 99.89% counting accuracy, a mean overlap of 0.9831 between separated waveforms and templates, and robust generalization ability to waveforms with spin precession, orbital eccentricity, and higher modes, marking a substantial advance in the precision and versatility of GW data analysis.

gr-qc↗

arXiv2025

Achieving Human Level Competitive Robot Table Tennis

Achieving human-level speed and performance on real world tasks is a north star for the robotics research community. This work takes a step towards that goal and presents the first learned robot agent that reaches amateur human-level performance in competitive table tennis. Table tennis is a physically demanding sport which requires human players to undergo years of training to achieve an advanced level of proficiency. In this paper, we contribute (1) a hierarchical and modular policy architecture consisting of (i) low level controllers with their detailed skill descriptors which model the agent's capabilities and help to bridge the sim-to-real gap and (ii) a high level controller that chooses the low level skills, (2) techniques for enabling zero-shot sim-to-real including an iterative approach to defining the task distribution that is grounded in the real-world and defines an automatic curriculum, and (3) real time adaptation to unseen opponents. Policy performance was assessed through 29 robot vs. human matches of which the robot won 45% (13/29). All humans were unseen players and their skill level varied from beginner to tournament level. Whilst the robot lost all matches vs. the most advanced players it won 100% matches vs. beginners and 55% matches vs. intermediate players, demonstrating solidly amateur human-level performance. Videos of the matches can be viewed at https://sites.google.com/view/competitive-robot-table-tennis

cs.RO↗

arXiv2025

Effective Index Construction Algorithm for Optimal $(k,η)$-cores Computation

Computing $(k,η)$-cores from uncertain graphs is a fundamental problem in uncertain graph analysis. UCF-Index is the state-of-the-art resolution to support $(k,η)$-core queries, allowing the $(k,η)$-core for any combination of $k$ and $η$ to be computed in an optimal time. However, this index constructed by current algorithm is usually incorrect. During decomposition, the key is to obtain the $k$-probabilities of its neighbors when the vertex with minimum $k$-probability is deleted. Current method uses recursive floating-point division to update it, which can lead to serious errors. We propose a correct and efficient index construction algorithm to address this issue. Firstly, we propose tight bounds on the $k$-probabilities of the vertices that need to be updated, and the accurate $k$-probabilities are recalculated in an on-demand manner. Secondly, vertices partitioning and progressive refinement strategy is devised to search the vertex with the minimum $k$-probability, thereby reducing initialization overhead for each $k$ and avoiding unnecessary recalculations. Finally, extensive experiments demonstrate the efficiency and scalability of our approach.

cs.DS↗

arXiv2025

Embedding Empirical Distributions for Computing Optimal Transport Maps

Distributional data have become increasingly prominent in modern signal processing, highlighting the necessity of computing optimal transport (OT) maps across multiple probability distributions. Nevertheless, recent studies on neural OT methods predominantly focused on the efficient computation of a single map between two distributions. To address this challenge, we introduce a novel approach to learning transport maps for new empirical distributions. Specifically, we employ the transformer architecture to produce embeddings from distributional data of varying length; these embeddings are then fed into a hypernetwork to generate neural OT maps. Various numerical experiments were conducted to validate the embeddings and the generated OT maps. The model implementation and the code are provided on https://github.com/jiangmingchen/HOTET.

cs.LG↗

arXiv2025

EDA-Q: Electronic Design Automation for Superconducting Quantum Chip

Electronic Design Automation (EDA) plays a crucial role in classical chip design and significantly influences the development of quantum chip design. However, traditional EDA tools cannot be directly applied to quantum chip design due to vast differences compared to the classical realm. Several EDA products tailored for quantum chip design currently exist, yet they only cover partial stages of the quantum chip design process instead of offering a fully comprehensive solution. Additionally, they often encounter issues such as limited automation, steep learning curves, challenges in integrating with actual fabrication processes, and difficulties in expanding functionality. To address these issues, we developed a full-stack EDA tool specifically for quantum chip design, called EDA-Q. The design workflow incorporates functionalities present in existing quantum EDA tools while supplementing critical design stages such as device mapping and fabrication process mapping, which users expect. EDA-Q utilizes a unique architecture to achieve exceptional scalability and flexibility. The integrated design mode guarantees algorithm compatibility with different chip components, while employing a specialized interactive processing mode to offer users a straightforward and adaptable command interface. Application examples demonstrate that EDA-Q significantly reduces chip design cycles, enhances automation levels, and decreases the time required for manual intervention. Multiple rounds of testing on the designed chip have validated the effectiveness of EDA-Q in practical applications.

