Ke Zhu

Yichi Zhang, Ke Zhu, Zhoufan Zhu

Learning Value-at-Risk (VaR) and Expected Shortfall (ES) is important for managing financial risks effectively. Existing approaches with limited parameters are vulnerable to model misspecification in the era of big data. To address this limitation, we propose a large tail risk model, the retrieval-enhanced self-grouping autoencoder (ReSGA), which is designed with millions of parameters to exploit the rich cross-sectional dependence and long-term temporal dynamics of assets using their characteristics. Applied to monthly US equity returns from 1926 to 2023 with 153 firm characteristics, ReSGA outperforms twelve econometric and machine learning competitors in terms of out-of-sample loss and statistical backtesting. In addition, its forecast advantages can translate into significant economic gains from long-short decile portfolios that are constructed by a new size-enhanced left-side momentum strategy. To clarify the role of complexity, we further conduct a systematic scaling analysis and demonstrate that improvements in joint VaR-ES forecasting are primarily driven by data complexity rather than model complexity. Finally, our analyses of group-importance and transfer-learning exhibit the interpretability and cross-market generalizability of ReSGA.

Zhoufan Zhu, Ningning Zhang, Ke Zhu

How to do big portfolio selection is very important but challenging for both researchers and practitioners. In this paper, we propose a new graph-based conditional moments (GRACE) method to do portfolio selection based on thousands of stocks or more. The GRACE method first learns the conditional quantiles and mean of stock returns via a factor-augmented temporal graph convolutional network, which guides the learning procedure through a factor-hypergraph built by the set of stock-to-stock relations from the domain knowledge as well as the set of factor-to-stock relations from the asset pricing knowledge. Next, the GRACE method learns the conditional variance, skewness, and kurtosis of stock returns from the learned conditional quantiles by using the quantiled conditional moment (QCM) method. The QCM method is a supervised learning procedure to learn these conditional higher-order moments, so it largely overcomes the computational difficulty from the classical high-dimensional GARCH-type methods. Moreover, the QCM method allows the mis-specification in modeling conditional quantiles to some extent, due to its regression-based nature. Finally, the GRACE method uses the learned conditional mean, variance, skewness, and kurtosis to construct several performance measures, which are criteria to sort the stocks to proceed the portfolio selection in the well-known 10-decile framework. An application to NASDAQ and NYSE stock markets shows that the GRACE method performs much better than its competitors, particularly when the performance measures are comprised of conditional variance, skewness, and kurtosis.

Ke Zhu, Yin-Yin He, Jianxin Wu

Neural network quantization aims to accelerate and trim full-precision neural network models by using low bit approximations. Methods adopting the quantization aware training (QAT) paradigm have recently seen a rapid growth, but are often conceptually complicated. This paper proposes a novel and highly effective QAT method, quantized feature distillation (QFD). QFD first trains a quantized (or binarized) representation as the teacher, then quantize the network using knowledge distillation (KD). Quantitative results show that QFD is more flexible and effective (i.e., quantization friendly) than previous quantization methods. QFD surpasses existing methods by a noticeable margin on not only image classification but also object detection, albeit being much simpler. Furthermore, QFD quantizes ViT and Swin-Transformer on MS-COCO detection and segmentation, which verifies its potential in real world deployment. To the best of our knowledge, this is the first time that vision transformers have been quantized in object detection and image segmentation tasks.

Ke Zhu, Minghao Fu, Jianxin Wu

Self-supervised learning (SSL) methods targeting scene images have seen a rapid growth recently, and they mostly rely on either a dedicated dense matching mechanism or a costly unsupervised object discovery module. This paper shows that instead of hinging on these strenuous operations, quality image representations can be learned by treating scene/multi-label image SSL simply as a multi-label classification problem, which greatly simplifies the learning framework. Specifically, multiple binary pseudo-labels are assigned for each input image by comparing its embeddings with those in two dictionaries, and the network is optimized using the binary cross entropy loss. The proposed method is named Multi-Label Self-supervised learning (MLS). Visualizations qualitatively show that clearly the pseudo-labels by MLS can automatically find semantically similar pseudo-positive pairs across different images to facilitate contrastive learning. MLS learns high quality representations on MS-COCO and achieves state-of-the-art results on classification, detection and segmentation benchmarks. At the same time, MLS is much simpler than existing methods, making it easier to deploy and for further exploration.

Ke Zhu, Zheng Ge, Liang Zhao et al.

