Showing 1–50 of 58 results for author: Dai, F

MineValiCoder: Reliable Code Generation with Test Case Quality Mining and Bipartite Graph-Based Mutual Validation

Authors: Zhen Zhao, Qihang Yang, Feifei Dai, Xiangfang Li, Bo Li

Abstract: Large Language Model (LLM)-based Test-Driven Development (TDD) has advanced automated code generation. However, existing approaches depend heavily on human-crafted test cases and cannot operate effectively when only natural-language requirements are available. Although recent work enables automatic test generation, it often overlooks the inherent stochasticity of LLMs, leading to two key defects:… ▽ More Large Language Model (LLM)-based Test-Driven Development (TDD) has advanced automated code generation. However, existing approaches depend heavily on human-crafted test cases and cannot operate effectively when only natural-language requirements are available. Although recent work enables automatic test generation, it often overlooks the inherent stochasticity of LLMs, leading to two key defects: faulty tests generate misleading feedback that distorts code optimization, while mixed-quality test cases produce conflicting evaluation signals that hinder reliable code selection. To address these challenges, we propose MineValiCoder, a collaborative closed-loop TDD framework based on the mutual reinforcement of test-case quality and code quality. MineValiCoder comprises three modules. The Test Case Quality Mining (TCQM) module filters faulty test cases through self-validation, providing reliable optimization supervision. The Parallel TDD Refinement module iteratively optimizes code and generates diverse high-quality code candidates using validated test-case feedback. The Bipartite Graph-Based Code-Test Mutual Validation (BiCoTeV) module dynamically models code-test interactions and performs mutual validation scoring for stable and reliable optimal-code selection. Extensive evaluations across four LLMs and mainstream benchmarks show that MineValiCoder significantly outperforms state-of-the-art methods. Specifically, it achieves Pass@1 scores of 96.34% on HumanEval, 87.40% on MBPP, 64.00% on APPS, and 51.33% on LiveCodeBench. These results demonstrate the effectiveness of MineValiCoder in mitigating LLM stochasticity and improving the reliability of automated code generation. △ Less

Submitted 24 July, 2026; originally announced July 2026.

Comments: 12 pages, 3 figures, 7 tables

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

Authors: DeepSeek-AI, Anyi Xu, Bangcai Lin, Bing Xue, Bingxuan Wang, Bingzheng Xu, Bochao Wu, Bowei Zhang, Chaofan Lin, Chen Dong, Chenchen Ling, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chengyu Hou, Chenhao Xu, Chenze Shao, Chong Ruan, Conner Sun, Damai Dai, Daya Guo, Dejian Yang, Deli Chen, Donghao Li, Dongjie Ji , et al. (294 additional authors not shown)

Abstract: We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models -- DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated) -- both supporting a context length of one million tokens. DeepSeek-V4 series incorporate several key upgrades in architecture and optimization: (1) a hybrid attention arc… ▽ More We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models -- DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated) -- both supporting a context length of one million tokens. DeepSeek-V4 series incorporate several key upgrades in architecture and optimization: (1) a hybrid attention architecture that combines Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA) to improve long-context efficiency; (2) Manifold-Constrained Hyper-Connections (mHC) that enhance conventional residual connections; (3) and the Muon optimizer for faster convergence and greater training stability. We pre-train both models on more than 32T diverse and high-quality tokens, followed by a comprehensive post-training pipeline that unlocks and further enhances their capabilities. DeepSeek-V4-Pro-Max, the maximum reasoning effort mode of DeepSeek-V4-Pro, redefines the state-of-the-art for open models, outperforming its predecessors in core tasks. Meanwhile, DeepSeek-V4 series are highly efficient in long-context scenarios. In the one-million-token context setting, DeepSeek-V4-Pro requires only 27% of single-token inference FLOPs and 10% of KV cache compared with DeepSeek-V3.2. This enables us to routinely support one-million-token contexts, thereby making long-horizon tasks and further test-time scaling more feasible. The model checkpoints are available at https://huggingface.co/collections/deepseek-ai/deepseek-v4. △ Less

Submitted 26 April, 2026; originally announced June 2026.

VIP: Visual-guided Prompt Evolution for Efficient Dense Vision-Language Inference

Authors: Hao Zhu, Shuo Jin, Wenbin Liao, Jiayu Xiao, Yan Zhu, Siyue Yu, Feng Dai

Abstract: Pursuing training-free open-vocabulary semantic segmentation in an efficient and generalizable manner remains challenging due to the deep-seated spatial bias in CLIP. To overcome the limitations of existing solutions, this work moves beyond the CLIP-based paradigm and harnesses the recent spatially-aware dino$.$txt framework to facilitate more efficient and high-quality dense prediction. While din… ▽ More Pursuing training-free open-vocabulary semantic segmentation in an efficient and generalizable manner remains challenging due to the deep-seated spatial bias in CLIP. To overcome the limitations of existing solutions, this work moves beyond the CLIP-based paradigm and harnesses the recent spatially-aware dino$.$txt framework to facilitate more efficient and high-quality dense prediction. While dino$.$txt exhibits robust spatial awareness, we find that the semantic ambiguity of text queries gives rise to severe mismatch within its dense cross-modal interactions. To address this, we introduce Visual-guided Prompt evolution (VIP) to rectify the semantic expressiveness of text queries in dino$.$txt, unleashing its potential for fine-grained object perception. Towards this end, VIP integrates alias expansion with a visual-guided distillation mechanism to mine valuable semantic cues, which are robustly aggregated in a saliency-aware manner to yield a high-fidelity prediction. Extensive evaluations demonstrate that VIP: 1. surpasses the top-leading methods by 1.4%-8.4% average mIoU, 2. generalizes well to diverse challenging domains, and 3. requires marginal inference time and memory overhead. △ Less

Submitted 13 May, 2026; v1 submitted 12 May, 2026; originally announced May 2026.

Comments: Accepted by ICML2026. Code is available at https://github.com/MiSsU-HH/VIP

TreeGaussian: Tree-Guided Cascaded Contrastive Learning for Hierarchical Consistent 3D Gaussian Scene Segmentation and Understanding

Authors: Jingbin You, Zehao Li, Hao Jiang, Xinzhu Ma, Shuqin Gao, Honglong Zhao, Congcong Zheng, Tianlu Mao, Feng Dai, Yucheng Zhang, Zhaoqi Wang

Abstract: 3D Gaussian Splatting (3DGS) has emerged as a real-time, differentiable representation for neural scene understanding. However, existing 3DGS-based methods struggle to represent hierarchical 3D semantic structures and capture whole-part relationships in complex scenes. Moreover, dense pairwise comparisons and inconsistent hierarchical labels from 2D priors hinder feature learning, resulting in sub… ▽ More 3D Gaussian Splatting (3DGS) has emerged as a real-time, differentiable representation for neural scene understanding. However, existing 3DGS-based methods struggle to represent hierarchical 3D semantic structures and capture whole-part relationships in complex scenes. Moreover, dense pairwise comparisons and inconsistent hierarchical labels from 2D priors hinder feature learning, resulting in suboptimal segmentation. To address these limitations, we introduce TreeGaussian, a tree-guided cascaded contrastive learning framework that explicitly models hierarchical semantic relationships and reduces redundancy in contrastive supervision. By constructing a multi-level object tree, TreeGaussian enables structured learning across object-part hierarchies. In addition, we propose a two-stage cascaded contrastive learning strategy that progressively refines feature representations from global to local, mitigating saturation and stabilizing training. A Consistent Segmentation Detection (CSD) mechanism and a graph-based denoising module are further introduced to align segmentation modes across views while suppressing unstable Gaussian points, enhancing segmentation consistency and quality. Extensive experiments, including open-vocabulary 3D object selection, 3D point cloud understanding, and ablation studies, demonstrate the effectiveness and robustness of our approach. △ Less

Submitted 31 March, 2026; originally announced April 2026.

Probe-to-Grasp Manipulation Using Self-Sensing Pneumatic Variable-Stiffness Joints

Authors: Ngoc Duy Tran, Yeman Fan, Feng Dai, Khang Nguyen, Anh Nguyen, Hoang Hiep Ly, Tung D. Ta, Shigeru Chiba

Abstract: Grasping deformable objects with varying stiffness remains a significant challenge in robotics. Estimating the local stiffness of a target object is important for determining an optimal grasp pose that enables stable pickup without damaging the object. This paper presents a probe-to-grasp manipulation framework for estimating the relative stiffness of objects using a passive soft-rigid two-finger… ▽ More Grasping deformable objects with varying stiffness remains a significant challenge in robotics. Estimating the local stiffness of a target object is important for determining an optimal grasp pose that enables stable pickup without damaging the object. This paper presents a probe-to-grasp manipulation framework for estimating the relative stiffness of objects using a passive soft-rigid two-finger hybrid gripper equipped with self-sensing pneumatic variable-stiffness joints. Each finger of the gripper consists of two rigid links connected by a soft pneumatic ring placed at the joint, enabling both compliant interaction and controllable joint stiffness via internal pressurization. By measuring the pressure inside the pneumatic ring, we can estimate the interaction force during contact. Building on this, we propose a practical probing strategy to infer relative object stiffness by correlating the estimated normal force with known gripper closing displacement. We validate the self-sensing model through stiffness characterization experiments across bending angles and pressure ranges, and demonstrate stiffness-aware probing-and-grasping in real-life applications: selecting grasp locations on fruits with spatially varying stiffness. The proposed system offers a minimal, low-cost sensing approach for stiffness-aware soft manipulation while retaining probing and grasping capability. △ Less

Submitted 29 March, 2026; originally announced March 2026.

Efficient Selection of Type Annotations for Performance Improvement in Gradual Typing

Authors: Senxi Li, Feng Dai, Tetsuro Yamazaki, Shigeru Chiba

Abstract: Gradual typing has gained popularity as a design choice for integrating static and dynamic typing within a single language. Several practical languages have adopted gradual typing to offer programmers the flexibility to annotate their programs as needed. Meanwhile there is a key challenge of unexpected performance degradation in partially typed programs. The execution speed may significantly decre… ▽ More Gradual typing has gained popularity as a design choice for integrating static and dynamic typing within a single language. Several practical languages have adopted gradual typing to offer programmers the flexibility to annotate their programs as needed. Meanwhile there is a key challenge of unexpected performance degradation in partially typed programs. The execution speed may significantly decrease when simply adding more type annotations. Prior studies have investigated strategies of selectively adding type annotations for better performance. However, they are restricted in substantial compilation time, which impedes the practical usage. This paper presents a new technique to select a subset of type annotations derived by type inference for improving the execution performance of gradually typed programs. The advantage of the proposal is shorter compilation time by employing a lightweight, amortized approach. It selects type annotations along the data flows, which is expected to avoid expensive runtime casts caused by a value repeatedly crossing the boundaries between untyped and typed code. We demonstrate the applicability of our proposal, and conduct experiments to validate its effectiveness of improving the execution time on Reticulated Python. Our implementation supports a Python subset to select type annotations derived by an implemented, external type inference engine. Experiment results show that our proposal outperforms a naive strategy of using all type annotations derived by type inference among the benchmark programs. In comparison with an existing approach, the proposal achieves comparable execution speed and shows advantage of maintaining a more stable compilation time of deriving and selecting type annotations. Our results empirically indicate that the proposed technique is practical within Reticulated Python for mitigating the performance bottleneck of gradually typed programs. △ Less

Submitted 5 March, 2026; originally announced March 2026.