cs.ET↗

arXiv2025

Bandwidth-Efficient Two-Server ORAMs with O(1) Client Storage

Oblivious RAM (ORAM) allows a client to securely retrieve elements from outsourced servers without leakage about the accessed elements or their virtual addresses. Two-server ORAM, designed for secure two-party RAM computation, stores data across two non-colluding servers. However, many two-server ORAM schemes suffer from excessive local storage or high bandwidth costs. To serve lightweight clients, it is crucial for ORAM to achieve concretely efficient bandwidth while maintaining O(1) local storage. Hence, this paper presents two new client-friendly two-server ORAM schemes that achieve practical logarithmic bandwidth under O(1) local storage, while incurring linear symmetric key computations. The core design features a hierarchical structure and a pairwise-area setting for the elements and their tags. Accordingly, we specify efficient read-only and write-only private information retrieval (PIR) algorithms in our schemes to ensure obliviousness in accessing two areas respectively, so as to avoid the necessity of costly shuffle techniques in previous works. We empirically evaluate our schemes against LO13 (TCC'13), AFN17 (PKC'17), and KM19 (PKC'19) in terms of both bandwidth and time cost. The results demonstrate that our schemes reduce bandwidth by approximately 2-4x compared to LO13, and by 16-64x compared to AFN17 and KM19. For a database of size 2^14 blocks, our schemes are over 64x faster than KM19, while achieving similar performance to LO13 and AFN17 in the WAN setting, with a latency of around 1 second.

cs.CR↗

arXiv2025

Deep Learning in Concealed Dense Prediction

Deep learning is developing rapidly and handling common computer vision tasks well. It is time to pay attention to more complex vision tasks, as model size, knowledge, and reasoning capabilities continue to improve. In this paper, we introduce and review a family of complex tasks, termed Concealed Dense Prediction (CDP), which has great value in agriculture, industry, etc. CDP's intrinsic trait is that the targets are concealed in their surroundings, thus fully perceiving them requires fine-grained representations, prior knowledge, auxiliary reasoning, etc. The contributions of this review are three-fold: (i) We introduce the scope, characteristics, and challenges specific to CDP tasks and emphasize their essential differences from generic vision tasks. (ii) We develop a taxonomy based on concealment counteracting to summarize deep learning efforts in CDP through experiments on three tasks. We compare 25 state-of-the-art methods across 12 widely used concealed datasets. (iii) We discuss the potential applications of CDP in the large model era and summarize 6 potential research directions. We offer perspectives for the future development of CDP by constructing a large-scale multimodal instruction fine-tuning dataset, CvpINST, and a concealed visual perception agent, CvpAgent.

cs.CV↗

arXiv2025

Streamlining Biomedical Research with Specialized LLMs

In this paper, we propose a novel system that integrates state-of-the-art, domain-specific large language models with advanced information retrieval techniques to deliver comprehensive and context-aware responses. Our approach facilitates seamless interaction among diverse components, enabling cross-validation of outputs to produce accurate, high-quality responses enriched with relevant data, images, tables, and other modalities. We demonstrate the system's capability to enhance response precision by leveraging a robust question-answering model, significantly improving the quality of dialogue generation. The system provides an accessible platform for real-time, high-fidelity interactions, allowing users to benefit from efficient human-computer interaction, precise retrieval, and simultaneous access to a wide range of literature and data. This dramatically improves the research efficiency of professionals in the biomedical and pharmaceutical domains and facilitates faster, more informed decision-making throughout the R\&D process. Furthermore, the system proposed in this paper is available at https://synapse-chat.patsnap.com.

cs.CL↗

arXiv2025

Voltage and power-frequency electric field measurements with Rydberg-atom interferometry

We present a Rydberg-atom interferometry-based technique for voltage measurement between electrodes embedded in an atomic vapor cell, enabling the detection of weak voltages ($<0.1$V) and unambiguous discrimination between positive and negative polarities. This makes up for the shortcomings of measurements based on the Stark effect, which suffer from quadratic field dependence (limiting sensitivity in weak-field regimes) and incapable of distinguishing the electric field direction. Furthermore, this method extends naturally to power-frequency (PF) electric field measurements by exploiting the quasi-static approximation-valid given the PF field's characteristic timescale ($\sim10^{-2}$s) vastly exceeds the interferometric measurement duration ($\sim10^{-6}$s). Crucially, our protocol provides instantaneous PF field reconstruction, providing comprehensive information including amplitude, frequency and phase. These advancements have direct implications for traceable voltage measurements and non-invasive characterization of PF fields near high-voltage infrastructure.

