arXiv subjects

Bo Chen

Publications and source records attributed to Bo Chen.

At least 163 records · Page 9Linked to original sources

arXiv2025

LLM4Tag: Automatic Tagging System for Information Retrieval via Large Language Models

Tagging systems play an essential role in various information retrieval applications such as search engines and recommender systems. Recently, Large Language Models (LLMs) have been applied in tagging systems due to their extensive world knowledge, semantic understanding, and reasoning capabilities. Despite achieving remarkable performance, existing methods still have limitations, including difficulties in retrieving relevant candidate tags comprehensively, challenges in adapting to emerging domain-specific knowledge, and the lack of reliable tag confidence quantification. To address these three limitations above, we propose an automatic tagging system LLM4Tag. First, a graph-based tag recall module is designed to effectively and comprehensively construct a small-scale highly relevant candidate tag set. Subsequently, a knowledge-enhanced tag generation module is employed to generate accurate tags with long-term and short-term knowledge injection. Finally, a tag confidence calibration module is introduced to generate reliable tag confidence scores. Extensive experiments over three large-scale industrial datasets show that LLM4Tag significantly outperforms the state-of-the-art baselines and LLM4Tag has been deployed online for content tagging to serve hundreds of millions of users.

cs.IR↗

arXiv2025

Efficiency Unleashed: Inference Acceleration for LLM-based Recommender Systems with Speculative Decoding

The past few years have witnessed a growing interest in LLM-based recommender systems (RSs), although their industrial deployment remains in a preliminary stage. Most existing deployments leverage LLMs offline as feature enhancers, generating augmented knowledge for downstream tasks. However, in recommendation scenarios with numerous users and items, even offline knowledge generation with LLMs demands significant time and computational resources. This inefficiency arises from the autoregressive nature of LLMs. A promising solution is speculative decoding, a Draft-Then-Verify approach that increases the number of tokens generated per decoding step. In this work, we first identify recommendation knowledge generation as a highly fitting use case for retrieval-based speculative decoding. Then, we discern its two characteristics: (1) the vast number of items and users in RSs leads to retrieval inefficiency, and (2) RSs exhibit high diversity tolerance for LLM-generated text. Building on these insights, we introduce Lossless Acceleration via Speculative Decoding for LLM-based Recommender Systems (LASER), which features a Customized Retrieval Pool to enhance retrieval efficiency and Relaxed Verification to improve the acceptance rate of draft tokens. LASER achieves a 3-5x speedup on public datasets and saves about 67\% of computational resources during the online A/B test on a large-scale advertising scenario with lossless downstream recommendation performance. Our code is available at https://github.com/YunjiaXi/LASER

cs.IR↗

arXiv2025

WenyanGPT: A Large Language Model for Classical Chinese Tasks

Classical Chinese, as the core carrier of Chinese culture, plays a crucial role in the inheritance and study of ancient literature. However, existing natural language processing models primarily optimize for Modern Chinese, resulting in inadequate performance on Classical Chinese. This paper presents a comprehensive solution for Classical Chinese language processing. By continuing pre-training and instruction fine-tuning on the LLaMA3-8B-Chinese model, we construct a large language model, WenyanGPT, which is specifically designed for Classical Chinese tasks. Additionally, we develop an evaluation benchmark dataset, WenyanBENCH. Experimental results on WenyanBENCH demonstrate that WenyanGPT significantly outperforms current advanced LLMs in various Classical Chinese tasks. We make the model's training data, instruction fine-tuning data\footnote, and evaluation benchmark dataset publicly available to promote further research and development in the field of Classical Chinese processing.

cs.CL↗

arXiv2025

Covariance-Intersection-based Distributed Kalman Filtering: Stability Problems Revisited

This paper studies the stability of covariance-intersection (CI)-based distributed Kalman filtering in time-varying systems. For the general time-varying case, a relationship between the error covariance and the observability Gramian is established. Utilizing this relationship, we demonstrate an intuition that the stability of a node is only related to the observability of those nodes that can reach it uniformly. For the periodic time-varying case, it is proved by a monotonicity analysis method that CI-based distributed Kalman filtering converges periodically for any initial condition. The convergent point is shown to be the unique positive definite solution to a Riccati-like equation. Additionally, by constructing an intermediate difference equation, the closed-loop transition matrix of the estimation error system is proved to be Schur stable. Notably, all theoretical results are obtained without requiring network connectivity assumptions. Finally, simulations verify the effectiveness of the stability results.

