arXiv subjects

Dong Li

Publications and source records attributed to Dong Li.

At least 235 records · Page 13Linked to original sources

arXiv2025

Absence of diode effect in chiral type-I superconductor NbGe2

Symmetry elegantly governs the fundamental properties and derived functionalities of condensed matter. For instance, realizing the superconducting diode effect (SDE) demands breaking space-inversion and time-reversal symmetries simultaneously. Although the SDE is widely observed in various platforms, its underlying mechanism remains debated, particularly regarding the role of vortices. Here, we systematically investigate the nonreciprocal transport in the chiral type-I superconductor NbGe2. Moreover, we induce type-II superconductivity with elevated superconducting critical temperature on the artificial surface by focused ion beam irradiation, enabling control over vortex dynamics in NbGe2 devices. Strikingly, we observe negligible diode efficiency (Q < 2%) at low magnetic fields, which rises significantly to Q ~ 50% at high magnetic fields, coinciding with an abrupt increase in vortex creep rate when the superconductivity of NbGe2 bulk is suppressed. These results unambiguously highlight the critical role of vortex dynamics in the SDE, in addition to the established symmetry rules.

cond-mat.supr-con↗

arXiv2025

MiniMax-01: Scaling Foundation Models with Lightning Attention

We introduce MiniMax-01 series, including MiniMax-Text-01 and MiniMax-VL-01, which are comparable to top-tier models while offering superior capabilities in processing longer contexts. The core lies in lightning attention and its efficient scaling. To maximize computational capacity, we integrate it with Mixture of Experts (MoE), creating a model with 32 experts and 456 billion total parameters, of which 45.9 billion are activated for each token. We develop an optimized parallel strategy and highly efficient computation-communication overlap techniques for MoE and lightning attention. This approach enables us to conduct efficient training and inference on models with hundreds of billions of parameters across contexts spanning millions of tokens. The context window of MiniMax-Text-01 can reach up to 1 million tokens during training and extrapolate to 4 million tokens during inference at an affordable cost. Our vision-language model, MiniMax-VL-01 is built through continued training with 512 billion vision-language tokens. Experiments on both standard and in-house benchmarks show that our models match the performance of state-of-the-art models like GPT-4o and Claude-3.5-Sonnet while offering 20-32 times longer context window. We publicly release MiniMax-01 at https://github.com/MiniMax-AI.

cs.CL↗

arXiv2025

Edit as You See: Image-guided Video Editing via Masked Motion Modeling

Recent advancements in diffusion models have significantly facilitated text-guided video editing. However, there is a relative scarcity of research on image-guided video editing, a method that empowers users to edit videos by merely indicating a target object in the initial frame and providing an RGB image as reference, without relying on the text prompts. In this paper, we propose a novel Image-guided Video Editing Diffusion model, termed IVEDiff for the image-guided video editing. IVEDiff is built on top of image editing models, and is equipped with learnable motion modules to maintain the temporal consistency of edited video. Inspired by self-supervised learning concepts, we introduce a masked motion modeling fine-tuning strategy that empowers the motion module's capabilities for capturing inter-frame motion dynamics, while preserving the capabilities for intra-frame semantic correlations modeling of the base image editing model. Moreover, an optical-flow-guided motion reference network is proposed to ensure the accurate propagation of information between edited video frames, alleviating the misleading effects of invalid information. We also construct a benchmark to facilitate further research. The comprehensive experiments demonstrate that our method is able to generate temporally smooth edited videos while robustly dealing with various editing objects with high quality.

cs.CV↗

arXiv2025

MSWA: Refining Local Attention with Multi-ScaleWindow Attention

Transformer-based LLMs have achieved exceptional performance across a wide range of NLP tasks. However, the standard self-attention mechanism suffers from quadratic time complexity and linearly increased cache size. Sliding window attention (SWA) solves this problem by restricting the attention range to a fixed-size local context window. Nevertheless, SWA employs a uniform window size for each head in each layer, making it inefficient in capturing context of varying scales. To mitigate this limitation, we propose Multi-Scale Window Attention (MSWA) which applies diverse window sizes across heads and layers in the Transformer. It not only allows for different window sizes among heads within the same layer but also progressively increases window size allocation from shallow to deep layers, thus enabling the model to capture contextual information with different lengths and distances. Experimental results on language modeling and common-sense reasoning tasks substantiate that MSWA outperforms traditional local attention in both effectiveness and efficiency.

