arXiv subjects

Xu Shen

Publications and source records attributed to Xu Shen.

At least 37 records · Page 2Linked to original sources

arXiv2025

SpecOffload: Unlocking Latent GPU Capacity for LLM Inference on Resource-Constrained Devices

Efficient LLM inference on resource-constrained devices presents significant challenges in compute and memory utilization. Due to limited GPU memory, existing systems offload model weights to CPU memory, incurring substantial I/O overhead between the CPU and GPU. This leads to two major inefficiencies: (1) GPU cores are underutilized, often remaining idle while waiting for data to be loaded; and (2) GPU memory has low impact on performance, as reducing its capacity has minimal effect on overall throughput.In this paper, we propose SpecOffload, a high-throughput inference engine that embeds speculative decoding into offloading. Our key idea is to unlock latent GPU resources for storing and executing a draft model used for speculative decoding, thus accelerating inference at near-zero additional cost. To support this, we carefully orchestrate the interleaved execution of target and draft models in speculative decoding within the offloading pipeline, and propose a planner to manage tensor placement and select optimal parameters. Compared to the best baseline, SpecOffload improves GPU core utilization by 4.49x and boosts inference throughput by 2.54x. Our code is available at https://github.com/MobiSense/SpecOffload-public .

cs.LG↗

arXiv2025

Harnessing LLMs Explanations to Boost Surrogate Models in Tabular Data Classification

Large Language Models (LLMs) have shown remarkable ability in solving complex tasks, making them a promising tool for enhancing tabular learning. However, existing LLM-based methods suffer from high resource requirements, suboptimal demonstration selection, and limited interpretability, which largely hinder their prediction performance and application in the real world. To overcome these problems, we propose a novel in-context learning framework for tabular prediction. The core idea is to leverage the explanations generated by LLMs to guide a smaller, locally deployable Surrogate Language Model (SLM) to make interpretable tabular predictions. Specifically, our framework mainly involves three stages: (i) Post Hoc Explanation Generation, where LLMs are utilized to generate explanations for question-answer pairs in candidate demonstrations, providing insights into the reasoning behind the answer. (ii) Post Hoc Explanation-Guided Demonstrations Selection, which utilizes explanations generated by LLMs to guide the process of demonstration selection from candidate demonstrations. (iii) Post Hoc Explanation-Guided Interpretable SLM Prediction, which utilizes the demonstrations obtained in step (ii) as in-context and merges corresponding explanations as rationales to improve the performance of SLM and guide the model to generate interpretable outputs. Experimental results highlight the framework's effectiveness, with an average accuracy improvement of 5.31% across various tabular datasets in diverse domains.

cs.LG↗

arXiv2025

Latte: Transfering LLMs` Latent-level Knowledge for Few-shot Tabular Learning

Few-shot tabular learning, in which machine learning models are trained with a limited amount of labeled data, provides a cost-effective approach to addressing real-world challenges. The advent of Large Language Models (LLMs) has sparked interest in leveraging their pre-trained knowledge for few-shot tabular learning. Despite promising results, existing approaches either rely on test-time knowledge extraction, which introduces undesirable latency, or text-level knowledge, which leads to unreliable feature engineering. To overcome these limitations, we propose Latte, a training-time knowledge extraction framework that transfers the latent prior knowledge within LLMs to optimize a more generalized downstream model. Latte enables general knowledge-guided downstream tabular learning, facilitating the weighted fusion of information across different feature values while reducing the risk of overfitting to limited labeled data. Furthermore, Latte is compatible with existing unsupervised pre-training paradigms and effectively utilizes available unlabeled samples to overcome the performance limitations imposed by an extremely small labeled dataset. Extensive experiments on various few-shot tabular learning benchmarks demonstrate the superior performance of Latte, establishing it as a state-of-the-art approach in this domain

cs.LG↗

arXiv2025

Leveraging Submodule Linearity Enhances Task Arithmetic Performance in LLMs

Task arithmetic is a straightforward yet highly effective strategy for model merging, enabling the resultant model to exhibit multi-task capabilities. Recent research indicates that models demonstrating linearity enhance the performance of task arithmetic. In contrast to existing methods that rely on the global linearization of the model, we argue that this linearity already exists within the model's submodules. In particular, we present a statistical analysis and show that submodules (e.g., layers, self-attentions, and MLPs) exhibit significantly higher linearity than the overall model. Based on these findings, we propose an innovative model merging strategy that independently merges these submodules. Especially, we derive a closed-form solution for optimal merging weights grounded in the linear properties of these submodules. Experimental results demonstrate that our method consistently outperforms the standard task arithmetic approach and other established baselines across different model scales and various tasks. This result highlights the benefits of leveraging the linearity of submodules and provides a new perspective for exploring solutions for effective and practical multi-task model merging.

cs.LG↗

arXiv2025

Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A Benchmark

To build safe and reliable graph machine learning systems, unsupervised graph-level anomaly detection (GLAD) and unsupervised graph-level out-of-distribution (OOD) detection (GLOD) have received significant attention in recent years. Though those two lines of research indeed share the same objective, they have been studied independently in the community due to distinct evaluation setups, creating a gap that hinders the application and evaluation of methods from one to the other. To bridge the gap, in this work, we present a \underline{\textbf{U}}nified \underline{\textbf{B}}enchmark for unsupervised \underline{\textbf{G}}raph-level \underline{\textbf{O}}OD and anoma\underline{\textbf{L}}y \underline{\textbf{D}}etection (\ourmethod), a comprehensive evaluation framework that unifies GLAD and GLOD under the concept of generalized graph-level OOD detection. Our benchmark encompasses 35 datasets spanning four practical anomaly and OOD detection scenarios, facilitating the comparison of 18 representative GLAD/GLOD methods. We conduct multi-dimensional analyses to explore the effectiveness, OOD sensitivity spectrum, robustness, and efficiency of existing methods, shedding light on their strengths and limitations. Furthermore, we provide an open-source codebase (https://github.com/UB-GOLD/UB-GOLD) of \ourmethod to foster reproducible research and outline potential directions for future investigations based on our insights.

