arXiv subjects

Zhenyu Li

Publications and source records attributed to Zhenyu Li.

At least 73 records · Page 4Linked to original sources

arXiv2025

VEDA: Efficient LLM Generation Through Voting-based KV Cache Eviction and Dataflow-flexible Accelerator

Large Language Models (LLMs) excel in natural language processing tasks but pose significant computational and memory challenges for edge deployment due to their intensive resource demands. This work addresses the efficiency of LLM inference by algorithm-hardware-dataflow tri-optimizations. We propose a novel voting-based KV cache eviction algorithm, balancing hardware efficiency and algorithm accuracy by adaptively identifying unimportant kv vectors. From a dataflow perspective, we introduce a flexible-product dataflow and a runtime reconfigurable PE array for matrix-vector multiplication. The proposed approach effectively handles the diverse dimensional requirements and solves the challenges of incrementally varying sequence lengths. Additionally, an element-serial scheduling scheme is proposed for nonlinear operations, such as softmax and layer normalization (layernorm). Results demonstrate a substantial reduction in latency, accompanied by a significant decrease in hardware complexity, from O(N) to O(1). The proposed solution is realized in a custom-designed accelerator, VEDA, which outperforms existing hardware platforms. This research represents a significant advancement in LLM inference on resource-constrained edge devices, facilitating real-time processing, enhancing data privacy, and enabling model customization.

cs.AR↗

arXiv2025

Place Recognition Meet Multiple Modalitie: A Comprehensive Review, Current Challenges and Future Directions

Place recognition is a cornerstone of vehicle navigation and mapping, which is pivotal in enabling systems to determine whether a location has been previously visited. This capability is critical for tasks such as loop closure in Simultaneous Localization and Mapping (SLAM) and long-term navigation under varying environmental conditions. In this survey, we comprehensively review recent advancements in place recognition, emphasizing three representative methodological paradigms: Convolutional Neural Network (CNN)-based approaches, Transformer-based frameworks, and cross-modal strategies. We begin by elucidating the significance of place recognition within the broader context of autonomous systems. Subsequently, we trace the evolution of CNN-based methods, highlighting their contributions to robust visual descriptor learning and scalability in large-scale environments. We then examine the emerging class of Transformer-based models, which leverage self-attention mechanisms to capture global dependencies and offer improved generalization across diverse scenes. Furthermore, we discuss cross-modal approaches that integrate heterogeneous data sources such as Lidar, vision, and text description, thereby enhancing resilience to viewpoint, illumination, and seasonal variations. We also summarize standard datasets and evaluation metrics widely adopted in the literature. Finally, we identify current research challenges and outline prospective directions, including domain adaptation, real-time performance, and lifelong learning, to inspire future advancements in this domain. The unified framework of leading-edge place recognition methods, i.e., code library, and the results of their experimental evaluations are available at https://github.com/CV4RA/SOTA-Place-Recognitioner.

cs.CV↗

arXiv2025

RIS-Assisted Survivable Fronthaul Design in Cell-Free Massive MIMO System

This paper investigates the application of reconfigurable intelligent surfaces (RISs) to improve fronthaul link survivability in cell-free massive MIMO (CF mMIMO) systems. To enhance the fronthaul survivability, two complementary mechanisms are considered. Firstly, RIS is set to provide reliable line-of-sight (LOS) connectivity and enhance the mmWave backup link. Secondly, a resource-sharing scheme that leverages redundant cable capacity through neighboring master access points (APs) to guarantee availability is considered. We formulate the redundant capacity minimization problem as a RIS-assisted multi-user MIMO rate control optimization problem, developing a novel solution that combines a modified weighted minimum mean square error (WMMSE) algorithm for precoding design with Riemannian gradient descent for RIS phase shift optimization. Our numerical evaluations show that RIS reduces the required redundant capacity by 65.6% compared to the no RIS case to reach a 99% survivability. The results show that the most substantial gains of RIS occur during complete outages of the direct disconnected master AP-CPU channel. These results demonstrate RIS's potential to significantly enhance fronthaul reliability while minimizing infrastructure costs in next-generation wireless networks.