cs.CL↗

arXiv2024

Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback

Reinforcement learning from human feedback (RLHF) has proven effective in enhancing the instruction-following capabilities of large language models; however, it remains underexplored in the cross-modality domain. As the number of modalities increases, aligning all-modality models with human intentions -- such as instruction following -- becomes a pressing challenge. In this work, we make the first attempt to fine-tune all-modality models (i.e. input and output with any modality, also named any-to-any models) using human preference data across all modalities (including text, image, audio, and video), ensuring its behavior aligns with human intentions. This endeavor presents several challenges. First, there is no large-scale all-modality human preference data in existing open-source resources, as most datasets are limited to specific modalities, predominantly text and image. Secondly, the effectiveness of binary preferences in RLHF for post-training alignment in complex all-modality scenarios remains an unexplored area. Finally, there is a lack of a systematic framework to evaluate the capabilities of all-modality models, particularly regarding modality selection and synergy. To address these challenges, we propose the align-anything framework, which includes meticulously annotated 200k all-modality human preference data. Then, we introduce an alignment method that learns from unified language feedback, effectively capturing complex modality-specific human preferences and enhancing the model's instruction-following capabilities. Furthermore, to assess performance improvements in all-modality models after post-training alignment, we construct a challenging all-modality capability evaluation framework -- eval-anything. All data, models, and code frameworks have been open-sourced for the community. For more details, please refer to https://github.com/PKU-Alignment/align-anything.

cs.AI↗

arXiv2024

EGSRAL: An Enhanced 3D Gaussian Splatting based Renderer with Automated Labeling for Large-Scale Driving Scene

3D Gaussian Splatting (3D GS) has gained popularity due to its faster rendering speed and high-quality novel view synthesis. Some researchers have explored using 3D GS for reconstructing driving scenes. However, these methods often rely on various data types, such as depth maps, 3D boxes, and trajectories of moving objects. Additionally, the lack of annotations for synthesized images limits their direct application in downstream tasks. To address these issues, we propose EGSRAL, a 3D GS-based method that relies solely on training images without extra annotations. EGSRAL enhances 3D GS's capability to model both dynamic objects and static backgrounds and introduces a novel adaptor for auto labeling, generating corresponding annotations based on existing annotations. We also propose a grouping strategy for vanilla 3D GS to address perspective issues in rendering large-scale, complex scenes. Our method achieves state-of-the-art performance on multiple datasets without any extra annotation. For example, the PSNR metric reaches 29.04 on the nuScenes dataset. Moreover, our automated labeling can significantly improve the performance of 2D/3D detection tasks. Code is available at https://github.com/jiangxb98/EGSRAL.

cs.CV↗

arXiv2024

Frenzy: A Memory-Aware Serverless LLM Training System for Heterogeneous GPU Clusters

Existing work only effective on a given number of GPUs, often neglecting the complexities involved in manually determining the specific types and quantities of GPUs needed, which can be a significant burden for developers. To address this issue, we propose Frenzy, a memory-aware serverless computing method for heterogeneous GPU clusters. Frenzy allows users to submit models without worrying about underlying hardware resources. First, Frenzy predicts the required number and type of GPUs by estimating the GPU memory usage of the LLM. Then, it employs a low-overhead heterogeneity-aware scheduling method to optimize training efficiency. We validated Frenzy's performance by conducting multi-task LLM training tests on a heterogeneous GPU cluster with three different GPU types. The results show that Frenzy's memory usage prediction accuracy exceeds 92\%, the scheduling overhead is reduced by 10 times, and it reduces the average job completion time by 12\% to 18\% compared to state-of-the-art methods.

cs.DC↗

arXiv2024

FTP: A Fine-grained Token-wise Pruner for Large Language Models via Token Routing

Recently, large language models (LLMs) have demonstrated superior performance across various tasks by adhering to scaling laws, which significantly increase model size. However, the huge computation overhead during inference hinders the deployment in industrial applications. Many works leverage traditional compression approaches to boost model inference, but these always introduce additional training costs to restore the performance and the pruning results typically show noticeable performance drops compared to the original model when aiming for a specific level of acceleration. To address these issues, we propose a fine-grained token-wise pruning approach for the LLMs, which presents a learnable router to adaptively identify the less important tokens and skip them across model blocks to reduce computational cost during inference. To construct the router efficiently, we present a search-based sparsity scheduler for pruning sparsity allocation, a trainable router combined with our proposed four low-dimensional factors as input and three proposed losses. We conduct extensive experiments across different benchmarks on different LLMs to demonstrate the superiority of our method. Our approach achieves state-of-the-art (SOTA) pruning results, surpassing other existing pruning methods. For instance, our method outperforms BlockPruner and ShortGPT by approximately 10 points on both LLaMA2-7B and Qwen1.5-7B in accuracy retention at comparable token sparsity levels.