This paper makes the first attempt towards unsupervised preference alignment in Vision-Language Models (VLMs). We generate chosen and rejected responses with regard to the original and augmented image pairs, and conduct preference alignment with direct preference optimization. It is based on a core idea: properly designed augmentation to the image input will induce VLM to generate false but hard negative responses, which helps the model to learn from and produce more robust and powerful answers. The whole pipeline no longer hinges on supervision from GPT-4 or human involvement during alignment, and is highly efficient with few lines of code. With only 8k randomly sampled unsupervised data, it achieves 90\% relative score to GPT-4 on complex reasoning in LLaVA-Bench, and improves LLaVA-7B/13B by 6.7\%/5.6\% score on complex multi-modal benchmark MM-Vet. Visualizations shows its improved ability to align with user-intentions. A series of ablations are firmly conducted to reveal the latent mechanism of the approach, which also indicates its potential towards further scaling. Code are available in https://github.com/Kevinz-code/SeVa.

Minghao Fu, Ke Zhu, Jianxin Wu

When pre-trained models become rapidly larger, the cost of fine-tuning on downstream tasks steadily increases, too. To economically fine-tune these models, parameter-efficient transfer learning (PETL) is proposed, which only tunes a tiny subset of trainable parameters to efficiently learn quality representations. However, current PETL methods are facing the dilemma that during training the GPU memory footprint is not effectively reduced as trainable parameters. PETL will likely fail, too, if the full fine-tuning encounters the out-of-GPU-memory issue. This phenomenon happens because trainable parameters from these methods are generally entangled with the backbone, such that a lot of intermediate states have to be stored in GPU memory for gradient propagation. To alleviate this problem, we introduce Disentangled Transfer Learning (DTL), which disentangles the trainable parameters from the backbone using a lightweight Compact Side Network (CSN). By progressively extracting task-specific information with a few low-rank linear mappings and appropriately adding the information back to the backbone, CSN effectively realizes knowledge transfer in various downstream tasks. We conducted extensive experiments to validate the effectiveness of our method. The proposed method not only reduces a large amount of GPU memory usage and trainable parameters, but also outperforms existing PETL methods by a significant margin in accuracy, achieving new state-of-the-art on several standard benchmarks. The code is available at https://github.com/heekhero/DTL.

Minghao Fu, Hao Yu, Jie Shao et al.

Deep neural networks, while achieving remarkable success across diverse tasks, demand significant resources, including computation, GPU memory, bandwidth, storage, and energy. Network quantization, as a standard compression and acceleration technique, reduces storage costs and enables potential inference acceleration by discretizing network weights and activations into a finite set of integer values. However, current quantization methods are often complex and sensitive, requiring extensive task-specific hyperparameters, where even a single misconfiguration can impair model performance, limiting generality across different models and tasks. In this paper, we propose Quantization without Tears (QwT), a method that simultaneously achieves quantization speed, accuracy, simplicity, and generality. The key insight of QwT is to incorporate a lightweight additional structure into the quantized network to mitigate information loss during quantization. This structure consists solely of a small set of linear layers, keeping the method simple and efficient. More importantly, it provides a closed-form solution, allowing us to improve accuracy effortlessly under 2 minutes. Extensive experiments across various vision, language, and multimodal tasks demonstrate that QwT is both highly effective and versatile. In fact, our approach offers a robust solution for network quantization that combines simplicity, accuracy, and adaptability, which provides new insights for the design of novel quantization paradigms. The code is publicly available at https://github.com/wujx2001/QwT

Yanpeng Sun, Jing Hao, Ke Zhu et al.

Training Large Multimodality Models (LMMs) relies on descriptive image caption that connects image and language. Existing methods either distill the caption from the LMM models or construct the captions from the internet images or by human. We propose to leverage off-the-shelf visual specialists, which were trained from annotated images initially not for image captioning, for enhancing the image caption. Our approach, named DCE, explores object low-level and fine-grained attributes (e.g., depth, emotion and fine-grained categories) and object relations (e.g., relative location and human-object-interaction (HOI)), and combine the attributes into the descriptive caption. Experiments demonstrate that such visual specialists are able to improve the performance for visual understanding tasks as well as reasoning that benefits from more accurate visual understanding. We will release the source code and the pipeline so that other visual specialists are easily combined into the pipeline. The complete source code of DCE pipeline and datasets will be available at \url{https://github.com/syp2ysy/DCE}.

