Searcharxiv⌕ Search

arXiv subjects

Yifan Li

Publications and source records attributed to Yifan Li.

At least 145 records · Page 8Linked to original sources
arXiv2025

Visual Large Language Models for Generalized and Specialized Applications

Visual-language models (VLM) have emerged as a powerful tool for learning a unified embedding space for vision and language. Inspired by large language models, which have demonstrated strong reasoning and multi-task capabilities, visual large language models (VLLMs) are gaining increasing attention for building general-purpose VLMs. Despite the significant progress made in VLLMs, the related literature remains limited, particularly from a comprehensive application perspective, encompassing generalized and specialized applications across vision (image, video, depth), action, and language modalities. In this survey, we focus on the diverse applications of VLLMs, examining their using scenarios, identifying ethics consideration and challenges, and discussing future directions for their development. By synthesizing these contents, we aim to provide a comprehensive guide that will pave the way for future innovations and broader applications of VLLMs. The paper list repository is available: https://github.com/JackYFL/awesome-VLLMs.

cs.CV↗
arXiv2024

Packing edge-colorings of subcubic outerplanar graphs

For a sequence $S = (s_1, s_2, \ldots, s_k)$ of non-decreasing positive integers, an $S$-packing edge-coloring (S-coloring) of a graph $G$ is a partition of $E(G)$ into $E_1, E_2, \ldots, E_k$ such that the distance between each pair of distinct edges $e_1,e_2 \in E_i$, $1 \le i \le k$, is at least $s_i + 1$. In particular, a $(1^{\ell},2^k)$-coloring is a partition of $E(G)$ into $\ell$ matchings and $k$ induced matchings, and it can be viewed as intermediate colorings between proper and strong edge-colorings. Hocquard, Lajou, and Lužar conjectured that every subcubic planar graph has a $(1,2^6)$-coloring and a $(1^2,2^3)$-coloring. In this paper, we confirm the conjecture of Hocquard, Lajou, and Lužar for subcubic outerplanar graphs by showing every subcubic outerplanar graph has a $(1,2^5)$-coloring and a $(1^2,2^3)$-coloring. Our results are best possible since we found subcubic outerplanar graphs with no $(1,2^4)$-coloring and no $(1^2,2^2)$-coloring respectively. Furthermore, we explore the question "What is the largest positive integer $k_1$ and $k_2$ such that every subcubic outerplanar graph is $(1,2^4,k_1)$-colorable and $(1^2,2^2,k_2)$-colorable?". We prove $3 \le k_1 \le 6$ and $3 \le k_2 \le 4$. We also consider the question "What is the largest positive integer $k_1'$ and $k_2'$ such that every $2$-connected subcubic outerplanar graph is $(1,2^3,k_1')$-colorable and $(1^2,2^2,k_2')$-colorable?". We prove $k_1' = 2$ and $3 \le k_2' \le 11$.

math.CO↗
arXiv2024

Tree-of-Code: A Hybrid Approach for Robust Complex Task Planning and Execution

The exceptional capabilities of large language models (LLMs) have substantially accelerated the rapid rise and widespread adoption of agents. Recent studies have demonstrated that generating Python code to consolidate LLM-based agents' actions into a unified action space (CodeAct) is a promising approach for developing real-world LLM agents. However, this step-by-step code generation approach often lacks consistency and robustness, leading to instability in agent applications, particularly for complex reasoning and out-of-domain tasks. In this paper, we propose a novel approach called Tree-of-Code (ToC) to tackle the challenges of complex problem planning and execution with an end-to-end mechanism. By integrating key ideas from both Tree-of-Thought and CodeAct, ToC combines their strengths to enhance solution exploration. In our framework, each final code execution result is treated as a node in the decision tree, with a breadth-first search strategy employed to explore potential solutions. The final outcome is determined through a voting mechanism based on the outputs of the nodes.

cs.SE↗
arXiv2024

Plug-n-play e-knit: prototyping large-area e-textiles using machine-knitted magnetically-repositionable sensor networks