cs.CL↗

arXiv2024

Fast and Slow Gradient Approximation for Binary Neural Network Optimization

Binary Neural Networks (BNNs) have garnered significant attention due to their immense potential for deployment on edge devices. However, the non-differentiability of the quantization function poses a challenge for the optimization of BNNs, as its derivative cannot be backpropagated. To address this issue, hypernetwork based methods, which utilize neural networks to learn the gradients of non-differentiable quantization functions, have emerged as a promising approach due to their adaptive learning capabilities to reduce estimation errors. However, existing hypernetwork based methods typically rely solely on current gradient information, neglecting the influence of historical gradients. This oversight can lead to accumulated gradient errors when calculating gradient momentum during optimization. To incorporate historical gradient information, we design a Historical Gradient Storage (HGS) module, which models the historical gradient sequence to generate the first-order momentum required for optimization. To further enhance gradient generation in hypernetworks, we propose a Fast and Slow Gradient Generation (FSG) method. Additionally, to produce more precise gradients, we introduce Layer Recognition Embeddings (LRE) into the hypernetwork, facilitating the generation of layer-specific fine gradients. Extensive comparative experiments on the CIFAR-10 and CIFAR-100 datasets demonstrate that our method achieves faster convergence and lower loss values, outperforming existing baselines.Code is available at http://github.com/two-tiger/FSG .

cs.LG↗

arXiv2024

Fast Occupancy Network

Occupancy Network has recently attracted much attention in autonomous driving. Instead of monocular 3D detection and recent bird's eye view(BEV) models predicting 3D bounding box of obstacles, Occupancy Network predicts the category of voxel in specified 3D space around the ego vehicle via transforming 3D detection task into 3D voxel segmentation task, which has much superiority in tackling category outlier obstacles and providing fine-grained 3D representation. However, existing methods usually require huge computation resources than previous methods, which hinder the Occupancy Network solution applying in intelligent driving systems. To address this problem, we make an analysis of the bottleneck of Occupancy Network inference cost, and present a simple and fast Occupancy Network model, which adopts a deformable 2D convolutional layer to lift BEV feature to 3D voxel feature and presents an efficient voxel feature pyramid network (FPN) module to improve performance with few computational cost. Further, we present a cost-free 2D segmentation branch in perspective view after feature extractors for Occupancy Network during inference phase to improve accuracy. Experimental results demonstrate that our method consistently outperforms existing methods in both accuracy and inference speed, which surpasses recent state-of-the-art (SOTA) OCCNet by 1.7% with ResNet50 backbone with about 3X inference speedup. Furthermore, our method can be easily applied to existing BEV models to transform them into Occupancy Network models.

cs.CV↗

arXiv2024

Orbital anomalous Hall effect in the few-layer Weyl semimetal TaIrTe4

We report on the observation of the linear anomalous Hall effect (AHE) in the nonmagnetic Weyl semimetal TaIrTe4. This is achieved by applying a direct current Idc and an alternating current Iac (Iac<<Idc) in TaIrTe4, where the former induces time-reversal symmetry breaking and the latter probes the triggered AHE. The anomalous Hall resistance VacH/Iac shows a linear dependence on Idc and changes sign with the polarity of Idc. In temperature-dependent measurements, VacH/Iac also experiences a sign reversal at 100 K, consistent with the temperature-dependent nonlinear Hall effect (NLHE). Furthermore, in measurements involving only dc transport, the dc Hall voltage exhibits a quadratic relationship with Idc. When the Idc direction is reversed, the Hall resistance changes sign, demonstrating a colossal nonreciprocal Hall effect (NRHE). Our theoretical calculations suggest that the observed linear AHE, NLHE, and NRHE all dominantly originate from the current-induced orbital magnetization compared to the minor spin contribution. This work provides deep insights into the orbital magnetoelectric effect and nonlinear Hall response, promising precise electric control of out-of-plane polarized orbit flow.