Ke Zhu, Yin-Yin He, Jianxin Wu

Most self-supervised learning (SSL) methods often work on curated datasets where the object-centric assumption holds. This assumption breaks down in uncurated images. Existing scene image SSL methods try to find the two views from original scene images that are well matched or dense, which is both complex and computationally heavy. This paper proposes a conceptually different pipeline: first find regions that are coarse objects (with adequate objectness), crop them out as pseudo object-centric images, then any SSL method can be directly applied as in a real object-centric dataset. That is, coarse crops benefits scene images SSL. A novel cropping strategy that produces coarse object box is proposed. The new pipeline and cropping strategy successfully learn quality features from uncurated datasets without ImageNet. Experiments show that our pipeline outperforms existing SSL methods (MoCo-v2, DenseCL and MAE) on classification, detection and segmentation tasks. We further conduct extensively ablations to verify that: 1) the pipeline do not rely on pretrained models; 2) the cropping strategy is better than existing object discovery methods; 3) our method is not sensitive to hyperparameters and data augmentations.

Ke Zhu, Yu Wang, Jiangjiang Liu et al.

This paper is a pioneering work attempting to address abstract visual reasoning (AVR) problems for large vision-language models (VLMs). We make a common LLaVA-NeXT 7B model capable of perceiving and reasoning about specific AVR problems, surpassing both open-sourced (e.g., Qwen-2-VL-72B) and closed-sourced powerful VLMs (e.g., GPT-4o) with significant margin. This is a great breakthrough since almost all previous VLMs fail or show nearly random performance on representative AVR benchmarks. Our key success is our innovative data synthesis and post-training process, aiming to fully relieve the task difficulty and elicit the model to learn, step by step. Our 7B model is also shown to be behave well on AVR without sacrificing common multimodal comprehension abilities. We hope our paper could serve as an early effort in this area and would inspire further research in abstract visual reasoning.

Tian Zhan, Chunfeng Xu, Cheng Zhang et al.

The Perspective-n-Point (PnP) problem has been widely studied in the literature and applied in various vision-based pose estimation scenarios. However, existing methods ignore the anisotropy uncertainty of observations, as demonstrated in several real-world datasets in this paper. This oversight may lead to suboptimal and inaccurate estimation, particularly in the presence of noisy observations. To this end, we propose a generalized maximum likelihood PnP solver, named GMLPnP, that minimizes the determinant criterion by iterating the GLS procedure to estimate the pose and uncertainty simultaneously. Further, the proposed method is decoupled from the camera model. Results of synthetic and real experiments show that our method achieves better accuracy in common pose estimation scenarios, GMLPnP improves rotation/translation accuracy by 4.7%/2.0% on TUM-RGBD and 18.6%/18.4% on KITTI-360 dataset compared to the best baseline. It is more accurate under very noisy observations in a vision-based UAV localization task, outperforming the best baseline by 34.4% in translation estimation accuracy.

Ningyuan Tang, Minghao Fu, Ke Zhu et al.

In finetuning a large pretrained model to downstream tasks, parameter-efficient fine-tuning (PEFT) methods can effectively finetune pretrained models with few trainable parameters, but suffer from high GPU memory consumption and slow training speed. Because learnable parameters from these methods are entangled with the pretrained model, gradients related to the frozen pretrained model's parameters have to be computed and stored during finetuning. We propose Low-rank Attention Side-Tuning (LAST), which disentangles the trainable module from the pretrained model by freezing not only parameters but also outputs of the pretrained network. LAST trains a side-network composed of only low-rank self-attention modules. By viewing the pretrained model as a frozen feature extractor, the side-network takes intermediate output from the pretrained model and focus on learning task-specific knowledge. We also show that LAST can be highly parallel across multiple optimization objectives, making it very efficient in downstream task adaptation, for example, in finding optimal hyperparameters. LAST outperforms previous state-of-the-art methods on VTAB-1K and other visual adaptation tasks with roughly only 30\% of GPU memory footprint and 60\% of training time compared to existing PEFT methods, but achieves significantly higher accuracy.

Jie Shao, Ke Zhu, Hanxiao Zhang et al.

This paper proposes a new pipeline for long-tail (LT) recognition. Instead of re-weighting or re-sampling, we utilize the long-tailed dataset itself to generate a balanced proxy that can be optimized through cross-entropy (CE). Specifically, a randomly initialized diffusion model, trained exclusively on the long-tailed dataset, is employed to synthesize new samples for underrepresented classes. Then, we utilize the inherent information in the original dataset to filter out harmful samples and keep the useful ones. Our strategy, Diffusion model for Long-Tail recognition (DiffuLT), represents a pioneering utilization of generative models in long-tail recognition. DiffuLT achieves state-of-the-art results on CIFAR10-LT, CIFAR100-LT, and ImageNet-LT, surpassing the best competitors with non-trivial margins. Abundant ablations make our pipeline interpretable, too. The whole generation pipeline is done without any external data or pre-trained model weights, making it highly generalizable to real-world long-tailed settings.