Prototyping electronic textile (e-textile) involves embedding electronic components into fabrics to develop smart clothing with specific functionalities. However, this process is still challenging since the complicated wiring setup is required during experimental phases. This paper presents plug-n-play e-knit, a large-scale, repositionable e-textile for providing trial-and-error prototyping platforms across the textile. Plug-n-play e-knit leverages industrial digital knitting machines loaded with conductive thread to automatically embed a communication and power supply network into garments, in addition to using soft magnet connectors to rearrange electronic components while preserving the stretchability of the garment. These combinations enable users to quickly establish e-textile sensor networks, and moreover test the performance and optimal placement of the electric devices on the textile. We demonstrated that our textiles leveraging custom I2C protocols could achieve the motion-resilient motion-tracking sensor network over a 2700 $cm^2$ garment area.

cs.HC↗
arXiv2024

Repositioning the Subject within Image

Current image manipulation primarily centers on static manipulation, such as replacing specific regions within an image or altering its overall style. In this paper, we introduce an innovative dynamic manipulation task, subject repositioning. This task involves relocating a user-specified subject to a desired position while preserving the image's fidelity. Our research reveals that the fundamental sub-tasks of subject repositioning, which include filling the void left by the repositioned subject, reconstructing obscured portions of the subject and blending the subject to be consistent with surrounding areas, can be effectively reformulated as a unified, prompt-guided inpainting task. Consequently, we can employ a single diffusion generative model to address these sub-tasks using various task prompts learned through our proposed task inversion technique. Additionally, we integrate pre-processing and post-processing techniques to further enhance the quality of subject repositioning. These elements together form our SEgment-gEnerate-and-bLEnd (SEELE) framework. To assess SEELE's effectiveness in subject repositioning, we assemble a real-world subject repositioning dataset called ReS. Results of SEELE on ReS demonstrate its efficacy. Code and ReS dataset are available at https://yikai-wang.github.io/seele/.

cs.CV↗
arXiv2024

Unified Lexical Representation for Interpretable Visual-Language Alignment

Visual-Language Alignment (VLA) has gained a lot of attention since CLIP's groundbreaking work. Although CLIP performs well, the typical direct latent feature alignment lacks clarity in its representation and similarity scores. On the other hand, lexical representation, a vector whose element represents the similarity between the sample and a word from the vocabulary, is a natural sparse representation and interpretable, providing exact matches for individual words. However, lexical representations are difficult to learn due to no ground-truth supervision and false-discovery issues, and thus requires complex design to train effectively. In this paper, we introduce LexVLA, a more interpretable VLA framework by learning a unified lexical representation for both modalities without complex design. We use DINOv2 as our visual model for its local-inclined features and Llama 2, a generative language model, to leverage its in-context lexical prediction ability. To avoid the false discovery, we propose an overuse penalty to refrain the lexical representation from falsely frequently activating meaningless words. We demonstrate that these two pre-trained uni-modal models can be well-aligned by fine-tuning on the modest multi-modal dataset and avoid intricate training configurations. On cross-modal retrieval benchmarks, LexVLA, trained on the CC-12M multi-modal dataset, outperforms baselines fine-tuned on larger datasets (e.g., YFCC15M) and those trained from scratch on even bigger datasets (e.g., 1.1B data, including CC-12M). We conduct extensive experiments to analyze LexVLA. Codes are available at https://github.com/Clementine24/LexVLA.

cs.CV↗
arXiv2024

Multi-modal Iterative and Deep Fusion Frameworks for Enhanced Passive DOA Sensing via a Green Massive H2AD MIMO Receiver

Most existing DOA estimation methods assume ideal source incident angles with minimal noise. Moreover, directly using pre-estimated angles to calculate weighted coefficients can lead to performance loss. Thus, a green multi-modal (MM) fusion DOA framework is proposed to realize a more practical, low-cost and high time-efficiency DOA estimation for a H$^2$AD array. Firstly, two more efficient clustering methods, global maximum cos\_similarity clustering (GMaxCS) and global minimum distance clustering (GMinD), are presented to infer more precise true solutions from the candidate solution sets. Based on this, an iteration weighted fusion (IWF)-based method is introduced to iteratively update weighted fusion coefficients and the clustering center of the true solution classes by using the estimated values. Particularly, the coarse DOA calculated by fully digital (FD) subarray, serves as the initial cluster center. The above process yields two methods called MM-IWF-GMaxCS and MM-IWF-GMinD. To further provide a higher-accuracy DOA estimation, a fusion network (fusionNet) is proposed to aggregate the inferred two-part true angles and thus generates two effective approaches called MM-fusionNet-GMaxCS and MM-fusionNet-GMinD. The simulation outcomes show the proposed four approaches can achieve the ideal DOA performance and the CRLB. Meanwhile, proposed MM-fusionNet-GMaxCS and MM-fusionNet-GMinD exhibit superior DOA performance compared to MM-IWF-GMaxCS and MM-IWF-GMinD, especially in extremely-low SNR range.