Journal ref: The Art, Science, and Engineering of Programming, 2026, Vol. 11, Issue 1, Article 3

Boxplots and quartile plots for grouped and periodic angular data

Authors: Joshua D. Berlinski, Fan Dai, Ranjan Maitra

Abstract: Angular observations, or observations lying on the unit circle, arise in many disciplines and require special care in their description, analysis, interpretation and visualization. We provide methods to construct concentric circular boxplot displays of distributions of groups of angular data. The use of concentric boxplots brings challenges of visual perception, so we set the boxwidths to be inver… ▽ More Angular observations, or observations lying on the unit circle, arise in many disciplines and require special care in their description, analysis, interpretation and visualization. We provide methods to construct concentric circular boxplot displays of distributions of groups of angular data. The use of concentric boxplots brings challenges of visual perception, so we set the boxwidths to be inversely proportional to the square root of their distance from the centre. A perception survey supports this scaled boxwidth choice. For a large number of groups, we propose circular quartile plots. A three-dimensional toroidal display is also implemented for periodic angular distributions. We illustrate our methods on datasets in (1) psychology, to display motor resonance under different conditions, (2) genomics, to understand the distribution of peak phases for ancillary clock genes, and (3) meteorology and wind turbine power generation, to study the changing and periodic distribution of wind direction over the course of a year. △ Less

Submitted 5 February, 2026; originally announced February 2026.

Comments: 7 pages, 8 figures

MSC Class: 62099; 62-04; 68U05; 62P10; 62P12 ACM Class: G.3; G.4; I.1.3

Democratizing planetary-scale analysis: An ultra-lightweight Earth embedding database for accurate and flexible global land monitoring

Authors: Shuang Chen, Jie Wang, Shuai Yuan, Jiayang Li, Yu Xia, Yuanhong Liao, Junbo Wei, Jincheng Yuan, Xiaoqing Xu, Xiaolin Zhu, Peng Zhu, Hongsheng Zhang, Yuyu Zhou, Haohuan Fu, Huabing Huang, Bin Chen, Fan Dai, Peng Gong

Abstract: The rapid evolution of satellite-borne Earth Observation (EO) systems has revolutionized terrestrial monitoring, yielding petabyte-scale archives. However, the immense computational and storage requirements for global-scale analysis often preclude widespread use, hindering planetary-scale studies. To address these barriers, we present Embedded Seamless Data (ESD), an ultra-lightweight, 30-m global… ▽ More The rapid evolution of satellite-borne Earth Observation (EO) systems has revolutionized terrestrial monitoring, yielding petabyte-scale archives. However, the immense computational and storage requirements for global-scale analysis often preclude widespread use, hindering planetary-scale studies. To address these barriers, we present Embedded Seamless Data (ESD), an ultra-lightweight, 30-m global Earth embedding database spanning the 25-year period from 2000 to 2024. By transforming high-dimensional, multi-sensor observations from the Landsat series (5, 7, 8, and 9) and MODIS Terra into information-dense, quantized latent vectors, ESD distills essential geophysical and semantic features into a unified latent space. Utilizing the ESDNet architecture and Finite Scalar Quantization (FSQ), the dataset achieves a transformative ~340-fold reduction in data volume compared to raw archives. This compression allows the entire global land surface for a single year to be encapsulated within approximately 2.4 TB, enabling decadal-scale global analysis on standard local workstations. Rigorous validation demonstrates high reconstructive fidelity (MAE: 0.0130; RMSE: 0.0179; CC: 0.8543). By condensing the annual phenological cycle into 12 temporal steps, the embeddings provide inherent denoising and a semantically organized space that outperforms raw reflectance in land-cover classification, achieving 79.74% accuracy (vs. 76.92% for raw fusion). With robust few-shot learning capabilities and longitudinal consistency, ESD provides a versatile foundation for democratizing planetary-scale research and advancing next-generation geospatial artificial intelligence. △ Less

Submitted 16 January, 2026; originally announced January 2026.

Max-Min Neural Network Operators For Approximation of Multivariate Functions

Authors: Abhishek Yadav, Uaday Singh, Feng Dai

Abstract: In this paper, we develop a multivariate framework for approximation by max-min neural network operators. Building on the recent advances in approximation theory by neural network operators, particularly, the univariate max-min operators, we propose and analyze new multivariate operators activated by sigmoidal functions. We establish pointwise and uniform convergence theorems and derive quantitati… ▽ More In this paper, we develop a multivariate framework for approximation by max-min neural network operators. Building on the recent advances in approximation theory by neural network operators, particularly, the univariate max-min operators, we propose and analyze new multivariate operators activated by sigmoidal functions. We establish pointwise and uniform convergence theorems and derive quantitative estimates for the order of approximation via modulus of continuity and multivariate generalized absolute moment. Our results demonstrate that multivariate max-min structure of operators, besides their algebraic elegance, provide efficient and stable approximation tools in both theoretical and applied settings. △ Less

Submitted 12 January, 2026; originally announced January 2026.

Comments: 17 pages with 8 figures

MSC Class: 00A05(Primary); 41A25(Secondary); 41A35 (Secondary); 41A36 (Secondary)

TEA: Temporal Adaptive Satellite Image Semantic Segmentation

Authors: Juyuan Kang, Hao Zhu, Yan Zhu, Wei Zhang, Jianing Chen, Tianxiang Xiao, Yike Ma, Hao Jiang, Feng Dai

Abstract: Crop mapping based on satellite images time-series (SITS) holds substantial economic value in agricultural production settings, in which parcel segmentation is an essential step. Existing approaches have achieved notable advancements in SITS segmentation with predetermined sequence lengths. However, we found that these approaches overlooked the generalization capability of models across scenarios… ▽ More Crop mapping based on satellite images time-series (SITS) holds substantial economic value in agricultural production settings, in which parcel segmentation is an essential step. Existing approaches have achieved notable advancements in SITS segmentation with predetermined sequence lengths. However, we found that these approaches overlooked the generalization capability of models across scenarios with varying temporal length, leading to markedly poor segmentation results in such cases. To address this issue, we propose TEA, a TEmporal Adaptive SITS semantic segmentation method to enhance the model's resilience under varying sequence lengths. We introduce a teacher model that encapsulates the global sequence knowledge to guide a student model with adaptive temporal input lengths. Specifically, teacher shapes the student's feature space via intermediate embedding, prototypes and soft label perspectives to realize knowledge transfer, while dynamically aggregating student model to mitigate knowledge forgetting. Finally, we introduce full-sequence reconstruction as an auxiliary task to further enhance the quality of representations across inputs of varying temporal lengths. Through extensive experiments, we demonstrate that our method brings remarkable improvements across inputs of different temporal lengths on common benchmarks. Our code will be publicly available. △ Less

Submitted 8 January, 2026; originally announced January 2026.

Comments: Under review. Code will be available at \href{https://github.com/KeplerKang/TEA}{this https URL}

Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem

Authors: Weixun Wang, XiaoXiao Xu, Wanhe An, Fangwen Dai, Wei Gao, Yancheng He, Ju Huang, Qiang Ji, Hanqi Jin, Xiaoyang Li, Yang Li, Zhongwen Li, Shirong Lin, Jiashun Liu, Zenan Liu, Tao Luo, Dilxat Muhtar, Yuanbin Qu, Jiaqiang Shi, Qinghui Sun, Yingshui Tan, Hao Tang, Runze Wang, Yi Wang, Zhaoguo Wang , et al. (65 additional authors not shown)

Abstract: Agentic crafting requires LLMs to operate in real-world environments over multiple turns by taking actions, observing outcomes, and iteratively refining artifacts. Despite its importance, the open-source community lacks a principled, end-to-end ecosystem to streamline agent development. We introduce the Agentic Learning Ecosystem (ALE), a foundational infrastructure that optimizes the production p… ▽ More Agentic crafting requires LLMs to operate in real-world environments over multiple turns by taking actions, observing outcomes, and iteratively refining artifacts. Despite its importance, the open-source community lacks a principled, end-to-end ecosystem to streamline agent development. We introduce the Agentic Learning Ecosystem (ALE), a foundational infrastructure that optimizes the production pipeline for agentic model. ALE consists of three components: ROLL, a post-training framework for weight optimization; ROCK, a sandbox environment manager for trajectory generation; and iFlow CLI, an agent framework for efficient context engineering. We release ROME, an open-source agent grounded by ALE and trained on over one million trajectories. Our approach includes data composition protocols for synthesizing complex behaviors and a novel policy optimization algorithm, Interaction-Perceptive Agentic Policy Optimization (IPA), which assigns credit over semantic interaction chunks rather than individual tokens to improve long-horizon training stability. Empirically, we evaluate ROME within a structured setting and introduce Terminal Bench Pro, a benchmark with improved scale and contamination control. ROME demonstrates strong performance across benchmarks like SWE-bench Verified and Terminal Bench, proving the effectiveness of ALE. △ Less

Submitted 11 March, 2026; v1 submitted 31 December, 2025; originally announced December 2025.

Comments: 36 pages, 15 figures

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Authors: DeepSeek-AI, Aixin Liu, Aoxue Mei, Bangcai Lin, Bing Xue, Bingxuan Wang, Bingzheng Xu, Bochao Wu, Bowei Zhang, Chaofan Lin, Chen Dong, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenhao Xu, Chong Ruan, Damai Dai, Daya Guo, Dejian Yang, Deli Chen, Erhang Li, Fangqi Zhou, Fangyun Lin, Fucong Dai, Guangbo Hao , et al. (239 additional authors not shown)

Abstract: We introduce DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance. The key technical breakthroughs of DeepSeek-V3.2 are as follows: (1) DeepSeek Sparse Attention (DSA): We introduce DSA, an efficient attention mechanism that substantially reduces computational complexity while preserving model performance in long-context scenarios. (2)… ▽ More We introduce DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance. The key technical breakthroughs of DeepSeek-V3.2 are as follows: (1) DeepSeek Sparse Attention (DSA): We introduce DSA, an efficient attention mechanism that substantially reduces computational complexity while preserving model performance in long-context scenarios. (2) Scalable Reinforcement Learning Framework: By implementing a robust reinforcement learning protocol and scaling post-training compute, DeepSeek-V3.2 performs comparably to GPT-5. Notably, our high-compute variant, DeepSeek-V3.2-Speciale, surpasses GPT-5 and exhibits reasoning proficiency on par with Gemini-3.0-Pro, achieving gold-medal performance in both the 2025 International Mathematical Olympiad (IMO) and the International Olympiad in Informatics (IOI). (3) Large-Scale Agentic Task Synthesis Pipeline: To integrate reasoning into tool-use scenarios, we developed a novel synthesis pipeline that systematically generates training data at scale. This methodology facilitates scalable agentic post-training, yielding substantial improvements in generalization and instruction-following robustness within complex, interactive environments. △ Less

Submitted 2 December, 2025; originally announced December 2025.