physics.atom-ph↗

arXiv2025

MILLION: Mastering Long-Context LLM Inference Via Outlier-Immunized KV Product Quantization

Large language models (LLMs) are increasingly utilized for complex tasks requiring longer context lengths, with some models supporting up to 128K or 1M tokens. This trend, however, presents significant challenges in inference speed and memory management. Quantization emerges as a promising approach to address the widening gap between LLM size and memory capacity. However, traditional quantization schemes often yield suboptimal compression results for KV caches due to two key factors: i) On-the-fly quantization and de-quantization, causing significant performance overhead; ii) Prevalence of outliers in KV values, challenging low-bitwidth uniform quantization. To this end, we propose MILLION, a novel quantization framework achieving low-bitwidth KV cache through product quantization. First, we conduct a thorough analysis of KV cache distribution, revealing the limitations of existing quantization schemes. Second, we introduce a non-uniform quantization algorithm based on product quantization, which efficiently compresses data while preserving accuracy. Third, we develop a high-performance GPU inference framework with efficient attention kernel and pipeline design for MILLION that leverages sparse computation and asynchronous quantization, significantly enhancing inference speed. Comprehensive evaluation results demonstrate that MILLION can achieve 4 bits quantization with trivial perplexity and accuracy loss, and achieve 2.09x end-to-end performance gains at 32K context length. Code is released at https://github.com/ZongwuWang/MILLION.

cs.DC↗

arXiv2025

From 128K to 4M: Efficient Training of Ultra-Long Context Large Language Models

Long-context capabilities are essential for a wide range of applications, including document and video understanding, in-context learning, and inference-time scaling, all of which require models to process and reason over long sequences of text and multimodal data. In this work, we introduce a efficient training recipe for building ultra-long context LLMs from aligned instruct model, pushing the boundaries of context lengths from 128K to 1M, 2M, and 4M tokens. Our approach leverages efficient continued pretraining strategies to extend the context window and employs effective instruction tuning to maintain the instruction-following and reasoning abilities. Our UltraLong-8B, built on Llama3.1-Instruct with our recipe, achieves state-of-the-art performance across a diverse set of long-context benchmarks. Importantly, models trained with our approach maintain competitive performance on standard benchmarks, demonstrating balanced improvements for both long and short context tasks. We further provide an in-depth analysis of key design choices, highlighting the impacts of scaling strategies and data composition. Our findings establish a robust framework for efficiently scaling context lengths while preserving general model capabilities. We release all model weights at: https://ultralong.github.io/.

cs.CL↗

arXiv2025

Hierarchical feature extraction on functional brain networks for autism spectrum disorder identification with resting-state fMRI data

Autism Spectrum Disorder (ASD) is a pervasive developmental disorder of the central nervous system, primarily manifesting in childhood. It is characterized by atypical and repetitive behaviors. Currently, diagnostic methods mainly rely on questionnaire surveys and behavioral observations, which are prone to misdiagnosis due to their subjective nature. With advancements in medical imaging, MR imaging-based diagnostics have emerged as a more objective alternative. In this paper, we propose a Hierarchical Neural Network model for ASD identification, termed ASD-HNet, which hierarchically extracts features from functional brain networks based on resting-state functional magnetic resonance imaging (rs-fMRI) data. This hierarchical approach enhances the extraction of brain representations, improving diagnostic accuracy and aiding in the identification of brain regions associated with ASD. Specifically, features are extracted at three levels: (1) the local region of interest (ROI) scale, (2) the community scale, and (3) the global representation scale. At the ROI scale, graph convolution is employed to transfer features between ROIs. At the community scale, functional gradients are introduced, and a K-Means clustering algorithm is applied to group ROIs with similar functional gradients into communities. Features from ROIs within the same community are then extracted to characterize the communities. At the global representation scale, we extract global features from the whole community-scale brain networks to represent the entire brain. We validate the effectiveness of our method using the publicly available Autism Brain Imaging Data Exchange I (ABIDE-I) dataset. Experimental results demonstrate that ASD-HNet outperforms existing methods. The code is available at https://github.com/LYQbyte/ASD-HNet.