Junjie Zhou, Ke Zhu, Jianxin Wu

Knowledge Distillation (KD) is essential in transferring dark knowledge from a large teacher to a small student network, such that the student can be much more efficient than the teacher but with comparable accuracy. Existing KD methods, however, rely on a large teacher trained specifically for the target task, which is both very inflexible and inefficient. In this paper, we argue that a SSL-pretrained model can effectively act as the teacher and its dark knowledge can be captured by the coordinate system or linear subspace where the features lie in. We then need only one forward pass of the teacher, and then tailor the coordinate system (TCS) for the student network. Our TCS method is teacher-free and applies to diverse architectures, works well for KD and practical few-shot learning, and allows cross-architecture distillation with large capacity gap. Experiments show that TCS achieves significantly higher accuracy than state-of-the-art KD methods, while only requiring roughly half of their training time and GPU memory costs.

Ke Zhu, Yu Wang, Yanpeng Sun et al.

Multimodal RLHF usually happens after supervised finetuning (SFT) stage to continually improve vision-language models' (VLMs) comprehension. Conventional wisdom holds its superiority over continual SFT during this preference alignment stage. In this paper, we observe that the inherent value of multimodal RLHF lies in its negative supervision, the logit of the rejected responses. We thus propose a novel negative supervised finetuning (nSFT) approach that fully excavates these information resided. Our nSFT disentangles this negative supervision in RLHF paradigm, and continually aligns VLMs with a simple SFT loss. This is more memory efficient than multimodal RLHF where 2 (e.g., DPO) or 4 (e.g., PPO) large VLMs are strictly required. The effectiveness of nSFT is rigorously proved by comparing it with various multimodal RLHF approaches, across different dataset sources, base VLMs and evaluation metrics. Besides, fruitful of ablations are provided to support our hypothesis. We hope this paper will stimulate further research to properly align large vision language models.

Ke Zhu, Minghao Fu, Jie Shao et al.

Long-tailed object detection faces great challenges because of its extremely imbalanced class distribution. Recent methods mainly focus on the classification bias and its loss function design, while ignoring the subtle influence of the regression branch. This paper shows that the regression bias exists and does adversely and seriously impact the detection accuracy. While existing methods fail to handle the regression bias, the class-specific regression head for rare classes is hypothesized to be the main cause of it in this paper. As a result, three kinds of viable solutions to cater for the rare categories are proposed, including adding a class-agnostic branch, clustering heads and merging heads. The proposed methods brings in consistent and significant improvements over existing long-tailed detection methods, especially in rare and common classes. The proposed method achieves state-of-the-art performance in the large vocabulary LVIS dataset with different backbones and architectures. It generalizes well to more difficult evaluation metrics, relatively balanced datasets, and the mask branch. This is the first attempt to reveal and explore rectifying of the regression bias in long-tailed object detection.

Shuai Bai, Yuxuan Cai, Ruizhe Chen et al.

We introduce Qwen3-VL, the most capable vision-language model in the Qwen series to date, achieving superior performance across a broad range of multimodal benchmarks. It natively supports interleaved contexts of up to 256K tokens, seamlessly integrating text, images, and video. The model family includes both dense (2B/4B/8B/32B) and mixture-of-experts (30B-A3B/235B-A22B) variants to accommodate diverse latency-quality trade-offs. Qwen3-VL delivers three core pillars: (i) markedly stronger pure-text understanding, surpassing comparable text-only backbones in several cases; (ii) robust long-context comprehension with a native 256K-token window for both text and interleaved multimodal inputs, enabling faithful retention, retrieval, and cross-referencing across long documents and videos; and (iii) advanced multimodal reasoning across single-image, multi-image, and video tasks, demonstrating leading performance on comprehensive evaluations such as MMMU and visual-math benchmarks (e.g., MathVista and MathVision). Architecturally, we introduce three key upgrades: (i) an enhanced interleaved-MRoPE for stronger spatial-temporal modeling across images and video; (ii) DeepStack integration, which effectively leverages multi-level ViT features to tighten vision-language alignment; and (iii) text-based time alignment for video, evolving from T-RoPE to explicit textual timestamp alignment for more precise temporal grounding. Under comparable token budgets and latency constraints, Qwen3-VL achieves superior performance in both dense and Mixture-of-Experts (MoE) architectures. We envision Qwen3-VL serving as a foundational engine for image-grounded reasoning, agentic decision-making, and multimodal code intelligence in real-world workflows.