TReFT: Taming Rectified Flow Models For One-Step Image Translation

Authors: Shengqian Li, Ming Gao, Yi Liu, Zuzeng Lin, Feng Wang, Feng Dai

Abstract: Rectified Flow (RF) models have advanced high-quality image and video synthesis via optimal transport theory. However, when applied to image-to-image translation, they still depend on costly multi-step denoising, hindering real-time applications. Although the recent adversarial training paradigm, CycleGAN-Turbo, works in pretrained diffusion models for one-step image translation, we find that dire… ▽ More Rectified Flow (RF) models have advanced high-quality image and video synthesis via optimal transport theory. However, when applied to image-to-image translation, they still depend on costly multi-step denoising, hindering real-time applications. Although the recent adversarial training paradigm, CycleGAN-Turbo, works in pretrained diffusion models for one-step image translation, we find that directly applying it to RF models leads to severe convergence issues. In this paper, we analyze these challenges and propose TReFT, a novel method to Tame Rectified Flow models for one-step image Translation. Unlike previous works, TReFT directly uses the velocity predicted by pretrained DiT or UNet as output-a simple yet effective design that tackles the convergence issues under adversarial training with one-step inference. This design is mainly motivated by a novel observation that, near the end of the denoising process, the velocity predicted by pretrained RF models converges to the vector from origin to the final clean image, a property we further justify through theoretical analysis. When applying TReFT to large pretrained RF models such as SD3.5 and FLUX, we introduce memory-efficient latent cycle-consistency and identity losses during training, as well as lightweight architectural simplifications for faster inference. Pretrained RF models finetuned with TReFT achieve performance comparable to sota methods across multiple image translation datasets while enabling real-time inference. △ Less

Submitted 25 November, 2025; originally announced November 2025.

MetroGS: Efficient and Stable Reconstruction of Geometrically Accurate High-Fidelity Large-Scale Scenes

Authors: Kehua Chen, Tianlu Mao, Xinzhu Ma, Hao Jiang, Zehao Li, Zihan Liu, Shuqin Gao, Honglong Zhao, Feng Dai, Yucheng Zhang, Zhaoqi Wang

Abstract: Recently, 3D Gaussian Splatting and its derivatives have achieved significant breakthroughs in large-scale scene reconstruction. However, how to efficiently and stably achieve high-quality geometric fidelity remains a core challenge. To address this issue, we introduce MetroGS, a novel Gaussian Splatting framework for efficient and robust reconstruction in complex urban environments. Our method is… ▽ More Recently, 3D Gaussian Splatting and its derivatives have achieved significant breakthroughs in large-scale scene reconstruction. However, how to efficiently and stably achieve high-quality geometric fidelity remains a core challenge. To address this issue, we introduce MetroGS, a novel Gaussian Splatting framework for efficient and robust reconstruction in complex urban environments. Our method is built upon a distributed 2D Gaussian Splatting representation as the core foundation, serving as a unified backbone for subsequent modules. To handle potential sparse regions in complex scenes, we propose a structured dense enhancement scheme that utilizes SfM priors and a pointmap model to achieve a denser initialization, while incorporating a sparsity compensation mechanism to improve reconstruction completeness. Furthermore, we design a progressive hybrid geometric optimization strategy that organically integrates monocular and multi-view optimization to achieve efficient and accurate geometric refinement. Finally, to address the appearance inconsistency commonly observed in large-scale scenes, we introduce a depth-guided appearance modeling approach that learns spatial features with 3D consistency, facilitating effective decoupling between geometry and appearance and further enhancing reconstruction stability. Experiments on large-scale urban datasets demonstrate that MetroGS achieves superior geometric accuracy, rendering quality, offering a unified solution for high-fidelity large-scale scene reconstruction. △ Less

Submitted 13 April, 2026; v1 submitted 24 November, 2025; originally announced November 2025.

Comments: Accepted by CVPR26; Project page: https://m3phist0.github.io/MetroGS

HLPD: Aligning LLMs to Human Language Preference for Machine-Revised Text Detection

Authors: Fangqi Dai, Xingjian Jiang, Zizhuang Deng

Abstract: To prevent misinformation and social issues arising from trustworthy-looking content generated by LLMs, it is crucial to develop efficient and reliable methods for identifying the source of texts. Previous approaches have demonstrated exceptional performance in detecting texts fully generated by LLMs. However, these methods struggle when confronting more advanced LLM output or text with adversaria… ▽ More To prevent misinformation and social issues arising from trustworthy-looking content generated by LLMs, it is crucial to develop efficient and reliable methods for identifying the source of texts. Previous approaches have demonstrated exceptional performance in detecting texts fully generated by LLMs. However, these methods struggle when confronting more advanced LLM output or text with adversarial multi-task machine revision, especially in the black-box setting, where the generating model is unknown. To address this challenge, grounded in the hypothesis that human writing possesses distinctive stylistic patterns, we propose Human Language Preference Detection (HLPD). HLPD employs a reward-based alignment process, Human Language Preference Optimization (HLPO), to shift the scoring model's token distribution toward human-like writing, making the model more sensitive to human writing, therefore enhancing the identification of machine-revised text. We test HLPD in an adversarial multi-task evaluation framework that leverages a five-dimensional prompt generator and multiple advanced LLMs to create diverse revision scenarios. When detecting texts revised by GPT-series models, HLPD achieves a 15.11% relative improvement in AUROC over ImBD, surpassing Fast-DetectGPT by 45.56%. When evaluated on texts generated by advanced LLMs, HLPD achieves the highest average AUROC, exceeding ImBD by 5.53% and Fast-DetectGPT by 34.14%. Code will be made available at https://github.com/dfq2021/HLPD. △ Less

Submitted 2 December, 2025; v1 submitted 10 November, 2025; originally announced November 2025.

Comments: 20 pages, 10 figures, accepted by AAAI'26

Towards Confidential and Efficient LLM Inference with Dual Privacy Protection

Authors: Honglan Yu, Yibin Wang, Feifei Dai, Dong Liu, Haihui Fan, Xiaoyan Gu

Abstract: CPU-based trusted execution environments (TEEs) and differential privacy (DP) have gained wide applications for private inference. Due to high inference latency in TEEs, researchers use partition-based approaches that offload linear model components to GPUs. However, dense nonlinear layers of large language models (LLMs) result in significant communication overhead between TEEs and GPUs. DP-based… ▽ More CPU-based trusted execution environments (TEEs) and differential privacy (DP) have gained wide applications for private inference. Due to high inference latency in TEEs, researchers use partition-based approaches that offload linear model components to GPUs. However, dense nonlinear layers of large language models (LLMs) result in significant communication overhead between TEEs and GPUs. DP-based approaches apply random noise to protect data privacy, but this compromises LLM performance and semantic understanding. To overcome the above drawbacks, this paper proposes CMIF, a Confidential and efficient Model Inference Framework. CMIF confidentially deploys the embedding layer in the client-side TEE and subsequent layers on GPU servers. Meanwhile, it optimizes the Report-Noisy-Max mechanism to protect sensitive inputs with a slight decrease in model performance. Extensive experiments on Llama-series models demonstrate that CMIF reduces additional inference overhead in TEEs while preserving user data privacy. △ Less

Submitted 10 September, 2025; originally announced September 2025.

Comments: Accepted by DASFAA2025

Long-VLA: Unleashing Long-Horizon Capability of Vision Language Action Model for Robot Manipulation

Authors: Yiguo Fan, Pengxiang Ding, Shuanghao Bai, Xinyang Tong, Yuyang Zhu, Hongchao Lu, Fengqi Dai, Wei Zhao, Yang Liu, Siteng Huang, Zhaoxin Fan, Badong Chen, Donglin Wang

Abstract: Vision-Language-Action (VLA) models have become a cornerstone in robotic policy learning, leveraging large-scale multimodal data for robust and scalable control. However, existing VLA frameworks primarily address short-horizon tasks, and their effectiveness on long-horizon, multi-step robotic manipulation remains limited due to challenges in skill chaining and subtask dependencies. In this work, w… ▽ More Vision-Language-Action (VLA) models have become a cornerstone in robotic policy learning, leveraging large-scale multimodal data for robust and scalable control. However, existing VLA frameworks primarily address short-horizon tasks, and their effectiveness on long-horizon, multi-step robotic manipulation remains limited due to challenges in skill chaining and subtask dependencies. In this work, we introduce Long-VLA, the first end-to-end VLA model specifically designed for long-horizon robotic tasks. Our approach features a novel phase-aware input masking strategy that adaptively segments each subtask into moving and interaction phases, enabling the model to focus on phase-relevant sensory cues and enhancing subtask compatibility. This unified strategy preserves the scalability and data efficiency of VLA training, and our architecture-agnostic module can be seamlessly integrated into existing VLA models. We further propose the L-CALVIN benchmark to systematically evaluate long-horizon manipulation. Extensive experiments on both simulated and real-world tasks demonstrate that Long-VLA significantly outperforms prior state-of-the-art methods, establishing a new baseline for long-horizon robotic control. △ Less

Submitted 28 August, 2025; v1 submitted 27 August, 2025; originally announced August 2025.

Comments: Accepted to CoRL 2025; Github Page: https://long-vla.github.io

RAGNet: Large-scale Reasoning-based Affordance Segmentation Benchmark towards General Grasping

Authors: Dongming Wu, Yanping Fu, Saike Huang, Yingfei Liu, Fan Jia, Nian Liu, Feng Dai, Tiancai Wang, Rao Muhammad Anwer, Fahad Shahbaz Khan, Jianbing Shen

Abstract: General robotic grasping systems require accurate object affordance perception in diverse open-world scenarios following human instructions. However, current studies suffer from the problem of lacking reasoning-based large-scale affordance prediction data, leading to considerable concern about open-world effectiveness. To address this limitation, we build a large-scale grasping-oriented affordance… ▽ More General robotic grasping systems require accurate object affordance perception in diverse open-world scenarios following human instructions. However, current studies suffer from the problem of lacking reasoning-based large-scale affordance prediction data, leading to considerable concern about open-world effectiveness. To address this limitation, we build a large-scale grasping-oriented affordance segmentation benchmark with human-like instructions, named RAGNet. It contains 273k images, 180 categories, and 26k reasoning instructions. The images cover diverse embodied data domains, such as wild, robot, ego-centric, and even simulation data. They are carefully annotated with an affordance map, while the difficulty of language instructions is largely increased by removing their category name and only providing functional descriptions. Furthermore, we propose a comprehensive affordance-based grasping framework, named AffordanceNet, which consists of a VLM pre-trained on our massive affordance data and a grasping network that conditions an affordance map to grasp the target. Extensive experiments on affordance segmentation benchmarks and real-robot manipulation tasks show that our model has a powerful open-world generalization ability. Our data and code is available at https://github.com/wudongming97/AffordanceNet. △ Less

Submitted 31 July, 2025; originally announced July 2025.