q-bio.NC↗

arXiv2025

Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUs

In this technical report, we tackle the challenges of training large-scale Mixture of Experts (MoE) models, focusing on overcoming cost inefficiency and resource limitations prevalent in such systems. To address these issues, we present two differently sized MoE large language models (LLMs), namely Ling-Lite and Ling-Plus (referred to as "Bailing" in Chinese, spelled Bǎilíng in Pinyin). Ling-Lite contains 16.8 billion parameters with 2.75 billion activated parameters, while Ling-Plus boasts 290 billion parameters with 28.8 billion activated parameters. Both models exhibit comparable performance to leading industry benchmarks. This report offers actionable insights to improve the efficiency and accessibility of AI development in resource-constrained settings, promoting more scalable and sustainable technologies. Specifically, to reduce training costs for large-scale MoE models, we propose innovative methods for (1) optimization of model architecture and training processes, (2) refinement of training anomaly handling, and (3) enhancement of model evaluation efficiency. Additionally, leveraging high-quality data generated from knowledge graphs, our models demonstrate superior capabilities in tool use compared to other models. Ultimately, our experimental findings demonstrate that a 300B MoE LLM can be effectively trained on lower-performance devices while achieving comparable performance to models of a similar scale, including dense and MoE models. Compared to high-performance devices, utilizing a lower-specification hardware system during the pre-training phase demonstrates significant cost savings, reducing computing costs by approximately 20%. The models can be accessed at https://huggingface.co/inclusionAI.

cs.LG↗

arXiv2025

Post-Newtonian Tests of Gravitational Quantum Field Theory with Spin and Scaling Gauge Symmetry

A self-consistent gravitational quantum field theory, with gravitational force treated on the same footing as the other three fundamental interactions, was established recently. The gravidynamics predicted by such a theory could lead to important implications, and the comparisons with experimental results may provide us opportunities to test such new approach of gravity based on the framework of the quantum field theory of gauge interactions. In this work, we start with the effective field equation of the gravitational quantum field theory, and then solve the perturbative gravigauge field order by order up to the 1st post-Newtonian level under the assumption of a simplified energy-momentum tensor of perfect fluids. Having the constraints on the related post-Newtonian parameters from the most up-to-date observational data, the new bound on the combined coupling in the gravitational quantum field theory $|γ_G(α_G-α_W/2)|\leq (2.4\pm30)\times10^{-6} $ is obtained. Under such bound, we found that the new gravitational quantum field theory successfully passed and found no conflict with the contemporary keynote Solar system experiments of gravity.

gr-qc↗

arXiv2025

Robotic Table Tennis: A Case Study into a High Speed Learning System

We present a deep-dive into a real-world robotic learning system that, in previous work, was shown to be capable of hundreds of table tennis rallies with a human and has the ability to precisely return the ball to desired targets. This system puts together a highly optimized perception subsystem, a high-speed low-latency robot controller, a simulation paradigm that can prevent damage in the real world and also train policies for zero-shot transfer, and automated real world environment resets that enable autonomous training and evaluation on physical robots. We complement a complete system description, including numerous design decisions that are typically not widely disseminated, with a collection of studies that clarify the importance of mitigating various sources of latency, accounting for training and deployment distribution shifts, robustness of the perception system, sensitivity to policy hyper-parameters, and choice of action space. A video demonstrating the components of the system and details of experimental results can be found at https://youtu.be/uFcnWjB42I0.

cs.RO↗

arXiv2025

Large Memory Network for Recommendation

Modeling user behavior sequences in recommender systems is essential for understanding user preferences over time, enabling personalized and accurate recommendations for improving user retention and enhancing business values. Despite its significance, there are two challenges for current sequential modeling approaches. From the spatial dimension, it is difficult to mutually perceive similar users' interests for a generalized intention understanding; from the temporal dimension, current methods are generally prone to forgetting long-term interests due to the fixed-length input sequence. In this paper, we present Large Memory Network (LMN), providing a novel idea by compressing and storing user history behavior information in a large-scale memory block. With the elaborated online deployment strategy, the memory block can be easily scaled up to million-scale in the industry. Extensive offline comparison experiments, memory scaling up experiments, and online A/B test on Douyin E-Commerce Search (ECS) are performed, validating the superior performance of LMN. Currently, LMN has been fully deployed in Douyin ECS, serving millions of users each day.

cs.IR↗