cs.AI↗
arXiv2024

SMoA: Improving Multi-agent Large Language Models with Sparse Mixture-of-Agents

While multi-agent systems have been shown to significantly enhance the performance of Large Language Models (LLMs) across various tasks and applications, the dense interaction between scaling agents potentially hampers their efficiency and diversity. To address these challenges, we draw inspiration from the sparse mixture-of-agents (SMoE) and propose a sparse mixture-of-agents (SMoA) framework to improve the efficiency and diversity of multi-agent LLMs. Unlike completely connected structures, SMoA introduces novel Response Selection and Early Stopping mechanisms to sparsify information flows among individual LLM agents, striking a balance between performance and efficiency. Additionally, inspired by the expert diversity principle in SMoE frameworks for workload balance between experts, we assign distinct role descriptions to each LLM agent, fostering diverse and divergent thinking. Extensive experiments on reasoning, alignment, and fairness benchmarks demonstrate that SMoA achieves performance comparable to traditional mixture-of-agents approaches but with significantly lower computational costs. Further analysis reveals that SMoA is more stable, has a greater capacity to scale, and offers considerable potential through hyper-parameter optimization. Code and data will be available at: https://github.com/David-Li0406/SMoA.

cs.AI↗
arXiv2024

Lightweight equivariant model for efficient machine learning interatomic potentials

In modern computational materials science, deep learning has shown the capability to predict interatomic potentials, thereby supporting and accelerating conventional simulations. However, existing models typically sacrifice either accuracy or efficiency. Moreover, lightweight models are highly demanded for offering simulating systems on a considerably larger scale at reduced computational costs. Here, we introduce a lightweight equivariant interaction graph neural network (LEIGNN) that can enable accurate and efficient interatomic potential and force predictions for molecules and crystals. Rather than relying on higher-order representations, LEIGNN employs a scalar-vector dual representation to encode equivariant features. By learning geometric symmetry information, our model remains lightweight while ensuring prediction accuracy and robustness through the equivariance. Our results show that LEIGNN consistently outperforms the prediction performance of the representative baselines and achieves significant efficiency across diverse datasets, which include catalysts, molecules, and organic isomers. Furthermore, we conduct molecular dynamics (MD) simulations using the LEIGNN force field across solid, liquid, and gas systems. It is found that LEIGNN can achieve the accuracy of \textit{ab initio} MD across all examined systems.

cs.CE↗
arXiv2024

Scalable Crystal Structure Relaxation Using an Iteration-Free Deep Generative Model with Uncertainty Quantification

In computational molecular and materials science, determining equilibrium structures is the crucial first step for accurate subsequent property calculations. However, the recent discovery of millions of new crystals and complex twisted structures has challenged traditional computational methods, both ab initio and machine-learning-based, due to their computationally intensive iterative processes. To address these scalability issues, here we introduce DeepRelax, a deep generative model capable of performing geometric crystal structure relaxation rapidly and without iterations. DeepRelax learns the equilibrium structural distribution, enabling it to predict relaxed structures directly from their unrelaxed ones. The ability to perform structural relaxation at the millisecond level per structure, combined with the scalability of parallel processing, makes DeepRelax particularly useful for large-scale virtual screening. We demonstrate DeepRelax's reliability and robustness by applying it to five diverse databases, including oxides, Materials Project, two-dimensional materials, van der Waals crystals, and crystals with point defects. DeepRelax consistently shows high accuracy and efficiency, validated by density functional theory calculations. Finally, we enhance its trustworthiness by integrating uncertainty quantification. This work significantly accelerates computational workflows, offering a robust and trustworthy machine-learning method for material discovery and advancing the application of AI for science. Code for DeepRelax is available at https://github.com/Shen-Group/DeepRelax.