Comments: Accepted by ICCV 2025. The code is at https://github.com/wudongming97/AffordanceNet

CausalDiffTab: Mixed-Type Causal-Aware Diffusion for Tabular Data Generation

Authors: Jia-Chen Zhang, Zheng Zhou, Yu-Jie Xiong, Chun-Ming Xia, Fei Dai

Abstract: Training data has been proven to be one of the most critical components in training generative AI. However, obtaining high-quality data remains challenging, with data privacy issues presenting a significant hurdle. To address the need for high-quality data. Synthesize data has emerged as a mainstream solution, demonstrating impressive performance in areas such as images, audio, and video. Generati… ▽ More Training data has been proven to be one of the most critical components in training generative AI. However, obtaining high-quality data remains challenging, with data privacy issues presenting a significant hurdle. To address the need for high-quality data. Synthesize data has emerged as a mainstream solution, demonstrating impressive performance in areas such as images, audio, and video. Generating mixed-type data, especially high-quality tabular data, still faces significant challenges. These primarily include its inherent heterogeneous data types, complex inter-variable relationships, and intricate column-wise distributions. In this paper, we introduce CausalDiffTab, a diffusion model-based generative model specifically designed to handle mixed tabular data containing both numerical and categorical features, while being more flexible in capturing complex interactions among variables. We further propose a hybrid adaptive causal regularization method based on the principle of Hierarchical Prior Fusion. This approach adaptively controls the weight of causal regularization, enhancing the model's performance without compromising its generative capabilities. Comprehensive experiments conducted on seven datasets demonstrate that CausalDiffTab outperforms baseline methods across all metrics. Our code is publicly available at: https://github.com/Godz-z/CausalDiffTab. △ Less

Submitted 17 June, 2025; originally announced June 2025.

Semantic-decoupled Spatial Partition Guided Point-supervised Oriented Object Detection

Authors: Xinyuan Liu, Hang Xu, Zirui Chen, Yike Ma, Chenggang Yan, Feng Dai

Abstract: Given its ability to reduce annotation costs, weakly supervised learning based on single-point annotations has emerged as a research focus in oriented object detection. Compared with the classical teacher-student paradigm, the simple model paradigm (e.g., PointOBB-v2) can substantially further reduce resources required for training while ensuring strong performance. The latter exhibits greater pot… ▽ More Given its ability to reduce annotation costs, weakly supervised learning based on single-point annotations has emerged as a research focus in oriented object detection. Compared with the classical teacher-student paradigm, the simple model paradigm (e.g., PointOBB-v2) can substantially further reduce resources required for training while ensuring strong performance. The latter exhibits greater potential for low-cost training, yet such methods still face challenges of insufficient sample assignment and poor pseudo-label quality. In this paper, we propose a training-efficient framework named SSP, which synergizes rule-driven prior injection and data-driven label purification. Specifically, SSP introduces two designs: (1) Pixel-level Spatial Partition-based Sample Assignment, which compactly estimates the upper and lower bounds of object scales and mines high-quality positive samples and hard negative samples through spatial partitioning of pixel maps. (2) Semantic Spatial Partition-based Box Extraction, which derives instances from spatial partitions modulated by semantic maps and converts them into pseudo-boxes for supervising detectors. Experiments on DOTA-v1.0 and other datasets demonstrate SSP's superiority: it achieves +6.73% mAP improvement compared with the baseline, while requiring only 2 h of training time and 6 GB of GPU memory. Furthermore, when SSP is integrated with stronger detector, the mAP can reach 50.81%. The code is available at https://github.com/antxinyuan/ssp. △ Less

Submitted 4 June, 2026; v1 submitted 12 June, 2025; originally announced June 2025.

Comments: Published in Pattern Recognition, 2026

Journal ref: Pattern Recognition, Volume 180, Part B, Article 114079 (2026)

TopoPoint: Enhance Topology Reasoning via Endpoint Detection in Autonomous Driving

Authors: Yanping Fu, Xinyuan Liu, Tianyu Li, Yike Ma, Yucheng Zhang, Feng Dai

Abstract: Topology reasoning, which unifies perception and structured reasoning, plays a vital role in understanding intersections for autonomous driving. However, its performance heavily relies on the accuracy of lane detection, particularly at connected lane endpoints. Existing methods often suffer from lane endpoints deviation, leading to incorrect topology construction. To address this issue, we propose… ▽ More Topology reasoning, which unifies perception and structured reasoning, plays a vital role in understanding intersections for autonomous driving. However, its performance heavily relies on the accuracy of lane detection, particularly at connected lane endpoints. Existing methods often suffer from lane endpoints deviation, leading to incorrect topology construction. To address this issue, we propose TopoPoint, a novel framework that explicitly detects lane endpoints and jointly reasons over endpoints and lanes for robust topology reasoning. During training, we independently initialize point and lane query, and proposed Point-Lane Merge Self-Attention to enhance global context sharing through incorporating geometric distances between points and lanes as an attention mask . We further design Point-Lane Graph Convolutional Network to enable mutual feature aggregation between point and lane query. During inference, we introduce Point-Lane Geometry Matching algorithm that computes distances between detected points and lanes to refine lane endpoints, effectively mitigating endpoint deviation. Extensive experiments on the OpenLane-V2 benchmark demonstrate that TopoPoint achieves state-of-the-art performance in topology reasoning (48.8 on OLS). Additionally, we propose DET$_p$ to evaluate endpoint detection, under which our method significantly outperforms existing approaches (52.6 v.s. 45.2 on DET$_p$). The code is released at https://github.com/Franpin/TopoPoint. △ Less

Submitted 23 May, 2025; originally announced May 2025.

VARD: Efficient and Dense Fine-Tuning for Diffusion Models with Value-based RL

Authors: Fengyuan Dai, Zifeng Zhuang, Yufei Huang, Siteng Huang, Bangyan Liao, Donglin Wang, Fajie Yuan

Abstract: Diffusion models have emerged as powerful generative tools across various domains, yet tailoring pre-trained models to exhibit specific desirable properties remains challenging. While reinforcement learning (RL) offers a promising solution,current methods struggle to simultaneously achieve stable, efficient fine-tuning and support non-differentiable rewards. Furthermore, their reliance on sparse r… ▽ More Diffusion models have emerged as powerful generative tools across various domains, yet tailoring pre-trained models to exhibit specific desirable properties remains challenging. While reinforcement learning (RL) offers a promising solution,current methods struggle to simultaneously achieve stable, efficient fine-tuning and support non-differentiable rewards. Furthermore, their reliance on sparse rewards provides inadequate supervision during intermediate steps, often resulting in suboptimal generation quality. To address these limitations, dense and differentiable signals are required throughout the diffusion process. Hence, we propose VAlue-based Reinforced Diffusion (VARD): a novel approach that first learns a value function predicting expection of rewards from intermediate states, and subsequently uses this value function with KL regularization to provide dense supervision throughout the generation process. Our method maintains proximity to the pretrained model while enabling effective and stable training via backpropagation. Experimental results demonstrate that our approach facilitates better trajectory guidance, improves training efficiency and extends the applicability of RL to diffusion models optimized for complex, non-differentiable reward functions. △ Less

Submitted 2 June, 2025; v1 submitted 21 May, 2025; originally announced May 2025.

Comments: Under review

Mixture of Routers

Authors: Jia-Chen Zhang, Yu-Jie Xiong, Xi-He Qiu, Chun-Ming Xia, Fei Dai, Zheng Zhou

Abstract: Supervised fine-tuning (SFT) is a milestone in aligning large language models with human instructions and adapting them to downstream tasks. In particular, Low-Rank Adaptation (LoRA) has gained widespread attention due to its parameter efficiency. However, its impact on improving the performance of large models remains limited. Recent studies suggest that combining LoRA with Mixture-of-Experts (Mo… ▽ More Supervised fine-tuning (SFT) is a milestone in aligning large language models with human instructions and adapting them to downstream tasks. In particular, Low-Rank Adaptation (LoRA) has gained widespread attention due to its parameter efficiency. However, its impact on improving the performance of large models remains limited. Recent studies suggest that combining LoRA with Mixture-of-Experts (MoE) can significantly enhance fine-tuning performance. MoE adapts to the diversity and complexity of datasets by dynamically selecting the most suitable experts, thereby improving task accuracy and efficiency. Despite impressive results, recent studies reveal issues in the MoE routing mechanism, such as incorrect assignments and imbalanced expert allocation. Inspired by the principles of Redundancy and Fault Tolerance Theory. We innovatively integrate the concept of Mixture of Experts into the routing mechanism and propose an efficient fine-tuning method called Mixture of Routers (MoR). It employs multiple sub-routers for joint selection and uses a learnable main router to determine the weights of the sub-routers. The results show that MoR outperforms baseline models on most tasks, achieving an average performance improvement of 1%. MoR can serve as a plug-and-play, parameter-efficient fine-tuning method suitable for a wide range of applications. Our code is available here: https://anonymous.4open.science/r/MoR-DFC6. △ Less

Submitted 4 November, 2025; v1 submitted 30 March, 2025; originally announced March 2025.

Comments: Under consideration at Pattern Recognition Letters

Exploring the Evolution of Physics Cognition in Video Generation: A Survey

Authors: Minghui Lin, Xiang Wang, Yishan Wang, Shu Wang, Fengqi Dai, Pengxiang Ding, Cunxiang Wang, Zhengrong Zuo, Nong Sang, Siteng Huang, Donglin Wang

Abstract: Recent advancements in video generation have witnessed significant progress, especially with the rapid advancement of diffusion models. Despite this, their deficiencies in physical cognition have gradually received widespread attention - generated content often violates the fundamental laws of physics, falling into the dilemma of ''visual realism but physical absurdity". Researchers began to incre… ▽ More Recent advancements in video generation have witnessed significant progress, especially with the rapid advancement of diffusion models. Despite this, their deficiencies in physical cognition have gradually received widespread attention - generated content often violates the fundamental laws of physics, falling into the dilemma of ''visual realism but physical absurdity". Researchers began to increasingly recognize the importance of physical fidelity in video generation and attempted to integrate heuristic physical cognition such as motion representations and physical knowledge into generative systems to simulate real-world dynamic scenarios. Considering the lack of a systematic overview in this field, this survey aims to provide a comprehensive summary of architecture designs and their applications to fill this gap. Specifically, we discuss and organize the evolutionary process of physical cognition in video generation from a cognitive science perspective, while proposing a three-tier taxonomy: 1) basic schema perception for generation, 2) passive cognition of physical knowledge for generation, and 3) active cognition for world simulation, encompassing state-of-the-art methods, classical paradigms, and benchmarks. Subsequently, we emphasize the inherent key challenges in this domain and delineate potential pathways for future research, contributing to advancing the frontiers of discussion in both academia and industry. Through structured review and interdisciplinary analysis, this survey aims to provide directional guidance for developing interpretable, controllable, and physically consistent video generation paradigms, thereby propelling generative models from the stage of ''visual mimicry'' towards a new phase of ''human-like physical comprehension''. △ Less

Submitted 27 March, 2025; originally announced March 2025.