cond-mat.mes-hall↗

arXiv2024

Room-temperature van der Waals magnetoresistive memories with data writing by orbital current in the Weyl semimetal TaIrTe4

Current-induced out of plane magnetization has been utilized for field-free switching of ferromagnets with perpendicular magnetic anisotropy. Identifying systems capable of energy-efficiently converting charge currents into out of plane orbit- or spin-polarized currents is crucial for advancing magnetic memory technologies. Here we introduce the Berry curvature dipole as a key evaluation factor, directly measurable through nonlinear Hall effects. In the Weyl semimetal TaIrTe4 used in our experiments, applying a current parallel to the Berry curvature dipole results in out of plane orbital magnetization, which governs the field-free perpendicular magnetization switching in TaIrTe4/Fe3GaTe2 heterostructures. Notably, all-electric control of van der Waals magnetoresistive memory at room temperature has been achieved with a low critical current density 2x10^6A/cm2 for data writing. Our findings reveal the connection between nonlinear Hall effects and field-free magnetization switching, highlighting the potential of the Berry curvature dipole in advancing orbitronics.

cond-mat.mes-hall↗

arXiv2024

Facilitating field-free perpendicular magnetization switching with a Berry curvature dipole in a Weyl semimetal

We report the synergy between orbital and spin-orbit torques in WTe2/Fe3GeTe2 heterostructures characterized by a Berry curvature dipole. By applying a current along the a axis in WTe2, we detect an out-of-plane magnetization in the system, which we attribute to nonequilibrium orbital magnetization linked to the Berry curvature dipole based on first-principles calculations, manifesting as the orbital Edelstein effect. This effect generates orbital torques that enable field-free perpendicular magnetization switching. Furthermore, by applying a relatively small current along the a axis and a pulsed current along the b axis in WTe2, we demonstrate controllable field-free magnetization switching of the adjacent Fe3GeTe2 layer, independently manipulating the orbital and spin-orbit torques. Our findings not only enhance the understanding of the collaborative dynamics between these torques but also suggest potential applications in magnetoresistive random-access memory.

cond-mat.mes-hall↗

arXiv2024

Less is More: Efficient Model Merging with Binary Task Switch

As an effective approach to equip models with multi-task capabilities without additional training, model merging has garnered significant attention. However, existing methods face challenges of redundant parameter conflicts and the excessive storage burden of parameters. In this work, through controlled experiments, we reveal that for task vectors, only those parameters with magnitudes above a certain threshold contribute positively to the task, exhibiting a pulse-like characteristic. We then attempt leveraging this characteristic to binarize the task vectors and reduce storage overhead. Further controlled experiments show that the binarized task vectors incur almost no decrease in fine-tuning and merging performance, and even exhibit stronger performance improvements as the proportion of redundant parameters increases. Based on these insights, we propose Task Switch (T-Switch), which decomposes task vectors into three components: 1) an activation switch instantiated by a binarized mask vector, 2) a polarity switch instantiated by a binarized sign vector, and 3) a scaling knob instantiated by a scalar coefficient. By storing task vectors in a binarized form, T-Switch alleviates parameter conflicts while ensuring efficient task parameter storage. Furthermore, to enable automated switch combination in T-Switch, we further introduce Auto-Switch, which enables training-free switch combination via retrieval from a small query set. Experiments indicate that our methods achieve significant performance improvements over existing baselines, requiring only 1-3% of the storage space of full-precision parameters.

cs.LG↗

arXiv2024

Evolution of Thought: Diverse and High-Quality Reasoning via Multi-Objective Optimization

As multi-modal large language models (MLLMs) are increasingly applied to complex reasoning tasks, the diversity and quality of reasoning paths become crucial factors affecting their performance. Although current methods aim to enhance reasoning quality through path expansion, they often neglect the diversity of reasoning paths and effective information sharing, leading to local optima and inefficiency. To address these challenges, we propose Evolution of Thought (EoT), a multi-objective framework designed to improve reasoning by fostering both high-quality and diverse reasoning paths. Specifically, we introduce the Non-dominated Sorting Genetic Algorithm II for multi-objective optimization, utilizing crossover and mutation operators to promote greater diversity in reasoning solutions. Additionally, we propose a Condensation-Aggregation mechanism to cluster and eliminate redundant paths, facilitate improved information sharing among parent nodes, and ultimately enhance both the efficiency and quality of the reasoning process. Validation experiments on various vision-language and language reasoning tasks demonstrate that EoT achieves superior reasoning performance and efficiency compared to other competitive baselines. Our study provides a novel perspective on the design of heuristic reasoning frameworks for MLLMs.