cs.IT↗

arXiv2025

Local rainbow colorings of hypergraphs

In this paper, we generalize the concepts related to rainbow coloring to hypergraphs. Specifically, an $(n,r,H)$-local coloring is defined as a collection of $n$ edge-colorings, $f_v: E(K^{(r)}_n) \rightarrow [k]$ for each vertex $v$ in the complete $r$-uniform hypergraph $K^{(r)}_n$, with the property that for any copy $T$ of $H$ in $K^{(r)}_n$, there exists at least one vertex $u$ in $T$ such that $f_u$ provides a rainbow edge-coloring of $T$ (i.e., no two edges in $T$ share the same color under $f_u$). The minimum number of colors required for this coloring is denoted as the local rainbow coloring number $C_r(n, H)$. We first establish an upper bound of the local rainbow coloring number for $r$-uniform hypergraphs $H$ consisting of $h$ vertices, that is, $C_r(n, H)= O\left( n^{\frac{h-r}{h}} \cdot h^{2r + \frac{r}{h}} \right)$. Furthermore, we identify a set of $r$-uniform hypergraphs whose local rainbow coloring numbers are bounded by a constant. A notable special case indicates that $C_3(n,H) \leq C(H)$ for some constant $C(H)$ depending only on $H$ if and only if $H$ contains at most 3 edges and does not belong to a specific set of three well-structured hypergraphs, possibly augmented with isolated vertices. We further establish two 3-uniform hypergraphs $H$ of particular interest for which $C_3(n,H) = n^{o(1)}$. Regarding lower bounds, we demonstrate that for every $r$-uniform hypergraph $H$ with sufficiently many edges, there exists a constant $b = b(H) > 0$ such that $C_r(n,H) = Ω(n^b)$. Additionally, we obtain lower bounds for several hypergraphs of specific interest.

math.CO↗

arXiv2025

DoubleDiffusion: Combining Heat Diffusion with Denoising Diffusion for Texture Generation on 3D Meshes

This paper addresses the problem of generating textures for 3D mesh assets. Existing approaches often rely on image diffusion models to generate multi-view image observations, which are then transformed onto the mesh surface to produce a single texture. However, due to the gap between multi-view images and 3D space, such process is susceptible to arange of issues such as geometric inconsistencies, visibility occlusion, and baking artifacts. To overcome this problem, we propose a novel approach that directly generates texture on 3D meshes. Our approach leverages heat dissipation diffusion, which serves as an efficient operator that propagates features on the geometric surface of a mesh, while remaining insensitive to the specific layout of the wireframe. By integrating this technique into a generative diffusion pipeline, we significantly improve the efficiency of texture generation compared to existing texture generation methods. We term our approach DoubleDiffusion, as it combines heat dissipation diffusion with denoising diffusion to enable native generative learning on 3D mesh surfaces.

cs.CV↗

arXiv2025

COMM:Concentrated Margin Maximization for Robust Document-Level Relation Extraction

Document-level relation extraction (DocRE) is the process of identifying and extracting relations between entities that span multiple sentences within a document. Due to its realistic settings, DocRE has garnered increasing research attention in recent years. Previous research has mostly focused on developing sophisticated encoding models to better capture the intricate patterns between entity pairs. While these advancements are undoubtedly crucial, an even more foundational challenge lies in the data itself. The complexity inherent in DocRE makes the labeling process prone to errors, compounded by the extreme sparsity of positive relation samples, which is driven by both the limited availability of positive instances and the broad diversity of positive relation types. These factors can lead to biased optimization processes, further complicating the task of accurate relation extraction. Recognizing these challenges, we have developed a robust framework called \textit{\textbf{COMM}} to better solve DocRE. \textit{\textbf{COMM}} operates by initially employing an instance-aware reasoning method to dynamically capture pertinent information of entity pairs within the document and extract relational features. Following this, \textit{\textbf{COMM}} takes into account the distribution of relations and the difficulty of samples to dynamically adjust the margins between prediction logits and the decision threshold, a process we call Concentrated Margin Maximization. In this way, \textit{\textbf{COMM}} not only enhances the extraction of relevant relational features but also boosts DocRE performance by addressing the specific challenges posed by the data. Extensive experiments and analysis demonstrate the versatility and effectiveness of \textit{\textbf{COMM}}, especially its robustness when trained on low-quality data (achieves \textgreater 10\% performance gains).