Comments: A comprehensive list of papers studied in this survey is available at https://github.com/minnie-lin/Awesome-Physics-Cognition-based-Video-Generation

HyperLoRA: Parameter-Efficient Adaptive Generation for Portrait Synthesis

Authors: Mengtian Li, Jinshu Chen, Wanquan Feng, Bingchuan Li, Fei Dai, Songtao Zhao, Qian He

Abstract: Personalized portrait synthesis, essential in domains like social entertainment, has recently made significant progress. Person-wise fine-tuning based methods, such as LoRA and DreamBooth, can produce photorealistic outputs but need training on individual samples, consuming time and resources and posing an unstable risk. Adapter based techniques such as IP-Adapter freeze the foundational model par… ▽ More Personalized portrait synthesis, essential in domains like social entertainment, has recently made significant progress. Person-wise fine-tuning based methods, such as LoRA and DreamBooth, can produce photorealistic outputs but need training on individual samples, consuming time and resources and posing an unstable risk. Adapter based techniques such as IP-Adapter freeze the foundational model parameters and employ a plug-in architecture to enable zero-shot inference, but they often exhibit a lack of naturalness and authenticity, which are not to be overlooked in portrait synthesis tasks. In this paper, we introduce a parameter-efficient adaptive generation method, namely HyperLoRA, that uses an adaptive plug-in network to generate LoRA weights, merging the superior performance of LoRA with the zero-shot capability of adapter scheme. Through our carefully designed network structure and training strategy, we achieve zero-shot personalized portrait generation (supporting both single and multiple image inputs) with high photorealism, fidelity, and editability. △ Less

Submitted 21 March, 2025; originally announced March 2025.

A Preliminary Investigation into Theory-Practice Barriers in Sino-New Zealand Undergraduate Computing Education

Authors: Fei Dai, Anthony Robins, Zhihao Peng, Wanni Huang, Chiu-Pih Tan, Tianzhen Chen

Abstract: This paper investigates the barriers hindering the effective transition from theoretical knowledge to practical application in a Sino-New Zealand double-degree undergraduate computing program. In this unique educational setting, students study at a campus in China but complete both Chinese and New Zealand courses taught jointly by lecturers from both countries. Through a questionnaire administered… ▽ More This paper investigates the barriers hindering the effective transition from theoretical knowledge to practical application in a Sino-New Zealand double-degree undergraduate computing program. In this unique educational setting, students study at a campus in China but complete both Chinese and New Zealand courses taught jointly by lecturers from both countries. Through a questionnaire administered to these students, we identify critical obstacles such as insufficient foundational knowledge, language barriers, cultural and pedagogical differences, and difficulties adapting to distinct educational systems. Our analysis reveals that these barriers significantly affect students' academic performance, engagement, and skill development. Based on the findings, we propose targeted interventions, including specialized bridging courses, enhanced language support, refined teaching methods, and improved resource allocation. △ Less

Submitted 17 March, 2025; originally announced March 2025.

Comments: This paper has been accepted in CSEDU 2025

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Authors: DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Peiyi Wang, Qihao Zhu, Runxin Xu, Ruoyu Zhang, Shirong Ma, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, Aixin Liu, Bing Xue, Bingxuan Wang, Bochao Wu, Bei Feng, Chengda Lu , et al. (175 additional authors not shown)

Abstract: General reasoning represents a long-standing and formidable challenge in artificial intelligence. Recent breakthroughs, exemplified by large language models (LLMs) and chain-of-thought prompting, have achieved considerable success on foundational reasoning tasks. However, this success is heavily contingent upon extensive human-annotated demonstrations, and models' capabilities are still insufficie… ▽ More General reasoning represents a long-standing and formidable challenge in artificial intelligence. Recent breakthroughs, exemplified by large language models (LLMs) and chain-of-thought prompting, have achieved considerable success on foundational reasoning tasks. However, this success is heavily contingent upon extensive human-annotated demonstrations, and models' capabilities are still insufficient for more complex problems. Here we show that the reasoning abilities of LLMs can be incentivized through pure reinforcement learning (RL), obviating the need for human-labeled reasoning trajectories. The proposed RL framework facilitates the emergent development of advanced reasoning patterns, such as self-reflection, verification, and dynamic strategy adaptation. Consequently, the trained model achieves superior performance on verifiable tasks such as mathematics, coding competitions, and STEM fields, surpassing its counterparts trained via conventional supervised learning on human demonstrations. Moreover, the emergent reasoning patterns exhibited by these large-scale models can be systematically harnessed to guide and enhance the reasoning capabilities of smaller models. △ Less

Submitted 3 January, 2026; v1 submitted 22 January, 2025; originally announced January 2025.

Journal ref: Nature volume 645, pages 633-638 (2025)

DeepSeek-V3 Technical Report

Authors: DeepSeek-AI, Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, Damai Dai, Daya Guo, Dejian Yang, Deli Chen, Dongjie Ji, Erhang Li, Fangyun Lin, Fucong Dai, Fuli Luo, Guangbo Hao, Guanting Chen, Guowei Li, H. Zhang, Han Bao , et al. (175 additional authors not shown)

Abstract: We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly validated in DeepSeek-V2. Furthermore, DeepSeek-V3 pioneers an auxiliary-loss-free strategy for loa… ▽ More We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly validated in DeepSeek-V2. Furthermore, DeepSeek-V3 pioneers an auxiliary-loss-free strategy for load balancing and sets a multi-token prediction training objective for stronger performance. We pre-train DeepSeek-V3 on 14.8 trillion diverse and high-quality tokens, followed by Supervised Fine-Tuning and Reinforcement Learning stages to fully harness its capabilities. Comprehensive evaluations reveal that DeepSeek-V3 outperforms other open-source models and achieves performance comparable to leading closed-source models. Despite its excellent performance, DeepSeek-V3 requires only 2.788M H800 GPU hours for its full training. In addition, its training process is remarkably stable. Throughout the entire training process, we did not experience any irrecoverable loss spikes or perform any rollbacks. The model checkpoints are available at https://github.com/deepseek-ai/DeepSeek-V3. △ Less

Submitted 18 February, 2025; v1 submitted 26 December, 2024; originally announced December 2024.

Exact: Exploring Space-Time Perceptive Clues for Weakly Supervised Satellite Image Time Series Semantic Segmentation

Authors: Hao Zhu, Yan Zhu, Jiayu Xiao, Tianxiang Xiao, Yike Ma, Yucheng Zhang, Feng Dai

Abstract: Automated crop mapping through Satellite Image Time Series (SITS) has emerged as a crucial avenue for agricultural monitoring and management. However, due to the low resolution and unclear parcel boundaries, annotating pixel-level masks is exceptionally complex and time-consuming in SITS. This paper embraces the weakly supervised paradigm (i.e., only image-level categories available) to liberate t… ▽ More Automated crop mapping through Satellite Image Time Series (SITS) has emerged as a crucial avenue for agricultural monitoring and management. However, due to the low resolution and unclear parcel boundaries, annotating pixel-level masks is exceptionally complex and time-consuming in SITS. This paper embraces the weakly supervised paradigm (i.e., only image-level categories available) to liberate the crop mapping task from the exhaustive annotation burden. The unique characteristics of SITS give rise to several challenges in weakly supervised learning: (1) noise perturbation from spatially neighboring regions, and (2) erroneous semantic bias from anomalous temporal periods. To address the above difficulties, we propose a novel method, termed exploring space-time perceptive clues (Exact). First, we introduce a set of spatial clues to explicitly capture the representative patterns of different crops from the most class-relative regions. Besides, we leverage the temporal-to-class interaction of the model to emphasize the contributions of pivotal clips, thereby enhancing the model perception for crop regions. Build upon the space-time perceptive clues, we derive the clue-based CAMs to effectively supervise the SITS segmentation network. Our method demonstrates impressive performance on various SITS benchmarks. Remarkably, the segmentation network trained on Exact-generated masks achieves 95% of its fully supervised performance, showing the bright promise of weakly supervised paradigm in crop mapping scenario. Our code will be publicly available. △ Less

Submitted 5 December, 2024; originally announced December 2024.

Comments: Under review. Code will be available at https://github.com/MiSsU-HH/Exact

I2VControl: Disentangled and Unified Video Motion Synthesis Control

Authors: Wanquan Feng, Tianhao Qi, Jiawei Liu, Mingzhen Sun, Pengqi Tu, Tianxiang Ma, Fei Dai, Songtao Zhao, Siyu Zhou, Qian He

Abstract: Motion controllability is crucial in video synthesis. However, most previous methods are limited to single control types, and combining them often results in logical conflicts. In this paper, we propose a disentangled and unified framework, namely I2VControl, to overcome the logical conflicts. We rethink camera control, object dragging, and motion brush, reformulating all tasks into a consistent r… ▽ More Motion controllability is crucial in video synthesis. However, most previous methods are limited to single control types, and combining them often results in logical conflicts. In this paper, we propose a disentangled and unified framework, namely I2VControl, to overcome the logical conflicts. We rethink camera control, object dragging, and motion brush, reformulating all tasks into a consistent representation based on point trajectories, each managed by a dedicated formulation. Accordingly, we propose a spatial partitioning strategy, where each unit is assigned to a concomitant control category, enabling diverse control types to be dynamically orchestrated within a single synthesis pipeline without conflicts. Furthermore, we design an adapter structure that functions as a plug-in for pre-trained models and is agnostic to specific model architectures. We conduct extensive experiments, achieving excellent performance on various control tasks, and our method further facilitates user-driven creative combinations, enhancing innovation and creativity. Project page: https://wanquanf.github.io/I2VControl . △ Less

Submitted 30 July, 2025; v1 submitted 25 November, 2024; originally announced November 2024.