eess.SY↗

arXiv2025

Provable Failure of Language Models in Learning Majority Boolean Logic via Gradient Descent

Recent advancements in Transformer-based architectures have led to impressive breakthroughs in natural language processing tasks, with models such as GPT-4, Claude, and Gemini demonstrating human-level reasoning abilities. However, despite their high performance, concerns remain about the inherent limitations of these models, especially when it comes to learning basic logical functions. While complexity-theoretic analyses indicate that Transformers can represent simple logic functions (e.g., $\mathsf{AND}$, $\mathsf{OR}$, and majority gates) by its nature of belonging to the $\mathsf{TC}^0$ class, these results assume ideal parameter settings and do not account for the constraints imposed by gradient descent-based training methods. In this work, we investigate whether Transformers can truly learn simple majority functions when trained using gradient-based methods. We focus on a simplified variant of the Transformer architecture and consider both $n=\mathrm{poly}(d)$ and $n=\exp(Ω(d))$ number of training samples, where each sample is a $d$-size binary string paired with the output of a basic majority function. Our analysis demonstrates that even after $\mathrm{poly}(d)$ gradient queries, the generalization error of the Transformer model still remains substantially large, growing exponentially with $d$. This work highlights fundamental optimization challenges in training Transformers for the simplest logical reasoning tasks and provides new insights into their theoretical limitations.

cs.LG↗

arXiv2025

OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts

The rapid advancement of multi-modal language models (MLLMs) like GPT-4o has propelled the development of Omni language models, designed to process and proactively respond to continuous streams of multi-modal data. Despite their potential, evaluating their real-world interactive capabilities in streaming video contexts remains a formidable challenge. In this work, we introduce OmniMMI, a comprehensive multi-modal interaction benchmark tailored for OmniLLMs in streaming video contexts. OmniMMI encompasses over 1,121 videos and 2,290 questions, addressing two critical yet underexplored challenges in existing video benchmarks: streaming video understanding and proactive reasoning, across six distinct subtasks. Moreover, we propose a novel framework, Multi-modal Multiplexing Modeling (M4), designed to enable an inference-efficient streaming model that can see, listen while generating.

cs.CV↗

arXiv2025

Ultrafast photoinduced phase transition in the antiferromagnetic Dirac semimetal EuAgAs

We report the observation of a light-induced subpicosecond phase transition in the antiferromagnetic Dirac semimetal EuAgAs, achieved through ultrafast optical excitation. Using ultrafast optical spectroscopy, we probe the nonequilibrium carrier dynamics, discovering distinct fluence-dependent responses in the antiferromagnetic and paramagnetic states, and revealing a possible magnetic order-driven transition between different topological states. Our results demonstrate that EuAgAs, with its highly tunable magnetic structure, possibly offers a unique platform for exploring topological phase transitions. These results underscore the potential of ultrashort optical pulses as powerful tools for the real-time control of topological phases, opening pathways for advances in spintronics, quantum computing, and energy-efficient information technologies.

cond-mat.str-el↗

arXiv2025

Explaining Domain Shifts in Language: Concept erasing for Interpretable Image Classification

Concept-based models can map black-box representations to human-understandable concepts, which makes the decision-making process more transparent and then allows users to understand the reason behind predictions. However, domain-specific concepts often impact the final predictions, which subsequently undermine the model generalization capabilities, and prevent the model from being used in high-stake applications. In this paper, we propose a novel Language-guided Concept-Erasing (LanCE) framework. In particular, we empirically demonstrate that pre-trained vision-language models (VLMs) can approximate distinct visual domain shifts via domain descriptors while prompting large Language Models (LLMs) can easily simulate a wide range of descriptors of unseen visual domains. Then, we introduce a novel plug-in domain descriptor orthogonality (DDO) regularizer to mitigate the impact of these domain-specific concepts on the final predictions. Notably, the DDO regularizer is agnostic to the design of concept-based models and we integrate it into several prevailing models. Through evaluation of domain generalization on four standard benchmarks and three newly introduced benchmarks, we demonstrate that DDO can significantly improve the out-of-distribution (OOD) generalization over the previous state-of-the-art concept-based models.Our code is available at https://github.com/joeyz0z/LanCE.