cs.CL↗

arXiv2025

TROI: Cross-Subject Pretraining with Sparse Voxel Selection for Enhanced fMRI Visual Decoding

fMRI (functional Magnetic Resonance Imaging) visual decoding involves decoding the original image from brain signals elicited by visual stimuli. This often relies on manually labeled ROIs (Regions of Interest) to select brain voxels. However, these ROIs can contain redundant information and noise, reducing decoding performance. Additionally, the lack of automated ROI labeling methods hinders the practical application of fMRI visual decoding technology, especially for new subjects. This work presents TROI (Trainable Region of Interest), a novel two-stage, data-driven ROI labeling method for cross-subject fMRI decoding tasks, particularly when subject samples are limited. TROI leverages labeled ROIs in the dataset to pretrain an image decoding backbone on a cross-subject dataset, enabling efficient optimization of the input layer for new subjects without retraining the entire model from scratch. In the first stage, we introduce a voxel selection method that combines sparse mask training and low-pass filtering to quickly generate the voxel mask and determine input layer dimensions. In the second stage, we apply a learning rate rewinding strategy to fine-tune the input layer for downstream tasks. Experimental results on the same small sample dataset as the baseline method for brain visual retrieval and reconstruction tasks show that our voxel selection method surpasses the state-of-the-art method MindEye2 with an annotated ROI mask.

cs.CV↗

arXiv2025

Bridging Text and Vision: A Multi-View Text-Vision Registration Approach for Cross-Modal Place Recognition

Mobile robots necessitate advanced natural language understanding capabilities to accurately identify locations and perform tasks such as package delivery. However, traditional visual place recognition (VPR) methods rely solely on single-view visual information and cannot interpret human language descriptions. To overcome this challenge, we bridge text and vision by proposing a multiview (360° views of the surroundings) text-vision registration approach called Text4VPR for place recognition task, which is the first method that exclusively utilizes textual descriptions to match a database of images. Text4VPR employs the frozen T5 language model to extract global textual embeddings. Additionally, it utilizes the Sinkhorn algorithm with temperature coefficient to assign local tokens to their respective clusters, thereby aggregating visual descriptors from images. During the training stage, Text4VPR emphasizes the alignment between individual text-image pairs for precise textual description. In the inference stage, Text4VPR uses the Cascaded Cross-Attention Cosine Alignment (CCCA) to address the internal mismatch between text and image groups. Subsequently, Text4VPR performs precisely place match based on the descriptions of text-image groups. On Street360Loc, the first text to image VPR dataset we created, Text4VPR builds a robust baseline, achieving a leading top-1 accuracy of 57% and a leading top-10 accuracy of 92% within a 5-meter radius on the test set, which indicates that localization from textual descriptions to images is not only feasible but also holds significant potential for further advancement, as shown in Figure 1.

cs.CV↗

arXiv2025

First Principles Reactive Flux Theory for Surface Reactions: Multiple Channels and Recrossing Dynamics