cond-mat.mtrl-sci↗
arXiv2024

DPA-2: a large atomic model as a multi-task learner

The rapid advancements in artificial intelligence (AI) are catalyzing transformative changes in atomic modeling, simulation, and design. AI-driven potential energy models have demonstrated the capability to conduct large-scale, long-duration simulations with the accuracy of ab initio electronic structure methods. However, the model generation process remains a bottleneck for large-scale applications. We propose a shift towards a model-centric ecosystem, wherein a large atomic model (LAM), pre-trained across multiple disciplines, can be efficiently fine-tuned and distilled for various downstream tasks, thereby establishing a new framework for molecular modeling. In this study, we introduce the DPA-2 architecture as a prototype for LAMs. Pre-trained on a diverse array of chemical and materials systems using a multi-task approach, DPA-2 demonstrates superior generalization capabilities across multiple downstream tasks compared to the traditional single-task pre-training and fine-tuning methodologies. Our approach sets the stage for the development and broad application of LAMs in molecular and materials simulation research.

physics.chem-ph↗
arXiv2024

Oracle Bone Script Similiar Character Screening Approach Based on Simsiam Contrastive Learning and Supervised Learning

This project proposes a new method that uses fuzzy comprehensive evaluation method to integrate ResNet-50 self-supervised and RepVGG supervised learning. The source image dataset HWOBC oracle is taken as input, the target image is selected, and finally the most similar image is output in turn without any manual intervention. The same feature encoding method is not used for images of different modalities. Before the model training, the image data is preprocessed, and the image is enhanced by random rotation processing, self-square graph equalization theory algorithm, and gamma transform, which effectively enhances the key feature learning. Finally, the fuzzy comprehensive evaluation method is used to combine the results of supervised training and unsupervised training, which can better solve the "most similar" problem that is difficult to quantify. At present, there are many unknown oracle-bone inscriptions waiting for us to crack. Contacting with the glyphs can provide new ideas for cracking.

cs.CV↗
arXiv2024

Facial Affective Behavior Analysis with Instruction Tuning

Facial affective behavior analysis (FABA) is crucial for understanding human mental states from images. However, traditional approaches primarily deploy models to discriminate among discrete emotion categories, and lack the fine granularity and reasoning capability for complex facial behaviors. The advent of Multi-modal Large Language Models (MLLMs) has been proven successful in general visual understanding tasks. However, directly harnessing MLLMs for FABA is challenging due to the scarcity of datasets and benchmarks, neglecting facial prior knowledge, and low training efficiency. To address these challenges, we introduce (i) an instruction-following dataset for two FABA tasks, e.g., emotion and action unit recognition, (ii) a benchmark FABA-Bench with a new metric considering both recognition and generation ability, and (iii) a new MLLM "EmoLA" as a strong baseline to the community. Our initiative on the dataset and benchmarks reveal the nature and rationale of facial affective behaviors, i.e., fine-grained facial movement, interpretability, and reasoning. Moreover, to build an effective and efficient FABA MLLM, we introduce a facial prior expert module with face structure knowledge and a low-rank adaptation module into pre-trained MLLM. We conduct extensive experiments on FABA-Bench and four commonly-used FABA datasets. The results demonstrate that the proposed facial prior expert can boost the performance and EmoLA achieves the best results on our FABA-Bench. On commonly-used FABA datasets, EmoLA is competitive rivaling task-specific state-of-the-art models.

cs.CV↗
arXiv2024

High-Performance Sorting-Based k-mer Counting in Distributed Memory with Flexible Hybrid Parallelism