cs.CV↗

arXiv2025

LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers

Diffusion Transformers have emerged as the preeminent models for a wide array of generative tasks, demonstrating superior performance and efficacy across various applications. The promising results come at the cost of slow inference, as each denoising step requires running the whole transformer model with a large amount of parameters. In this paper, we show that performing the full computation of the model at each diffusion step is unnecessary, as some computations can be skipped by lazily reusing the results of previous steps. Furthermore, we show that the lower bound of similarity between outputs at consecutive steps is notably high, and this similarity can be linearly approximated using the inputs. To verify our demonstrations, we propose the \textbf{LazyDiT}, a lazy learning framework that efficiently leverages cached results from earlier steps to skip redundant computations. Specifically, we incorporate lazy learning layers into the model, effectively trained to maximize laziness, enabling dynamic skipping of redundant computations. Experimental results show that LazyDiT outperforms the DDIM sampler across multiple diffusion transformer models at various resolutions. Furthermore, we implement our method on mobile devices, achieving better performance than DDIM with similar latency. Code: https://github.com/shawnricecake/lazydit

cs.LG↗

arXiv2025

Anisotropic Hybridization Dynamics in the Quasi-One-Dimensional Kondo Lattice CeCo$_2$Ga$_8$ Revealed by Ultrafast Optical Spectroscopy

We investigate the ultrafast dynamics of the quasi-one-dimensional Kondo lattice CeCo$_2$Ga$_8$ using optical pump-probe spectroscopy. Time-resolved pump-probe reflectivity measurements reveal a strong anisotropy in the photoinduced response, which is a direct consequence of the material's unique electronic structure. The temperature dependence of the relaxation dynamics provides evidence for the formation of two distinct hybridization gaps that appear at different temperatures in the heavy fermion state. A direct gap of 2$Δ_{dir}$ $\approx$ 50 meV that persists up to $T^†$ $\approx$ 90 K, well above the coherence temperature $T^*$ $\approx$ 20 K. We attribute this higher-temperature gap to the hybridization fluctuations. An indirect gap of 2$Δ_{ind}$ $\approx$ 10 meV opens closer to $T^*$, signifying the development of long-range coherence in the heavy fermion state. Furthermore, we find that the hybridization gap can be suppressed with increasing pump fluence, indicating a delicate interplay between photoexcitation and the coherent heavy fermion state. Our results provide insights into the interplay of Kondo physics and low dimensionality in CeCo$_2$Ga$_8$, and establish ultrafast optical spectroscopy as a sensitive probe of anisotropic hybridization in heavy fermion materials.

cond-mat.str-el↗

arXiv2025

Interplay of electron-phonon coupling, pseudogap, and superconductivity in CsCa$_2$Fe$_4$As$_4$F$_2$ studied using ultrafast optical spectroscopy

The quasiparticle relaxation dynamics of the iron-based superconductor CsCa$_2$Fe$_4$As$_4$F$_2$ ($T_c$ $\sim$ 29 K) were investigated using ultrafast optical spectroscopy. A pseudogap ($Δ_{PG}$ $\approx$ 3.3 meV) was observed to open below $T^{\ast}$ $\approx$ 60 K, prior to the emergence of a superconducting gap ($Δ$ $\approx$ 6.6 $\pm$ 0.4 meV). At high excitation fluence, a coherent A1g phonon mode at 5.49 THz was identified, exhibiting deviations from anharmonic behavior below $T_c$. The electron-phonon coupling constant for this mode was estimated to be $λ_{A_{1g}}$ $\approx$ 0.23. These results provide insights into the interplay between the electron-phonon interactions, pseudogap, and the superconducting pairing mechanism in CsCa$_2$Fe$_4$As$_4$F$_2$.