Jie Shao, Ke Zhu, Minghao Fu et al.

Diffusion models have achieved remarkable progress in class-to-image generation. However, we observe that despite impressive FID scores, state-of-the-art models often generate distorted or low-quality images, especially in certain classes. This gap arises because FID evaluates global distribution alignment, while ignoring the perceptual quality of individual samples. We further examine the role of CFG, a common technique used to enhance generation quality. While effective in improving metrics and suppressing outliers, CFG can introduce distribution shift and visual artifacts due to its misalignment with both training objectives and user expectations. In this work, we propose FaME, a training-free and inference-efficient method for improving perceptual quality. FaME uses an image quality assessment model to identify low-quality generations and stores their sampling trajectories. These failure modes are then used as negative guidance to steer future sampling away from poor-quality regions. Experiments on ImageNet demonstrate that FaME brings consistent improvements in visual quality without compromising FID. FaME also shows the potential to be extended to improve text-to-image generation.

Xiaolin Yan, Yangxing Liu, Jiazhang Zheng et al.

Large language models (LLMs) have recently achieved significant advances in reasoning and demonstrated their advantages in solving challenging problems. Yet, their effectiveness in the semiconductor display industry remains limited due to a lack of domain-specific training and expertise. To bridge this gap, we present X-Intelligence 3.0, the first high-performance reasoning model specifically developed for the semiconductor display industry. This model is designed to deliver expert-level understanding and reasoning for the industry's complex challenges. Leveraging a carefully curated industry knowledge base, the model undergoes supervised fine-tuning and reinforcement learning to enhance its reasoning and comprehension capabilities. To further accelerate development, we implemented an automated evaluation framework that simulates expert-level assessments. We also integrated a domain-specific retrieval-augmented generation (RAG) mechanism, resulting in notable performance gains on benchmark datasets. Despite its relatively compact size of 32 billion parameters, X-Intelligence 3.0 outperforms SOTA DeepSeek-R1-671B across multiple evaluations. This demonstrates its exceptional efficiency and establishes it as a powerful solution to the longstanding reasoning challenges faced by the semiconductor display industry.

Minghao Fu, Ke Zhu, Jianxin Wu

In order to mimic the human few-shot learning (FSL) ability better and to make FSL closer to real-world applications, this paper proposes a practical FSL (pFSL) setting. pFSL is based on unsupervised pretrained models (analogous to human prior knowledge) and recognizes many novel classes simultaneously. Compared to traditional FSL, pFSL is simpler in its formulation, easier to evaluate, more challenging and more practical. To cope with the rarity of training examples, this paper proposes IbM2, an instance-based max-margin method not only for the new pFSL setting, but also works well in traditional FSL scenarios. Based on the Gaussian Annulus Theorem, IbM2 converts random noise applied to the instances into a mechanism to achieve maximum margin in the many-way pFSL (or traditional FSL) recognition task. Experiments with various self-supervised pretraining methods and diverse many- or few-way FSL tasks show that IbM2 almost always leads to improvements compared to its respective baseline methods, and in most cases the improvements are significant. With both the new pFSL setting and novel IbM2 method, this paper shows that practical few-shot learning is both viable and promising.

Ke Zhu, Jianxin Wu

Multi-label image recognition is a challenging computer vision task of practical use. Progresses in this area, however, are often characterized by complicated methods, heavy computations, and lack of intuitive explanations. To effectively capture different spatial regions occupied by objects from different categories, we propose an embarrassingly simple module, named class-specific residual attention (CSRA). CSRA generates class-specific features for every category by proposing a simple spatial attention score, and then combines it with the class-agnostic average pooling feature. CSRA achieves state-of-the-art results on multilabel recognition, and at the same time is much simpler than them. Furthermore, with only 4 lines of code, CSRA also leads to consistent improvement across many diverse pretrained models and datasets without any extra training. CSRA is both easy to implement and light in computations, which also enjoys intuitive explanations and visualizations.

Heyang Gong, Ke Zhu

Path-specific effects in mediation analysis provide a useful tool for fairness analysis, which is mostly based on nested counterfactuals. However, the dictum ``no causation without manipulation'' implies that path-specific effects might be induced by certain interventions. This paper proposes a new path intervention inspired by information accounts of causality, and develops the corresponding intervention diagrams and $π$-formula. Compared with the interventionist approach of Robins et al.(2020) based on nested counterfactuals, our proposed path intervention method explicitly describes the manipulation in structural causal model with a simple information transferring interpretation, and does not require the non-existence of recanting witness to identify path-specific effects. Hence, it could serve useful communications and theoretical focus for mediation analysis.