Heterogenous reactions typically consist of multiple elementary steps and their rate coefficients are of fundamental importance in elucidating the mechanisms and micro-kinetics of these processes. Transition-state theory (TST) for calculating surface reaction rate coefficients often relies solely on the harmonic approximation of adsorbent vibrations and neglects recrossing dynamics. Here, we combine, for the first time, an efficient metadynamics enhanced sampling method with a more general reactive flux approach to calculate rate coefficients of surface reactions of any order and/or with multiple reaction coordinates, overcoming these limitations of TST. We apply this approach to a textbook surface reaction, CO oxidation on Pt(111), for which rate constants have been precisely measured, using a full-dimensional neural network potential energy surface constructed from first-principles data. An accurate multi-dimensional free-energy surface is obtained by incorporating three collective variables, yielding rate coefficients for both CO oxidation and the competing CO desorption that are in good agreement with experimental data. Interestingly, our results reveal significant dynamic recrossing in both channels, which however arises from distinct physical mechanisms. This approach represents an accurate and general framework for calculating rate coefficients of elementary surface processes from first-principles, which is vital for developing predictive kinetic models for heterogenous catalysis.

physics.chem-ph↗

arXiv2025

A chip-based optoelectronic-oscillator frequency comb

Microresonator-based Kerr frequency combs ("Kerr microcombs") constitute chip-scale frequency combs of broad spectral bandwidth and repetition rate ranging from gigahertz to terahertz. An appealing application exploiting microcombs' coherence and large repetition rate is microwave and millimeter-wave generation. Latest endeavor applying two-point optical frequency division (OFD) on photonic-chip-based microcombs has created microwaves with exceptionally low phase noise. Nevertheless, microcomb-based OFD still requires extensive active locking, additional lasers, and external RF or microwave sources, as well as sophisticated initiation. Here we demonstrate a simple and entirely passive (no active locking) architecture, which incorporates an optoelectronic oscillator (OEO) and symphonizes a coherent microcomb and a low-noise microwave spontaneously. Our OEO microcomb leverages state-of-the-art integrated chip devices including a high-power DFB laser, a broadband silicon Mach-Zehnder modulator, an ultralow-loss silicon nitride microresonator, and a high-speed photodetector. Each can be manufactured in large volume with low cost and high yield using established CMOS and III-V foundries. Our system synergizes a microcomb of 10.7 GHz repetition rate and an X-band microwave with phase noise of $-$97/$-$126/$-$130 dBc/Hz at 1/10/100 kHz Fourier frequency offset, yet does not demand active locking, additional lasers, and external RF or microwave sources. With potential to be fully integrated, our OEO microcomb can become an invaluable technology and building block for microwave photonics, radio-over-fiber, and optical communication.

physics.optics↗

arXiv2025

MambaPlace:Text-to-Point-Cloud Cross-Modal Place Recognition with Attention Mamba Mechanisms

Vision Language Place Recognition (VLVPR) enhances robot localization performance by incorporating natural language descriptions from images. By utilizing language information, VLVPR directs robot place matching, overcoming the constraint of solely depending on vision. The essence of multimodal fusion lies in mining the complementary information between different modalities. However, general fusion methods rely on traditional neural architectures and are not well equipped to capture the dynamics of cross modal interactions, especially in the presence of complex intra modal and inter modal correlations. To this end, this paper proposes a novel coarse to fine and end to end connected cross modal place recognition framework, called MambaPlace. In the coarse localization stage, the text description and 3D point cloud are encoded by the pretrained T5 and instance encoder, respectively. They are then processed using Text Attention Mamba (TAM) and Point Clouds Mamba (PCM) for data enhancement and alignment. In the subsequent fine localization stage, the features of the text description and 3D point cloud are cross modally fused and further enhanced through cascaded Cross Attention Mamba (CCAM). Finally, we predict the positional offset from the fused text point cloud features, achieving the most accurate localization. Extensive experiments show that MambaPlace achieves improved localization accuracy on the KITTI360Pose dataset compared to the state of the art methods.

cs.CV↗

arXiv2025

Quantum encryption design overcomes Shannon's theorem to achieve perfect secrecy with reusable keys

