Yao Ding

Tencent Hunyuan Team, Ao Liu, Botong Zhou et al. · tencent-ai

As Large Language Models (LLMs) rapidly advance, we introduce Hunyuan-TurboS, a novel large hybrid Transformer-Mamba Mixture of Experts (MoE) model. It synergistically combines Mamba's long-sequence processing efficiency with Transformer's superior contextual understanding. Hunyuan-TurboS features an adaptive long-short chain-of-thought (CoT) mechanism, dynamically switching between rapid responses for simple queries and deep "thinking" modes for complex problems, optimizing computational resources. Architecturally, this 56B activated (560B total) parameter model employs 128 layers (Mamba2, Attention, FFN) with an innovative AMF/MF block pattern. Faster Mamba2 ensures linear complexity, Grouped-Query Attention minimizes KV cache, and FFNs use an MoE structure. Pre-trained on 16T high-quality tokens, it supports a 256K context length and is the first industry-deployed large-scale Mamba model. Our comprehensive post-training strategy enhances capabilities via Supervised Fine-Tuning (3M instructions), a novel Adaptive Long-short CoT Fusion method, Multi-round Deliberation Learning for iterative improvement, and a two-stage Large-scale Reinforcement Learning process targeting STEM and general instruction-following. Evaluations show strong performance: overall top 7 rank on LMSYS Chatbot Arena with a score of 1356, outperforming leading models like Gemini-2.0-Flash-001 (1352) and o4-mini-2025-04-16 (1345). TurboS also achieves an average of 77.9% across 23 automated benchmarks. Hunyuan-TurboS balances high performance and efficiency, offering substantial capabilities at lower inference costs than many reasoning models, establishing a new paradigm for efficient large-scale pre-trained models.

Hongyang Gu, Qisong Yang, Lei Pu et al.

Extracting robust discriminative features is a critical challenge in person re-identification (ReID). While Transformer-based methods have successfully addressed some limitations of convolutional neural networks (CNNs), such as their local processing nature and information loss resulting from convolution and downsampling operations, they still face the scalability issue due to the quadratic increase in memory and computational requirements with the length of the input sequence. To overcome this, we propose a pure Mamba-based person ReID framework named ReIDMamba. Specifically, we have designed a Mamba-based strong baseline that effectively leverages fine-grained, discriminative global features by introducing multiple class tokens. To further enhance robust features learning within Mamba, we have carefully designed two novel techniques. First, the multi-granularity feature extractor (MGFE) module, designed with a multi-branch architecture and class token fusion, effectively forms multi-granularity features, enhancing both discrimination ability and fine-grained coverage. Second, the ranking-aware triplet regularization (RATR) is introduced to reduce redundancy in features from multiple branches, enhancing the diversity of multi-granularity features by incorporating both intra-class and inter-class diversity constraints, thus ensuring the robustness of person features. To our knowledge, this is the pioneering work that integrates a purely Mamba-driven approach into ReID research. Our proposed ReIDMamba model boasts only one-third the parameters of TransReID, along with lower GPU memory usage and faster inference throughput. Experimental results demonstrate ReIDMamba's superior and promising performance, achieving state-of-the-art performance on five person ReID benchmarks. Code is available at https://github.com/GuHY777/ReIDMamba.

Aitao Yang, Min Li, Yao Ding et al.

Efficient extraction of spectral sequences and geospatial information has always been a hot topic in hyperspectral image classification. In terms of spectral sequence feature capture, RNN and Transformer have become mainstream classification frameworks due to their long-range feature capture capabilities. In terms of spatial information aggregation, CNN enhances the receptive field to retain integrated spatial information as much as possible. However, the spectral feature-capturing architectures exhibit low computational efficiency, and CNNs lack the flexibility to perceive spatial contextual information. To address these issues, this paper proposes GraphMamba--an efficient graph structure learning vision Mamba classification framework that fully considers HSI characteristics to achieve deep spatial-spectral information mining. Specifically, we propose a novel hyperspectral visual GraphMamba processing paradigm (HVGM) that preserves spatial-spectral features by constructing spatial-spectral cubes and utilizes linear spectral encoding to enhance the operability of subsequent tasks. The core components of GraphMamba include the HyperMamba module for improving computational efficiency and the SpectralGCN module for adaptive spatial context awareness. The HyperMamba mitigates clutter interference by employing the global mask (GM) and introduces a parallel training inference architecture to alleviate computational bottlenecks. The SpatialGCN incorporates weighted multi-hop aggregation (WMA) spatial encoding to focus on highly correlated spatial structural features, thus flexibly aggregating contextual information while mitigating spatial noise interference. Extensive experiments were conducted on three different scales of real HSI datasets, and compared with the state-of-the-art classification frameworks, GraphMamba achieved optimal performance.