Comments: Accepted to ICCV 2025. Project page: https://wanquanf.github.io/I2VControl

Focus-Consistent Multi-Level Aggregation for Compositional Zero-Shot Learning

Authors: Fengyuan Dai, Siteng Huang, Min Zhang, Biao Gong, Donglin Wang

Abstract: To transfer knowledge from seen attribute-object compositions to recognize unseen ones, recent compositional zero-shot learning (CZSL) methods mainly discuss the optimal classification branches to identify the elements, leading to the popularity of employing a three-branch architecture. However, these methods mix up the underlying relationship among the branches, in the aspect of consistency and d… ▽ More To transfer knowledge from seen attribute-object compositions to recognize unseen ones, recent compositional zero-shot learning (CZSL) methods mainly discuss the optimal classification branches to identify the elements, leading to the popularity of employing a three-branch architecture. However, these methods mix up the underlying relationship among the branches, in the aspect of consistency and diversity. Specifically, consistently providing the highest-level features for all three branches increases the difficulty in distinguishing classes that are superficially similar. Furthermore, a single branch may focus on suboptimal regions when spatial messages are not shared between the personalized branches. Recognizing these issues and endeavoring to address them, we propose a novel method called Focus-Consistent Multi-Level Aggregation (FOMA). Our method incorporates a Multi-Level Feature Aggregation (MFA) module to generate personalized features for each branch based on the image content. Additionally, a Focus-Consistent Constraint encourages a consistent focus on the informative regions, thereby implicitly exchanging spatial information between all branches. Extensive experiments on three benchmark datasets (UT-Zappos, C-GQA, and Clothing16K) demonstrate that our FOMA outperforms SOTA. △ Less

Submitted 30 August, 2024; originally announced August 2024.

Comments: Compositional Zero-Shot Learning

TopoLogic: An Interpretable Pipeline for Lane Topology Reasoning on Driving Scenes

Authors: Yanping Fu, Wenbin Liao, Xinyuan Liu, Hang xu, Yike Ma, Feng Dai, Yucheng Zhang

Abstract: As an emerging task that integrates perception and reasoning, topology reasoning in autonomous driving scenes has recently garnered widespread attention. However, existing work often emphasizes "perception over reasoning": they typically boost reasoning performance by enhancing the perception of lanes and directly adopt MLP to learn lane topology from lane query. This paradigm overlooks the geomet… ▽ More As an emerging task that integrates perception and reasoning, topology reasoning in autonomous driving scenes has recently garnered widespread attention. However, existing work often emphasizes "perception over reasoning": they typically boost reasoning performance by enhancing the perception of lanes and directly adopt MLP to learn lane topology from lane query. This paradigm overlooks the geometric features intrinsic to the lanes themselves and are prone to being influenced by inherent endpoint shifts in lane detection. To tackle this issue, we propose an interpretable method for lane topology reasoning based on lane geometric distance and lane query similarity, named TopoLogic. This method mitigates the impact of endpoint shifts in geometric space, and introduces explicit similarity calculation in semantic space as a complement. By integrating results from both spaces, our methods provides more comprehensive information for lane topology. Ultimately, our approach significantly outperforms the existing state-of-the-art methods on the mainstream benchmark OpenLane-V2 (23.9 v.s. 10.9 in TOP$_{ll}$ and 44.1 v.s. 39.8 in OLS on subset_A. Additionally, our proposed geometric distance topology reasoning method can be incorporated into well-trained models without re-training, significantly boost the performance of lane topology reasoning. The code is released at https://github.com/Franpin/TopoLogic. △ Less

Submitted 23 May, 2024; originally announced May 2024.

Modeling Supply Chain Interaction and Disruption: Insights from Real-world Data and Complex Adaptive System

Authors: Jiawei Feng, Mengsi Cai, Fangze Dai, Tianci Bu, Xiaoyu Zhang, Huijun Zheng, Xin Lu

Abstract: In the rapidly evolving automotive industry, Systems-on-Chips (SoCs) are playing an increasingly crucial role in enhancing vehicle intelligence, connectivity, and safety features. For enterprises whose business encompasses automotive SoCs, the sustained and stable provision and receipt of SoC relevant goods or services are essential. Considering the imperative for a resilient and adaptable supply… ▽ More In the rapidly evolving automotive industry, Systems-on-Chips (SoCs) are playing an increasingly crucial role in enhancing vehicle intelligence, connectivity, and safety features. For enterprises whose business encompasses automotive SoCs, the sustained and stable provision and receipt of SoC relevant goods or services are essential. Considering the imperative for a resilient and adaptable supply network, enterprises are concentrating their efforts on formulating strategies to address risks stemming from supply chain disruptions caused by technological obsolescence, natural disasters, and geopolitical tensions. This study presents an open supply knowledge extraction and complement approach and build a supply chain network of automotive SoC enterprises in China, which incorporates cross-domain named entity recognition under limited information, fuzzy matching of firm entities, and supply relation inferring based on knowledge graph. Subsequently, we exhibit the degree and registered capital distribution across firms, and analyze the correlations between centrality metrics in the supply chain network. Finally, based on recovery capacity and risk transfer, two interaction disruption models (IDMs) are developed to elucidate the adaptive behaviors and effect of network disruptions under various business and attack strategies. This research not only aids in exploring the complexities of Chinese automotive SoC supply chain but also enriches our understanding of the dynamics of firm behavior in this crucial industry sector. △ Less

Submitted 17 May, 2024; originally announced May 2024.

Comments: arXiv admin note: text overlap with arXiv:2304.10428 by other authors

Acoustic tactile sensing for mobile robot wheels

Authors: Wilfred Mason, David Brenken, Falcon Z. Dai, Ricardo Gonzalo Cruz Castillo, Olivier St-Martin Cormier, Audrey Sedal

Abstract: Tactile sensing in mobile robots remains under-explored, mainly due to challenges related to sensor integration and the complexities of distributed sensing. In this work, we present a tactile sensing architecture for mobile robots based on wheel-mounted acoustic waveguides. Our sensor architecture enables tactile sensing along the entire circumference of a wheel with a single active component: an… ▽ More Tactile sensing in mobile robots remains under-explored, mainly due to challenges related to sensor integration and the complexities of distributed sensing. In this work, we present a tactile sensing architecture for mobile robots based on wheel-mounted acoustic waveguides. Our sensor architecture enables tactile sensing along the entire circumference of a wheel with a single active component: an off-the-shelf acoustic rangefinder. We present findings showing that our sensor, mounted on the wheel of a mobile robot, is capable of discriminating between different terrains, detecting and classifying obstacles with different geometries, and performing collision detection via contact localization. We also present a comparison between our sensor and sensors traditionally used in mobile robots, and point to the potential for sensor fusion approaches that leverage the unique capabilities of our tactile sensing architecture. Our findings demonstrate that autonomous mobile robots can further leverage our sensor architecture for diverse mapping tasks requiring knowledge of terrain material, surface topology, and underlying structure. △ Less

Submitted 28 February, 2024; originally announced February 2024.

Comments: 12 pages, 12 figures

Subwords as Skills: Tokenization for Sparse-Reward Reinforcement Learning

Authors: David Yunis, Justin Jung, Falcon Dai, Matthew Walter

Abstract: Exploration in sparse-reward reinforcement learning is difficult due to the requirement of long, coordinated sequences of actions in order to achieve any reward. Moreover, in continuous action spaces there are an infinite number of possible actions, which only increases the difficulty of exploration. One class of methods designed to address these issues forms temporally extended actions, often cal… ▽ More Exploration in sparse-reward reinforcement learning is difficult due to the requirement of long, coordinated sequences of actions in order to achieve any reward. Moreover, in continuous action spaces there are an infinite number of possible actions, which only increases the difficulty of exploration. One class of methods designed to address these issues forms temporally extended actions, often called skills, from interaction data collected in the same domain, and optimizes a policy on top of this new action space. Typically such methods require a lengthy pretraining phase, especially in continuous action spaces, in order to form the skills before reinforcement learning can begin. Given prior evidence that the full range of the continuous action space is not required in such tasks, we propose a novel approach to skill-generation with two components. First we discretize the action space through clustering, and second we leverage a tokenization technique borrowed from natural language processing to generate temporally extended actions. Such a method outperforms baselines for skill-generation in several challenging sparse-reward domains, and requires orders-of-magnitude less computation in skill-generation and online rollouts. Our code is available at \url{https://github.com/dyunis/subwords_as_skills}. △ Less

Submitted 30 October, 2024; v1 submitted 8 September, 2023; originally announced September 2023.

Comments: Accepted to NeurIPS 2024

A stochastic block model for community detection in attributed networks

Authors: Xiao Wang, Fang Dai, Wenyan Guo, Junfeng Wang

Abstract: Community detection is an important content in complex network analysis. The existing community detection methods in attributed networks mostly focus on only using network structure, while the methods of integrating node attributes is mainly for the traditional community structures, and cannot detect multipartite structures and mixture structures in network. In addition, the model-based community… ▽ More Community detection is an important content in complex network analysis. The existing community detection methods in attributed networks mostly focus on only using network structure, while the methods of integrating node attributes is mainly for the traditional community structures, and cannot detect multipartite structures and mixture structures in network. In addition, the model-based community detection methods currently proposed for attributed networks do not fully consider unique topology information of nodes, such as betweenness centrality and clustering coefficient. Therefore, a stochastic block model that integrates betweenness centrality and clustering coefficient of nodes for community detection in attributed networks, named BCSBM, is proposed in this paper. Different from other generative models for attributed networks, the generation process of links and attributes in BCSBM model follows the Poisson distribution, and the probability between community is considered based on the stochastic block model. Moreover, the betweenness centrality and clustering coefficient of nodes are introduced into the process of links and attributes generation. Finally, the expectation maximization algorithm is employed to estimate the parameters of the BCSBM model, and the node-community memberships is obtained through the hard division process, so the community detection is completed. By experimenting on six real-work networks containing different network structures, and comparing with the community detection results of five algorithms, the experimental results show that the BCSBM model not only inherits the advantages of the stochastic block model and can detect various network structures, but also has good data fitting ability due to introducing the betweenness centrality and clustering coefficient of nodes. Overall, the performance of this model is superior to other five compared algorithms. △ Less

Submitted 30 August, 2023; originally announced August 2023.

On Reward Structures of Markov Decision Processes

Authors: Falcon Z. Dai

Abstract: A Markov decision process can be parameterized by a transition kernel and a reward function. Both play essential roles in the study of reinforcement learning as evidenced by their presence in the Bellman equations. In our inquiry of various kinds of "costs" associated with reinforcement learning inspired by the demands in robotic applications, rewards are central to understanding the structure of… ▽ More A Markov decision process can be parameterized by a transition kernel and a reward function. Both play essential roles in the study of reinforcement learning as evidenced by their presence in the Bellman equations. In our inquiry of various kinds of "costs" associated with reinforcement learning inspired by the demands in robotic applications, rewards are central to understanding the structure of a Markov decision process and reward-centric notions can elucidate important concepts in reinforcement learning. Specifically, we study the sample complexity of policy evaluation and develop a novel estimator with an instance-specific error bound of $\tilde{O}(\sqrt{\frac{τ_s}{n}})$ for estimating a single state value. Under the online regret minimization setting, we refine the transition-based MDP constant, diameter, into a reward-based constant, maximum expected hitting cost, and with it, provide a theoretical explanation for how a well-known technique, potential-based reward shaping, could accelerate learning with expert knowledge. In an attempt to study safe reinforcement learning, we model hazardous environments with irrecoverability and proposed a quantitative notion of safe learning via reset efficiency. In this setting, we modify a classic algorithm to account for resets achieving promising preliminary numerical results. Lastly, for MDPs with multiple reward functions, we develop a planning algorithm that computationally efficiently finds Pareto-optimal stochastic policies. △ Less

Submitted 31 August, 2023; v1 submitted 28 August, 2023; originally announced August 2023.