cond-mat.supr-con↗

arXiv2025

Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent

In-context learning has been recognized as a key factor in the success of Large Language Models (LLMs). It refers to the model's ability to learn patterns on the fly from provided in-context examples in the prompt during inference. Previous studies have demonstrated that the Transformer architecture used in LLMs can implement a single-step gradient descent update by processing in-context examples in a single forward pass. Recent work has further shown that, during in-context learning, a looped Transformer can implement multi-step gradient descent updates in forward passes. However, their theoretical results require an exponential number of in-context examples, $n = \exp(Ω(T))$, where $T$ is the number of loops or passes, to achieve a reasonably low error. In this paper, we study linear looped Transformers in-context learning on linear vector generation tasks. We show that linear looped Transformers can implement multi-step gradient descent efficiently for in-context learning. Our results demonstrate that as long as the input data has a constant condition number, e.g., $n = O(d)$, the linear looped Transformers can achieve a small error by multi-step gradient descent during in-context learning. Furthermore, our preliminary experiments validate our theoretical analysis. Our findings reveal that the Transformer architecture possesses a stronger in-context learning capability than previously understood, offering new insights into the mechanisms behind LLMs and potentially guiding the better design of efficient inference algorithms for LLMs.

cs.LG↗

arXiv2025

Joint Modeling in Recommendations: A Survey

In today's digital landscape, Deep Recommender Systems (DRS) play a crucial role in navigating and customizing online content for individual preferences. However, conventional methods, which mainly depend on single recommendation task, scenario, data modality and user behavior, are increasingly seen as insufficient due to their inability to accurately reflect users' complex and changing preferences. This gap underscores the need for joint modeling approaches, which are central to overcoming these limitations by integrating diverse tasks, scenarios, modalities, and behaviors in the recommendation process, thus promising significant enhancements in recommendation precision, efficiency, and customization. In this paper, we comprehensively survey the joint modeling methods in recommendations. We begin by defining the scope of joint modeling through four distinct dimensions: multi-task, multi-scenario, multi-modal, and multi-behavior modeling. Subsequently, we examine these methods in depth, identifying and summarizing their underlying paradigms based on the latest advancements and potential research trajectories. Ultimately, we highlight several promising avenues for future exploration in joint modeling for recommendations and provide a concise conclusion to our findings.

cs.IR↗

arXiv2025

Distributed Zonotopic Fusion Estimation for Multi-sensor Systems

Fusion estimation is often used in multi-sensor systems to provide accurate state information which plays an important role in the design of efficient control and decision-making. This paper is concerned with the distributed zonotopic fusion estimation problem for multi-sensor systems. The objective is to propose a zonotopic fusion estimation approach using different zonotope fusion criteria. We begin by proposing a novel zonotope fusion criterion to compute a distributed zonotopic fusion estimate (DZFE). The DZFE is formulated as a zonotope enclosure for the intersection of local zonotopic estimates from individual sensors. Then, the optimal parameter matrices for tuning the DZFE are determined by the analytical solution of an optimization problem. To reduce the conservatism of the DZFE with optimal parameters, we enhance our approach with an improved zonotope fusion criterion, which further improves the estimation performance of this DZFE by constructing tight strips for the intersection. In addition, we tackle the problem of handling sequentially arrived local estimates in realistic communication environments with a sequential zonotope fusion criterion. This sequential zonotope fusion offers reduced computational complexity compared to batch zonotope fusion. Notice that the proposed zonotope fusion criteria are designed to meet the state inclusion property and demonstrate performance superiority over local zonotopic estimates. We also derive stability conditions for these DZFEs to ensure their generator matrices are ultimately bounded. Finally, two illustrative examples are employed to show the effectiveness and advantages of the proposed methods.

eess.SY↗

arXiv2025

HSR-Enhanced Sparse Attention Acceleration

Large Language Models (LLMs) have demonstrated remarkable capabilities across various applications, but their performance on long-context tasks is often limited by the computational complexity of attention mechanisms. We introduce a novel approach to accelerate attention computation in LLMs, particularly for long-context scenarios. We leverage the inherent sparsity within attention mechanisms, both in conventional Softmax attention and ReLU attention (with $\mathsf{ReLU}^α$ activation, $α\in \mathbb{N}_+$), to significantly reduce the running time complexity. Our method employs a Half-Space Reporting (HSR) data structure to identify non-zero or ``massively activated'' entries in the attention matrix. We present theoretical analyses for two key scenarios: generation decoding and prompt prefilling. Our approach achieves a running time of $O(mn^{4/5})$ significantly faster than the naive approach $O(mn)$ for generation decoding, where $n$ is the context length, $m$ is the query length, and $d$ is the hidden dimension. We can also reduce the running time for prompt prefilling from $O(mn)$ to $O(mn^{1 - 1 / \lfloor d/2\rfloor} + mn^{4/5})$. Our method introduces only provably negligible error for Softmax attention. This work represents a significant step towards enabling efficient long-context processing in LLMs.