Xingwu Sun, Yanfeng Chen, Yiqing Huang et al. · tencent-ai

In this paper, we introduce Hunyuan-Large, which is currently the largest open-source Transformer-based mixture of experts model, with a total of 389 billion parameters and 52 billion activation parameters, capable of handling up to 256K tokens. We conduct a thorough evaluation of Hunyuan-Large's superior performance across various benchmarks including language understanding and generation, logical reasoning, mathematical problem-solving, coding, long-context, and aggregated tasks, where it outperforms LLama3.1-70B and exhibits comparable performance when compared to the significantly larger LLama3.1-405B model. Key practice of Hunyuan-Large include large-scale synthetic data that is orders larger than in previous literature, a mixed expert routing strategy, a key-value cache compression technique, and an expert-specific learning rate strategy. Additionally, we also investigate the scaling laws and learning rate schedule of mixture of experts models, providing valuable insights and guidances for future model development and optimization. The code and checkpoints of Hunyuan-Large are released to facilitate future innovations and applications. Codes: https://github.com/Tencent/Hunyuan-Large Models: https://huggingface.co/tencent/Tencent-Hunyuan-Large

Yaoming Cai, Zijia Zhang, Zhihua Cai et al.

This paper presents FLGC, a simple yet effective fully linear graph convolutional network for semi-supervised and unsupervised learning. Instead of using gradient descent, we train FLGC based on computing a global optimal closed-form solution with a decoupled procedure, resulting in a generalized linear framework and making it easier to implement, train, and apply. We show that (1) FLGC is powerful to deal with both graph-structured data and regular data, (2) training graph convolutional models with closed-form solutions improve computational efficiency without degrading performance, and (3) FLGC acts as a natural generalization of classic linear models in the non-Euclidean domain, e.g., ridge regression and subspace clustering. Furthermore, we implement a semi-supervised FLGC and an unsupervised FLGC by introducing an initial residual strategy, enabling FLGC to aggregate long-range neighborhoods and alleviate over-smoothing. We compare our semi-supervised and unsupervised FLGCs against many state-of-the-art methods on a variety of classification and clustering benchmarks, demonstrating that the proposed FLGC models consistently outperform previous methods in terms of accuracy, robustness, and learning efficiency. The core code of our FLGC is released at https://github.com/AngryCai/FLGC.

Yao Ding, Weijie Kang, Aitao Yang et al.

Hyperspectral image (HSI) clustering has been a fundamental but challenging task with zero training labels. Currently, some deep graph clustering methods have been successfully explored for HSI due to their outstanding performance in effective spatial structural information encoding. Nevertheless, insufficient structural information utilization, poor feature presentation ability, and weak graph update capability limit their performance. Thus, in this paper, a homophily structure graph learning with an adaptive filter clustering method (AHSGC) for HSI is proposed. Specifically, homogeneous region generation is first developed for HSI processing and constructing the original graph. Afterward, an adaptive filter graph encoder is designed to adaptively capture the high and low frequency features on the graph for subsequence processing. Then, a graph embedding clustering self-training decoder is developed with KL Divergence, with which the pseudo-label is generated for network training. Meanwhile, homophily-enhanced structure learning is introduced to update the graph according to the clustering task, in which the orient correlation estimation is adopted to estimate the node connection, and graph edge sparsification is designed to adjust the edges in the graph dynamically. Finally, a joint network optimization is introduced to achieve network self-training and update the graph. The K-means is adopted to express the latent features. Extensive experiments and repeated comparative analysis have verified that our AHSGC contains high clustering accuracy, low computational complexity, and strong robustness. The code source will be available at https://github.com/DY-HYX.

Muhammad Ahmad, Salvatore Distifano, Adil Mehmood Khan et al.