In generating large quantities of DNA data, high-throughput sequencing technologies require advanced bioinformatics infrastructures for efficient data analysis. k-mer counting, the process of quantifying the frequency of fixed-length k DNA subsequences, is a fundamental step in various bioinformatics pipelines, including genome assembly and protein prediction. Due to the growing volume of data, the scaling of the counting process is critical. In the literature, distributed memory software uses hash tables, which exhibit poor cache friendliness and consume excessive memory. They often also lack support for flexible parallelism, which makes integration into existing bioinformatics pipelines difficult. In this work, we propose HySortK, a highly efficient sorting-based distributed memory k-mer counter. HySortK reduces the communication volume through a carefully designed communication scheme and domain-specific optimization strategies. Furthermore, we introduce an abstract task layer for flexible hybrid parallelism to address load imbalances in different scenarios. HySortK achieves a 2-10x speedup compared to the GPU baseline on 4 and 8 nodes. Compared to state-of-the-art CPU software, HySortK achieves up to 2x speedup while reducing peak memory usage by 30% on 16 nodes. Finally, we integrated HySortK into an existing genome assembly pipeline and achieved up to 1.8x speedup, proving its flexibility and practicality in real-world scenarios.

cs.DC↗
arXiv2024

"Glue pizza and eat rocks" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Models

Retrieval-Augmented Generative (RAG) models enhance Large Language Models (LLMs) by integrating external knowledge bases, improving their performance in applications like fact-checking and information searching. In this paper, we demonstrate a security threat where adversaries can exploit the openness of these knowledge bases by injecting deceptive content into the retrieval database, intentionally changing the model's behavior. This threat is critical as it mirrors real-world usage scenarios where RAG systems interact with publicly accessible knowledge bases, such as web scrapings and user-contributed data pools. To be more realistic, we target a realistic setting where the adversary has no knowledge of users' queries, knowledge base data, and the LLM parameters. We demonstrate that it is possible to exploit the model successfully through crafted content uploads with access to the retriever. Our findings emphasize an urgent need for security measures in the design and deployment of RAG systems to prevent potential manipulation and ensure the integrity of machine-generated content.

cs.CR↗
arXiv2024

KnobTree: Intelligent Database Parameter Configuration via Explainable Reinforcement Learning

Databases are fundamental to contemporary information systems, yet traditional rule-based configuration methods struggle to manage the complexity of real-world applications with hundreds of tunable parameters. Deep reinforcement learning (DRL), which combines perception and decision-making, presents a potential solution for intelligent database configuration tuning. However, due to black-box property of RL-based method, the generated database tuning strategies still face the urgent problem of lack explainability. Besides, the redundant parameters in large scale database always make the strategy learning become unstable. This paper proposes KnobTree, an interpertable framework designed for the optimization of database parameter configuration. In this framework, an interpertable database tuning algorithm based on RL-based differentatial tree is proposed, which building a transparent tree-based model to generate explainable database tuning strategies. To address the problem of large-scale parameters, We also introduce a explainable method for parameter importance assessment, by utilizing Shapley Values to identify parameters that have significant impacts on database performance. Experiments conducted on MySQL and Gbase8s databases have verified exceptional transparency and interpretability of the KnobTree model. The good property makes generated strategies can offer practical guidance to algorithm designers and database administrators. Moreover, our approach also slightly outperforms the existing RL-based tuning algorithms in aspects such as throughput, latency, and processing time.

cs.AI↗
arXiv2024

Towards Event-oriented Long Video Understanding

With the rapid development of video Multimodal Large Language Models (MLLMs), numerous benchmarks have been proposed to assess their video understanding capability. However, due to the lack of rich events in the videos, these datasets may suffer from the short-cut bias that the answers can be deduced from a few frames, without the need to watch the entire video. To address this issue, we introduce Event-Bench, an event-oriented long video understanding benchmark built on existing datasets and human annotations. Event-Bench includes six event-related tasks and 2,190 test instances to comprehensively evaluate video event understanding ability. Additionally, we propose Video Instruction Merging~(VIM), a cost-effective method that enhances video MLLMs using merged, event-intensive video instructions, addressing the scarcity of human-annotated, event-intensive data. Extensive experiments show that the best-performing model, GPT-4o, achieves an overall accuracy of 53.33, significantly outperforming the best open-source model by 41.42%. Leveraging an effective instruction synthesis method and an adaptive model architecture, VIM surpasses both state-of-the-art open-source models and GPT-4V on the Event-Bench. All code, data, and models are publicly available at https://github.com/RUCAIBox/Event-Bench.

cs.CV↗