cs.LG↗

arXiv2025

AquaScope: Reliable Underwater Image Transmission on Mobile Devices

Underwater communication is essential for both recreational and scientific activities, such as scuba diving. However, existing methods remain highly constrained by environmental challenges and often require specialized hardware, driving research into more accessible underwater communication solutions. While recent acoustic-based communication systems support text messaging on mobile devices, their low data rates severely limit broader applications. We present AquaScope, the first acoustic communication system capable of underwater image transmission on commodity mobile devices. To address the key challenges of underwater environments -- limited bandwidth and high transmission errors -- AquaScope employs and enhances generative image compression to improve compression efficiency, and integrates it with reliability-enhancement techniques at the physical layer to strengthen error resilience. We implemented AquaScope on the Android platform and demonstrated its feasibility for underwater image transmission. Experimental results show that AquaScope enables reliable, low-latency image transmission while preserving perceptual image quality, across various bandwidth-constrained and error-prone underwater conditions.

cs.NI↗

arXiv2025

Force Matching with Relativistic Constraints: A Physics-Inspired Approach to Stable and Efficient Generative Modeling

This paper introduces Force Matching (ForM), a novel framework for generative modeling that represents an initial exploration into leveraging special relativistic mechanics to enhance the stability of the sampling process. By incorporating the Lorentz factor, ForM imposes a velocity constraint, ensuring that sample velocities remain bounded within a constant limit. This constraint serves as a fundamental mechanism for stabilizing the generative dynamics, leading to a more robust and controlled sampling process. We provide a rigorous theoretical analysis demonstrating that the velocity constraint is preserved throughout the sampling procedure within the ForM framework. To validate the effectiveness of our approach, we conduct extensive empirical evaluations. On the \textit{half-moons} dataset, ForM significantly outperforms baseline methods, achieving the lowest Euclidean distance loss of \textbf{0.714}, in contrast to vanilla first-order flow matching (5.853) and first- and second-order flow matching (5.793). Additionally, we perform an ablation study to further investigate the impact of our velocity constraint, reaffirming the superiority of ForM in stabilizing the generative process. The theoretical guarantees and empirical results underscore the potential of integrating special relativity principles into generative modeling. Our findings suggest that ForM provides a promising pathway toward achieving stable, efficient, and flexible generative processes. This work lays the foundation for future advancements in high-dimensional generative modeling, opening new avenues for the application of physical principles in machine learning.

cs.LG↗

arXiv2025

Scalable Distributed Reproduction Numbers of Network Epidemics with Differential Privacy

Reproduction numbers are widely used for the estimation and prediction of epidemic spreading processes over networks. However, conventional reproduction numbers of an overall network do not indicate where an epidemic is spreading. Therefore, we propose a novel notion of local distributed reproduction numbers to capture the spreading behaviors of each node in a network. We first show how to compute them and then use them to derive new conditions under which an outbreak can occur. These conditions are then used to derive new conditions for the existence, uniqueness, and stability of equilibrium states of the underlying epidemic model. Building upon these local distributed reproduction numbers, we define cluster distributed reproduction numbers to model the spread between clusters composed of nodes. Furthermore, we demonstrate that the local distributed reproduction numbers can be aggregated into cluster distributed reproduction numbers at different scales. However, both local and cluster distributed reproduction numbers can reveal the frequency of interactions between nodes in a network, which raises privacy concerns. Thus, we next develop a privacy framework that implements a differential privacy mechanism to provably protect the frequency of interactions between nodes when computing distributed reproduction numbers. Numerical experiments show that, even under differential privacy, the distributed reproduction numbers provide accurate estimates of the epidemic spread while also providing more insights than conventional reproduction numbers.

eess.SY↗