Comments: This PhD thesis draws heavily from arXiv:1907.02114 and arXiv:2002.06299; minor edits

Rethinking Boundary Discontinuity Problem for Oriented Object Detection

Authors: Hang Xu, Xinyuan Liu, Haonan Xu, Yike Ma, Zunjie Zhu, Chenggang Yan, Feng Dai

Abstract: Oriented object detection has been developed rapidly in the past few years, where rotation equivariance is crucial for detectors to predict rotated boxes. It is expected that the prediction can maintain the corresponding rotation when objects rotate, but severe mutation in angular prediction is sometimes observed when objects rotate near the boundary angle, which is well-known boundary discontinui… ▽ More Oriented object detection has been developed rapidly in the past few years, where rotation equivariance is crucial for detectors to predict rotated boxes. It is expected that the prediction can maintain the corresponding rotation when objects rotate, but severe mutation in angular prediction is sometimes observed when objects rotate near the boundary angle, which is well-known boundary discontinuity problem. The problem has been long believed to be caused by the sharp loss increase at the angular boundary, and widely used joint-optim IoU-like methods deal with this problem by loss-smoothing. However, we experimentally find that even state-of-the-art IoU-like methods actually fail to solve the problem. On further analysis, we find that the key to solution lies in encoding mode of the smoothing function rather than in joint or independent optimization. In existing IoU-like methods, the model essentially attempts to fit the angular relationship between box and object, where the break point at angular boundary makes the predictions highly unstable.To deal with this issue, we propose a dual-optimization paradigm for angles. We decouple reversibility and joint-optim from single smoothing function into two distinct entities, which for the first time achieves the objectives of both correcting angular boundary and blending angle with other parameters.Extensive experiments on multiple datasets show that boundary discontinuity problem is well-addressed. Moreover, typical IoU-like methods are improved to the same level without obvious performance gap. The code is available at https://github.com/hangxu-cv/cvpr24acm. △ Less

Submitted 21 March, 2024; v1 submitted 17 May, 2023; originally announced May 2023.

Comments: cvpr 2024

Universal discretization and sparse sampling recovery

Authors: F. Dai, V. Temlyakov

Abstract: Recently, it was discovered that for a given function class $\mathbf{F}$ the error of best linear recovery in the square norm can be bounded above by the Kolmogorov width of $\mathbf{F}$ in the uniform norm. That analysis is based on deep results in discretization of the square norm of functions from finite dimensional subspaces. In this paper we show how very recent results on universal discretiz… ▽ More Recently, it was discovered that for a given function class $\mathbf{F}$ the error of best linear recovery in the square norm can be bounded above by the Kolmogorov width of $\mathbf{F}$ in the uniform norm. That analysis is based on deep results in discretization of the square norm of functions from finite dimensional subspaces. In this paper we show how very recent results on universal discretization of the square norm of functions from a collection of finite dimensional subspaces lead to an inequality between optimal sparse recovery in the square norm and best sparse approximations in the uniform norm with respect to appropriate dictionaries. △ Less

Submitted 16 May, 2023; v1 submitted 14 January, 2023; originally announced January 2023.

Comments: 41 pages

MSC Class: Primary 65J05; Secondary 42A05; 65D30; 41A63

OpTree: An Efficient Algorithm for All-gather Operation in Optical Interconnect Systems

Authors: Fei Dai, Yawen Chen, Zhiyi Huang, Haibo Zhang

Abstract: All-gather collective communication is one of the most important communication primitives in parallel and distributed computation, which plays an essential role in many HPC applications such as distributed Deep Learning (DL) with model and hybrid parallelism. To solve the communication bottleneck of All-gather, optical interconnection network can provide unprecedented high bandwidth and reliabilit… ▽ More All-gather collective communication is one of the most important communication primitives in parallel and distributed computation, which plays an essential role in many HPC applications such as distributed Deep Learning (DL) with model and hybrid parallelism. To solve the communication bottleneck of All-gather, optical interconnection network can provide unprecedented high bandwidth and reliability for data transfer among the distributed nodes. However, most traditional All-gather algorithms are designed for electrical interconnection, which cannot fit well for optical interconnect systems, resulting in poor performance. This paper proposes an efficient scheme, called OpTree, for All-gather operation on optical interconnect systems. OpTree derives an optimal $m$-ary tree corresponding to the optimal number of communication stages, achieving minimum communication time. We further analyze and compare the communication steps of OpTree with existing All-gather algorithms. Theoretical results exhibit that OpTree requires much less number of communication steps than existing All-gather algorithms on optical interconnect systems. Simulation results show that OpTree can reduce communication time by 72.21%, 94.30%, and 88.58%, respectively, compared with three existing All-gather schemes, WRHT, Ring, and NE. △ Less

Submitted 28 November, 2022; originally announced November 2022.

Comments: This paper is under review at a conference

DPA-1: Pretraining of Attention-based Deep Potential Model for Molecular Simulation

Authors: Duo Zhang, Hangrui Bi, Fu-Zhi Dai, Wanrun Jiang, Linfeng Zhang, Han Wang

Abstract: Machine learning assisted modeling of the inter-atomic potential energy surface (PES) is revolutionizing the field of molecular simulation. With the accumulation of high-quality electronic structure data, a model that can be pretrained on all available data and finetuned on downstream tasks with a small additional effort would bring the field to a new stage. Here we propose DPA-1, a Deep Potential… ▽ More Machine learning assisted modeling of the inter-atomic potential energy surface (PES) is revolutionizing the field of molecular simulation. With the accumulation of high-quality electronic structure data, a model that can be pretrained on all available data and finetuned on downstream tasks with a small additional effort would bring the field to a new stage. Here we propose DPA-1, a Deep Potential model with a novel attention mechanism, which is highly effective for representing the conformation and chemical spaces of atomic systems and learning the PES. We tested DPA-1 on a number of systems and observed superior performance compared with existing benchmarks. When pretrained on large-scale datasets containing 56 elements, DPA-1 can be successfully applied to various downstream tasks with a great improvement of sample efficiency. Surprisingly, for different elements, the learned type embedding parameters form a $spiral$ in the latent space and have a natural correspondence with their positions on the periodic table, showing interesting interpretability of the pretrained DPA-1 model. △ Less

Submitted 14 September, 2023; v1 submitted 17 August, 2022; originally announced August 2022.

Efficient All-reduce for Distributed DNN Training in Optical Interconnect System

Authors: Fei Dai, Yawen Chen, Zhiyi Huang, Haibo Zhang, Fangfang Zhang

Abstract: Communication efficiency plays an important role in accelerating the distributed training of Deep Neural Networks (DNN). All-reduce is the crucial communication primitive to reduce model parameters in distributed DNN training. Most existing all-reduce algorithms are designed for traditional electrical interconnect systems, which cannot meet the communication requirements for distributed training o… ▽ More Communication efficiency plays an important role in accelerating the distributed training of Deep Neural Networks (DNN). All-reduce is the crucial communication primitive to reduce model parameters in distributed DNN training. Most existing all-reduce algorithms are designed for traditional electrical interconnect systems, which cannot meet the communication requirements for distributed training of large DNNs due to the low data bandwidth of the electrical interconnect systems. One of the promising alternatives for electrical interconnect is optical interconnect, which can provide high bandwidth, low transmission delay, and low power cost. We propose an efficient scheme called WRHT (Wavelength Reused Hierarchical Tree) for implementing all-reduce operation in optical interconnect systems. WRHT can take advantage of WDM (Wavelength Division Multiplexing) to reduce the communication time of distributed data-parallel DNN training. We further derive the required number of wavelengths, the minimum number of communication steps, and the communication time for the all-reduce operation on optical interconnect. The constraint of insertion loss is also considered in our analysis. Simulation results show that the communication time of all-reduce by WRHT is reduced by 80.81%, 64.36%, and 82.12%, respectively, compared with three traditional all-reduce algorithms according to our simulation results of an optical interconnect system. Our results also show that WRHT can reduce the communication time of all-reduce operation by 92.42% and 91.31% compared to two existing all-reduce algorithms running in the electrical interconnect system. △ Less

Submitted 16 February, 2023; v1 submitted 22 July, 2022; originally announced July 2022.

Comments: This paper is accepted by PPoPP as a poster

Cycle Self-Training for Semi-Supervised Object Detection with Distribution Consistency Reweighting

Authors: Hao Liu, Bin Chen, Bo Wang, Chunpeng Wu, Feng Dai, Peng Wu

Abstract: Recently, many semi-supervised object detection (SSOD) methods adopt teacher-student framework and have achieved state-of-the-art results. However, the teacher network is tightly coupled with the student network since the teacher is an exponential moving average (EMA) of the student, which causes a performance bottleneck. To address the coupling problem, we propose a Cycle Self-Training (CST) fram… ▽ More Recently, many semi-supervised object detection (SSOD) methods adopt teacher-student framework and have achieved state-of-the-art results. However, the teacher network is tightly coupled with the student network since the teacher is an exponential moving average (EMA) of the student, which causes a performance bottleneck. To address the coupling problem, we propose a Cycle Self-Training (CST) framework for SSOD, which consists of two teachers T1 and T2, two students S1 and S2. Based on these networks, a cycle self-training mechanism is built, i.e., S1${\rightarrow}$T1${\rightarrow}$S2${\rightarrow}$T2${\rightarrow}$S1. For S${\rightarrow}$T, we also utilize the EMA weights of the students to update the teachers. For T${\rightarrow}$S, instead of providing supervision for its own student S1(S2) directly, the teacher T1(T2) generates pseudo-labels for the student S2(S1), which looses the coupling effect. Moreover, owing to the property of EMA, the teacher is most likely to accumulate the biases from the student and make the mistakes irreversible. To mitigate the problem, we also propose a distribution consistency reweighting strategy, where pseudo-labels are reweighted based on distribution consistency across the teachers T1 and T2. With the strategy, the two students S2 and S1 can be trained robustly with noisy pseudo labels to avoid confirmation biases. Extensive experiments prove the superiority of CST by consistently improving the AP over the baseline and outperforming state-of-the-art methods by 2.1% absolute AP improvements with scarce labeled data. △ Less

Submitted 12 July, 2022; originally announced July 2022.