cs.NE↗

arXiv2024

MLDGG: Meta-Learning for Domain Generalization on Graphs

Domain generalization on graphs aims to develop models with robust generalization capabilities, ensuring effective performance on the testing set despite disparities between testing and training distributions. However, existing methods often rely on static encoders directly applied to the target domain, constraining its flexible adaptability. In contrast to conventional methodologies, which concentrate on developing specific generalized models, our framework, MLDGG, endeavors to achieve adaptable generalization across diverse domains by integrating cross-multi-domain meta-learning with structure learning and semantic identification. Initially, it introduces a generalized structure learner to mitigate the adverse effects of task-unrelated edges, enhancing the comprehensiveness of representations learned by Graph Neural Networks (GNNs) while capturing shared structural information across domains. Subsequently, a representation learner is designed to disentangle domain-invariant semantic and domain-specific variation information in node embedding by leveraging causal reasoning for semantic identification, further enhancing generalization. In the context of meta-learning, meta-parameters for both learners are optimized to facilitate knowledge transfer and enable effective adaptation to graphs through fine-tuning within the target domains, where target graphs are inaccessible during training. Our empirical results demonstrate that MLDGG surpasses baseline methods, showcasing its effectiveness in three different distribution shift settings.

cs.LG↗

arXiv2024

An Efficient Memory Module for Graph Few-Shot Class-Incremental Learning

Incremental graph learning has gained significant attention for its ability to address the catastrophic forgetting problem in graph representation learning. However, traditional methods often rely on a large number of labels for node classification, which is impractical in real-world applications. This makes few-shot incremental learning on graphs a pressing need. Current methods typically require extensive training samples from meta-learning to build memory and perform intensive fine-tuning of GNN parameters, leading to high memory consumption and potential loss of previously learned knowledge. To tackle these challenges, we introduce Mecoin, an efficient method for building and maintaining memory. Mecoin employs Structured Memory Units to cache prototypes of learned categories, as well as Memory Construction Modules to update these prototypes for new categories through interactions between the nodes and the cached prototypes. Additionally, we have designed a Memory Representation Adaptation Module to store probabilities associated with each class prototype, reducing the need for parameter fine-tuning and lowering the forgetting rate. When a sample matches its corresponding class prototype, the relevant probabilities are retrieved from the MRaM. Knowledge is then distilled back into the GNN through a Graph Knowledge Distillation Module, preserving the model's memory. We analyze the effectiveness of Mecoin in terms of generalization error and explore the impact of different distillation strategies on model performance through experiments and VC-dimension analysis. Compared to other related works, Mecoin shows superior performance in accuracy and forgetting rate. Our code is publicly available on the https://github.com/Arvin0313/Mecoin-GFSCIL.git .

cs.LG↗

arXiv2024

FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making

Large language models (LLMs) have demonstrated notable potential in conducting complex tasks and are increasingly utilized in various financial applications. However, high-quality sequential financial investment decision-making remains challenging. These tasks require multiple interactions with a volatile environment for every decision, demanding sufficient intelligence to maximize returns and manage risks. Although LLMs have been used to develop agent systems that surpass human teams and yield impressive investment returns, opportunities to enhance multi-sourced information synthesis and optimize decision-making outcomes through timely experience refinement remain unexplored. Here, we introduce the FinCon, an LLM-based multi-agent framework with CONceptual verbal reinforcement tailored for diverse FINancial tasks. Inspired by effective real-world investment firm organizational structures, FinCon utilizes a manager-analyst communication hierarchy. This structure allows for synchronized cross-functional agent collaboration towards unified goals through natural language interactions and equips each agent with greater memory capacity than humans. Additionally, a risk-control component in FinCon enhances decision quality by episodically initiating a self-critiquing mechanism to update systematic investment beliefs. The conceptualized beliefs serve as verbal reinforcement for the future agent's behavior and can be selectively propagated to the appropriate node that requires knowledge updates. This feature significantly improves performance while reducing unnecessary peer-to-peer communication costs. Moreover, FinCon demonstrates strong generalization capabilities in various financial tasks, including single stock trading and portfolio management.

cs.CL↗