Hyperspectral Image Classification (HSC) presents significant challenges owing to the high dimensionality and intricate nature of Hyperspectral (HS) data. While traditional Machine Learning (TML) approaches have demonstrated effectiveness, they often encounter substantial obstacles in real-world applications, including the variability of optimal feature sets, subjectivity in human-driven design, inherent biases, and methodological limitations. Specifically, TML suffers from the curse of dimensionality, difficulties in feature selection and extraction, insufficient consideration of spatial information, limited robustness against noise, scalability issues, and inadequate adaptability to complex data distributions. In recent years, Deep Learning (DL) techniques have emerged as robust solutions to address these challenges. This survey offers a comprehensive overview of current trends and future prospects in HSC, emphasizing advancements from DL models to the increasing adoption of Transformer and Mamba Model architectures. We systematically review key concepts, methodologies, and state-of-the-art approaches in DL for HSC. Furthermore, we investigate the potential of Transformer-based models and the Mamba Model in HSC, detailing their advantages and challenges. Emerging trends in HSC are explored, including in-depth discussions on Explainable AI and Interoperability concepts, alongside Diffusion Models for image denoising, feature extraction, and image fusion. Comprehensive experimental results were conducted on three HS datasets to substantiate the efficacy of various conventional DL models and Transformers. Additionally, we identify several open challenges and pertinent research questions in the field of HSC. Finally, we outline future research directions and potential applications aimed at enhancing the accuracy and efficiency of HSC.

Yao Ding, Yuqing Wu, Ziyang Ding

With the acceleration of technological innovation efficient retrieval and classification of patent literature have become essential for intellectual property management and enterprise RD Traditional keyword and rulebased retrieval methods often fail to address complex query intents or capture semantic associations across technical domains resulting in incomplete and lowrelevance results This study presents an automated patent retrieval framework integrating Large Language Models LLMs with RetrievalAugmented Generation RAG technology The system comprises three components: 1) a preprocessing module for patent data standardization, 2) a highefficiency vector retrieval engine leveraging LLMgenerated embeddings, and 3) a RAGenhanced query module that combines external document retrieval with contextaware response generation Evaluations were conducted on the Google Patents dataset 20062024 containing millions of global patent records with metadata such as filing date domain and status The proposed gpt35turbo0125RAG configuration achieved 805 semantic matching accuracy and 92.1% recall surpassing baseline LLM methods by 28 percentage points The framework also demonstrated strong generalization in crossdomain classification and semantic clustering tasks These results validate the effectiveness of LLMRAG integration for intelligent patent retrieval providing a foundation for nextgeneration AIdriven intellectual property analysis platforms

Binghao Liu, Yao Ding, Jianbin Jiao et al.

Encouraging progress in few-shot semantic segmentation has been made by leveraging features learned upon base classes with sufficient training data to represent novel classes with few-shot examples. However, this feature sharing mechanism inevitably causes semantic aliasing between novel classes when they have similar compositions of semantic concepts. In this paper, we reformulate few-shot segmentation as a semantic reconstruction problem, and convert base class features into a series of basis vectors which span a class-level semantic space for novel class reconstruction. By introducing contrastive loss, we maximize the orthogonality of basis vectors while minimizing semantic aliasing between classes. Within the reconstructed representation space, we further suppress interference from other classes by projecting query features to the support vector for precise semantic activation. Our proposed approach, referred to as anti-aliasing semantic reconstruction (ASR), provides a systematic yet interpretable solution for few-shot learning problems. Extensive experiments on PASCAL VOC and MS COCO datasets show that ASR achieves strong results compared with the prior works.

Yuqi Gong, Xuehui Yu, Yao Ding et al.

FPN-based detectors have made significant progress in general object detection, e.g., MS COCO and PASCAL VOC. However, these detectors fail in certain application scenarios, e.g., tiny object detection. In this paper, we argue that the top-down connections between adjacent layers in FPN bring two-side influences for tiny object detection, not only positive. We propose a novel concept, fusion factor, to control information that deep layers deliver to shallow layers, for adapting FPN to tiny object detection. After series of experiments and analysis, we explore how to estimate an effective value of fusion factor for a particular dataset by a statistical method. The estimation is dependent on the number of objects distributed in each layer. Comprehensive experiments are conducted on tiny object detection datasets, e.g., TinyPerson and Tiny CityPersons. Our results show that when configuring FPN with a proper fusion factor, the network is able to achieve significant performance gains over the baseline on tiny object detection datasets. Codes and models will be released.