Comments: ACM Multimedia 2022

Forecasting SQL Query Cost at Twitter

Authors: Chunxu Tang, Beinan Wang, Zhenxiao Luo, Huijun Wu, Shajan Dasan, Maosong Fu, Yao Li, Mainak Ghosh, Ruchin Kabra, Nikhil Kantibhai Navadiya, Da Cheng, Fred Dai, Vrushali Channapattan, Prachi Mishra

Abstract: With the advent of the Big Data era, it is usually computationally expensive to calculate the resource usages of a SQL query with traditional DBMS approaches. Can we estimate the cost of each query more efficiently without any computation in a SQL engine kernel? Can machine learning techniques help to estimate SQL query resource utilization? The answers are yes. We propose a SQL query cost predict… ▽ More With the advent of the Big Data era, it is usually computationally expensive to calculate the resource usages of a SQL query with traditional DBMS approaches. Can we estimate the cost of each query more efficiently without any computation in a SQL engine kernel? Can machine learning techniques help to estimate SQL query resource utilization? The answers are yes. We propose a SQL query cost predictor service, which employs machine learning techniques to train models from historical query request logs and rapidly forecasts the CPU and memory resource usages of online queries without any computation in a SQL engine. At Twitter, infrastructure engineers are maintaining a large-scale SQL federation system across on-premises and cloud data centers for serving ad-hoc queries. The proposed service can help to improve query scheduling by relieving the issue of imbalanced online analytical processing (OLAP) workloads in the SQL engine clusters. It can also assist in enabling preemptive scaling. Additionally, the proposed approach uses plain SQL statements for the model training and online prediction, indicating it is both hardware and software-agnostic. The method can be generalized to broader SQL systems and heterogeneous environments. The models can achieve 97.9\% accuracy for CPU usage prediction and 97\% accuracy for memory usage prediction. △ Less

Submitted 12 April, 2022; originally announced April 2022.

Comments: 2021 IEEE International Conference on Cloud Engineering (IC2E). IEEE, 2021

Fully Three-dimensional Radial Visualization

Authors: Yifan Zhu, Fan Dai, Ranjan Maitra

Abstract: We develop methodology for three-dimensional (3D) radial visualization (RadViz) of multidimensional datasets. The classical two-dimensional (2D) RadViz visualizes multivariate data in the 2D plane by mapping every observation to a point inside the unit circle. Our tool, RadViz3D, distributes anchor points uniformly on the 3D unit sphere. We show that this uniform distribution provides the best vis… ▽ More We develop methodology for three-dimensional (3D) radial visualization (RadViz) of multidimensional datasets. The classical two-dimensional (2D) RadViz visualizes multivariate data in the 2D plane by mapping every observation to a point inside the unit circle. Our tool, RadViz3D, distributes anchor points uniformly on the 3D unit sphere. We show that this uniform distribution provides the best visualization with minimal artificial visual correlation for data with uncorrelated variables. However, anchor points can be placed exactly equi-distant from each other only for the five Platonic solids, so we provide equi-distant anchor points for these five settings, and approximately equi-distant anchor points via a Fibonacci grid for the other cases. Our methodology, implemented in the R package $radviz3d$, makes fully 3D RadViz possible and is shown to improve the ability of this nonlinear technique in more faithfully displaying simulated data as well as the crabs, olive oils and wine datasets. Additionally, because radial visualization is naturally suited for compositional data, we use RadViz3D to illustrate (i) the chemical composition of Longquan celadon ceramics and their Jingdezhen imitation over centuries, and (ii) US regional SARS-Cov-2 variants' prevalence in the Covid-19 pandemic during the summer 2021 surge of the Delta variant. △ Less

Submitted 19 October, 2021; originally announced October 2021.

Comments: 10 pages, 7 figures, 1 table

MSC Class: 62H25; 62H99; 62P10; 62P25 ACM Class: G.3; I.3.3; I.3.7; J.3; J.4

Journal ref: Journal of Computational and Graphical Statistics, 31(3), 935-944, 2022

Accelerating Fully Connected Neural Network on Optical Network-on-Chip (ONoC)

Authors: Fei Dai, Yawen Chen, Haibo Zhang, Zhiyi Huang

Abstract: Fully Connected Neural Network (FCNN) is a class of Artificial Neural Networks widely used in computer science and engineering, whereas the training process can take a long time with large datasets in existing many-core systems. Optical Network-on-Chip (ONoC), an emerging chip-scale optical interconnection technology, has great potential to accelerate the training of FCNN with low transmission del… ▽ More Fully Connected Neural Network (FCNN) is a class of Artificial Neural Networks widely used in computer science and engineering, whereas the training process can take a long time with large datasets in existing many-core systems. Optical Network-on-Chip (ONoC), an emerging chip-scale optical interconnection technology, has great potential to accelerate the training of FCNN with low transmission delay, low power consumption, and high throughput. However, existing methods based on Electrical Network-on-Chip (ENoC) cannot fit in ONoC because of the unique properties of ONoC. In this paper, we propose a fine-grained parallel computing model for accelerating FCNN training on ONoC and derive the optimal number of cores for each execution stage with the objective of minimizing the total amount of time to complete one epoch of FCNN training. To allocate the optimal number of cores for each execution stage, we present three mapping strategies and compare their advantages and disadvantages in terms of hotspot level, memory requirement, and state transitions. Simulation results show that the average prediction error for the optimal number of cores in NN benchmarks is within 2.3%. We further carry out extensive simulations which demonstrate that FCNN training time can be reduced by 22.28% and 4.91% on average using our proposed scheme, compared with traditional parallel computing methods that either allocate a fixed number of cores or allocate as many cores as possible, respectively. Compared with ENoC, simulation results show that under batch sizes of 64 and 128, on average ONoC can achieve 21.02% and 12.95% on reducing training time with 47.85% and 39.27% on saving energy, respectively. △ Less

Submitted 30 September, 2021; originally announced September 2021.

Comments: 14 pages, 10 figures. This paper is under the second review of IEEE Transactions of Computers

Unbiased IoU for Spherical Image Object Detection

Authors: Qiang Zhao, Bin Chen, Hang Xu, Yike Ma, Xiaodong Li, Bailan Feng, Chenggang Yan, Feng Dai

Abstract: As one of the most fundamental and challenging problems in computer vision, object detection tries to locate object instances and find their categories in natural images. The most important step in the evaluation of object detection algorithm is calculating the intersection-over-union (IoU) between the predicted bounding box and the ground truth one. Although this procedure is well-defined and sol… ▽ More As one of the most fundamental and challenging problems in computer vision, object detection tries to locate object instances and find their categories in natural images. The most important step in the evaluation of object detection algorithm is calculating the intersection-over-union (IoU) between the predicted bounding box and the ground truth one. Although this procedure is well-defined and solved for planar images, it is not easy for spherical image object detection. Existing methods either compute the IoUs based on biased bounding box representations or make excessive approximations, thus would give incorrect results. In this paper, we first identify that spherical rectangles are unbiased bounding boxes for objects in spherical images, and then propose an analytical method for IoU calculation without any approximations. Based on the unbiased representation and calculation, we also present an anchor free object detection algorithm for spherical images. The experiments on two spherical object detection datasets show that the proposed method can achieve better performance than existing methods. △ Less

Submitted 18 August, 2021; originally announced August 2021.

Word2vec Conjecture and A Limitative Result

Authors: Falcon Z. Dai

Abstract: Being inspired by the success of \texttt{word2vec} \citep{mikolov2013distributed} in capturing analogies, we study the conjecture that analogical relations can be represented by vector spaces. Unlike many previous works that focus on the distributional semantic aspect of \texttt{word2vec}, we study the purely \emph{representational} question: can \emph{all} semantic word-word relations be represen… ▽ More Being inspired by the success of \texttt{word2vec} \citep{mikolov2013distributed} in capturing analogies, we study the conjecture that analogical relations can be represented by vector spaces. Unlike many previous works that focus on the distributional semantic aspect of \texttt{word2vec}, we study the purely \emph{representational} question: can \emph{all} semantic word-word relations be represented by differences (or directions) of vectors? We call this the word2vec conjecture and point out some of its desirable implications. However, we will exhibit a class of relations that cannot be represented in this way, thus falsifying the conjecture and establishing a limitative result for the representability of semantic relations by vector spaces over fields of characteristic 0, e.g., real or complex numbers. △ Less

Submitted 23 October, 2020; originally announced October 2020.

Loop Estimator for Discounted Values in Markov Reward Processes

Authors: Falcon Z. Dai, Matthew R. Walter

Abstract: At the working heart of policy iteration algorithms commonly used and studied in the discounted setting of reinforcement learning, the policy evaluation step estimates the value of states with samples from a Markov reward process induced by following a Markov policy in a Markov decision process. We propose a simple and efficient estimator called loop estimator that exploits the regenerative struct… ▽ More At the working heart of policy iteration algorithms commonly used and studied in the discounted setting of reinforcement learning, the policy evaluation step estimates the value of states with samples from a Markov reward process induced by following a Markov policy in a Markov decision process. We propose a simple and efficient estimator called loop estimator that exploits the regenerative structure of Markov reward processes without explicitly estimating a full model. Our method enjoys a space complexity of $O(1)$ when estimating the value of a single positive recurrent state $s$ unlike TD with $O(S)$ or model-based methods with $O\left(S^2\right)$. Moreover, the regenerative structure enables us to show, without relying on the generative model approach, that the estimator has an instance-dependent convergence rate of $\widetilde{O}\left(\sqrt{τ_s/T}\right)$ over steps $T$ on a single sample path, where $τ_s$ is the maximal expected hitting time to state $s$. In preliminary numerical experiments, the loop estimator outperforms model-free methods, such as TD(k), and is competitive with the model-based estimator. △ Less

Submitted 3 March, 2021; v1 submitted 14 February, 2020; originally announced February 2020.

Comments: accepted to AAAI 2021

Encryption Algorithm for TCP Session Hijacking

Authors: Minghan Chen, Fangyan Dai, Bingjie Yan, Jieren Cheng, Longjuan Wang

Abstract: Distributed network of the computer and the design defects of the TCP protocol are given to the network attack to be multiplicative. Based on the simple and open assumptions of the TCP protocol in academic and collaborative communication environments, the protocol lacks secure authentication. In this paper, by adding RSA-based cryptography technology, RSA-based signature technology, DH key exchang… ▽ More Distributed network of the computer and the design defects of the TCP protocol are given to the network attack to be multiplicative. Based on the simple and open assumptions of the TCP protocol in academic and collaborative communication environments, the protocol lacks secure authentication. In this paper, by adding RSA-based cryptography technology, RSA-based signature technology, DH key exchange algorithm, and HAMC-SHA1 integrity verification technology to the TCP protocol, and propose a security strategy which can effectively defend against TCP session hijacking. △ Less

Submitted 4 February, 2020; originally announced February 2020.