Shannon's perfect-secrecy theorem states that a perfect encryption system that yields zero information to the adversary must be a one-time pad (OTP) with the keys randomly generated and never reused. In this work we design the first encryption method (classical or quantum) that overcomes Shannon's theorem to achieve perfect secrecy with reusable keys. Because the mechanisms used are fundamentally quantum, Shannon's theorem remains true in the classical regime. Consequently, the quantum encryption design demonstrates decisive quantum advantage by achieving a goal impossible for classical systems. Finally, the design has major practical advantages by not requiring authentication and having silent tampering detection.

quant-ph↗

arXiv2025

CoPRA: Bridging Cross-domain Pretrained Sequence Models with Complex Structures for Protein-RNA Binding Affinity Prediction

Accurately measuring protein-RNA binding affinity is crucial in many biological processes and drug design. Previous computational methods for protein-RNA binding affinity prediction rely on either sequence or structure features, unable to capture the binding mechanisms comprehensively. The recent emerging pre-trained language models trained on massive unsupervised sequences of protein and RNA have shown strong representation ability for various in-domain downstream tasks, including binding site prediction. However, applying different-domain language models collaboratively for complex-level tasks remains unexplored. In this paper, we propose CoPRA to bridge pre-trained language models from different biological domains via Complex structure for Protein-RNA binding Affinity prediction. We demonstrate for the first time that cross-biological modal language models can collaborate to improve binding affinity prediction. We propose a Co-Former to combine the cross-modal sequence and structure information and a bi-scope pre-training strategy for improving Co-Former's interaction understanding. Meanwhile, we build the largest protein-RNA binding affinity dataset PRA310 for performance evaluation. We also test our model on a public dataset for mutation effect prediction. CoPRA reaches state-of-the-art performance on all the datasets. We provide extensive analyses and verify that CoPRA can (1) accurately predict the protein-RNA binding affinity; (2) understand the binding affinity change caused by mutations; and (3) benefit from scaling data and model size.

q-bio.BM↗

arXiv2025

PatchRefiner V2: Fast and Lightweight Real-Domain High-Resolution Metric Depth Estimation

While current high-resolution depth estimation methods achieve strong results, they often suffer from computational inefficiencies due to reliance on heavyweight models and multiple inference steps, increasing inference time. To address this, we introduce PatchRefiner V2 (PRV2), which replaces heavy refiner models with lightweight encoders. This reduces model size and inference time but introduces noisy features. To overcome this, we propose a Coarse-to-Fine (C2F) module with a Guided Denoising Unit for refining and denoising the refiner features and a Noisy Pretraining strategy to pretrain the refiner branch to fully exploit the potential of the lightweight refiner branch. Additionally, we introduce a Scale-and-Shift Invariant Gradient Matching (SSIGM) loss to enhance synthetic-to-real domain transfer. PRV2 outperforms state-of-the-art depth estimation methods on UnrealStereo4K in both accuracy and speed, using fewer parameters and faster inference. It also shows improved depth boundary delineation on real-world datasets like CityScape, ScanNet++, and KITTI, demonstrating its versatility across domains.

cs.CV↗

arXiv2024

FocusLLM: Precise Understanding of Long Context by Dynamic Condensing

Empowering LLMs with the ability to precisely understand long contexts is crucial for many downstream applications. However, handling long contexts with conventional transformer architecture requires substantial training and inference resources. Existing context condensing methods cannot accurately understand the full context, as there is a considerable amount of information loss in the condensing process. To address these issues, we present FocusLLM, a framework designed to extend the fixed context length of any decoder-only LLM, allowing the model to focus on relevant information from very long sequences. FocusLLM first divides long text input into chunks based on the model's original context length. It then employs the dynamic condensing process to distill crucial information from each chunk. Ultimately, through the novel parallel decoding mechanism, FocusLLM can integrate the extracted information into its local context. FocusLLM stands out for great training efficiency and versatility: trained with an 8K input length and with much less training cost than previous methods, FocusLLM exhibits superior performance across downstream tasks and maintains strong language modeling ability when handling extensive long texts, even up to 400K tokens. Our code is available at https://github.com/leezythu/FocusLLM.

cs.CL↗

arXiv2024

Amodal Depth Anything: Amodal Depth Estimation in the Wild

Amodal depth estimation aims to predict the depth of occluded (invisible) parts of objects in a scene. This task addresses the question of whether models can effectively perceive the geometry of occluded regions based on visible cues. Prior methods primarily rely on synthetic datasets and focus on metric depth estimation, limiting their generalization to real-world settings due to domain shifts and scalability challenges. In this paper, we propose a novel formulation of amodal depth estimation in the wild, focusing on relative depth prediction to improve model generalization across diverse natural images. We introduce a new large-scale dataset, Amodal Depth In the Wild (ADIW), created using a scalable pipeline that leverages segmentation datasets and compositing techniques. Depth maps are generated using large pre-trained depth models, and a scale-and-shift alignment strategy is employed to refine and blend depth predictions, ensuring consistency in ground-truth annotations. To tackle the amodal depth task, we present two complementary frameworks: Amodal-DAV2, a deterministic model based on Depth Anything V2, and Amodal-DepthFM, a generative model that integrates conditional flow matching principles. Our proposed frameworks effectively leverage the capabilities of large pre-trained models with minimal modifications to achieve high-quality amodal depth predictions. Experiments validate our design choices, demonstrating the flexibility of our models in generating diverse, plausible depth structures for occluded regions. Our method achieves a 69.5% improvement in accuracy over the previous SoTA on the ADIW dataset.

cs.CV↗

arXiv2024

ImmersePro: End-to-End Stereo Video Synthesis Via Implicit Disparity Learning

We introduce \textit{ImmersePro}, an innovative framework specifically designed to transform single-view videos into stereo videos. This framework utilizes a novel dual-branch architecture comprising a disparity branch and a context branch on video data by leveraging spatial-temporal attention mechanisms. \textit{ImmersePro} employs implicit disparity guidance, enabling the generation of stereo pairs from video sequences without the need for explicit disparity maps, thus reducing potential errors associated with disparity estimation models. In addition to the technical advancements, we introduce the YouTube-SBS dataset, a comprehensive collection of 423 stereo videos sourced from YouTube. This dataset is unprecedented in its scale, featuring over 7 million stereo pairs, and is designed to facilitate training and benchmarking of stereo video generation models. Our experiments demonstrate the effectiveness of \textit{ImmersePro} in producing high-quality stereo videos, offering significant improvements over existing methods. Compared to the best competitor stereo-from-mono we quantitatively improve the results by 11.76\% (L1), 6.39\% (SSIM), and 5.10\% (PSNR).

cs.CV↗

arXiv2024

The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation

Accurate depth estimation under out-of-distribution (OoD) scenarios, such as adverse weather conditions, sensor failure, and noise contamination, is desirable for safety-critical applications. Existing depth estimation systems, however, suffer inevitably from real-world corruptions and perturbations and are struggled to provide reliable depth predictions under such cases. In this paper, we summarize the winning solutions from the RoboDepth Challenge -- an academic competition designed to facilitate and advance robust OoD depth estimation. This challenge was developed based on the newly established KITTI-C and NYUDepth2-C benchmarks. We hosted two stand-alone tracks, with an emphasis on robust self-supervised and robust fully-supervised depth estimation, respectively. Out of more than two hundred participants, nine unique and top-performing solutions have appeared, with novel designs ranging from the following aspects: spatial- and frequency-domain augmentations, masked image modeling, image restoration and super-resolution, adversarial training, diffusion-based noise suppression, vision-language pre-training, learned model ensembling, and hierarchical feature enhancement. Extensive experimental analyses along with insightful observations are drawn to better understand the rationale behind each design. We hope this challenge could lay a solid foundation for future research on robust and reliable depth estimation and beyond. The datasets, competition toolkit, workshop recordings, and source code from the winning teams are publicly available on the challenge website.

cs.CV↗