cs.LG↗

arXiv2025

Bruhat-Tits buildings and $p$-adic period domains

Let $G$ be a connected reductive group over a $p$-adic local field $F$. Rémy-Thuillier-Werner constructed embeddings of the (reduced) Bruhat-Tits building $\mathcal{B}(G,F)$ into the Berkovich spaces associated to suitable flag varieties of $G$, generalizing the work of Berkovich in split case. They defined compactifications of $\mathcal{B}(G,F)$ by taking closure inside these Berkovich flag varieties. We show that, in the setting of a basic local Shimura datum, the Rémy-Thuillier-Werner embedding factors through the associated $p$-adic Hodge-Tate period domain. Moreover, we compare the boundaries of the Berkovich compactification of $\mathcal{B}(G,F)$ with non basic Newton strata. In the case of $\mathrm{GL}_n$ and the cocharacter $μ=(1^d, 0^{n-d})$ for an integer $d$ which is coprime to $n$, we further construct a continuous retraction map from the $p$-adic period domain to the building. This reveals new information on these $p$-adic period domains, which share many similarities with the Drinfeld spaces.

math.NT↗

arXiv2025

From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning

Large Language Models (LLMs) tend to prioritize adherence to user prompts over providing veracious responses, leading to the sycophancy issue. When challenged by users, LLMs tend to admit mistakes and provide inaccurate responses even if they initially provided the correct answer. Recent works propose to employ supervised fine-tuning (SFT) to mitigate the sycophancy issue, while it typically leads to the degeneration of LLMs' general capability. To address the challenge, we propose a novel supervised pinpoint tuning (SPT), where the region-of-interest modules are tuned for a given objective. Specifically, SPT first reveals and verifies a small percentage (<5%) of the basic modules, which significantly affect a particular behavior of LLMs. i.e., sycophancy. Subsequently, SPT merely fine-tunes these identified modules while freezing the rest. To verify the effectiveness of the proposed SPT, we conduct comprehensive experiments, demonstrating that SPT significantly mitigates the sycophancy issue of LLMs (even better than SFT). Moreover, SPT introduces limited or even no side effects on the general capability of LLMs. Our results shed light on how to precisely, effectively, and efficiently explain and improve the targeted ability of LLMs. Code and data are available at https://github.com/yellowtownhz/sycophancy-interpretability.

cs.CL↗

arXiv2024

Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control

As the development and application of Large Language Models (LLMs) continue to advance rapidly, enhancing their trustworthiness and aligning them with human preferences has become a critical area of research. Traditional methods rely heavily on extensive data for Reinforcement Learning from Human Feedback (RLHF), but representation engineering offers a new, training-free approach. This technique leverages semantic features to control the representation of LLM's intermediate hidden states, enabling the model to meet specific requirements such as increased honesty or heightened safety awareness. However, a significant challenge arises when attempting to fulfill multiple requirements simultaneously. It proves difficult to encode various semantic contents, like honesty and safety, into a singular semantic feature, restricting its practicality. In this work, we address this issue through ``Sparse Activation Control''. By delving into the intrinsic mechanisms of LLMs, we manage to identify and pinpoint components that are closely related to specific tasks within the model, i.e., attention heads. These heads display sparse characteristics that allow for near-independent control over different tasks. Our experiments, conducted on the open-source Llama series models, have yielded encouraging results. The models were able to align with human preferences on issues of safety, factuality, and bias concurrently.

cs.CL↗

arXiv2024

SAC-KG: Exploiting Large Language Models as Skilled Automatic Constructors for Domain Knowledge Graphs

Knowledge graphs (KGs) play a pivotal role in knowledge-intensive tasks across specialized domains, where the acquisition of precise and dependable knowledge is crucial. However, existing KG construction methods heavily rely on human intervention to attain qualified KGs, which severely hinders the practical applicability in real-world scenarios. To address this challenge, we propose a general KG construction framework, named SAC-KG, to exploit large language models (LLMs) as Skilled Automatic Constructors for domain Knowledge Graph. SAC-KG effectively involves LLMs as domain experts to generate specialized and precise multi-level KGs. Specifically, SAC-KG consists of three components: Generator, Verifier, and Pruner. For a given entity, Generator produces its relations and tails from raw domain corpora, to construct a specialized single-level KG. Verifier and Pruner then work together to ensure precision by correcting generation errors and determining whether newly produced tails require further iteration for the next-level KG.Experiments demonstrate that SAC-KG automatically constructs a domain KG at the scale of over one million nodes and achieves a precision of 89.32%, leading to a superior performance with over 20% increase in precision rate compared to existing state-of-the-art methods for the KG construction task.

cs.AI↗

arXiv2024

Interpreting and Improving Large Language Models in Arithmetic Calculation

Large language models (LLMs) have demonstrated remarkable potential across numerous applications and have shown an emergent ability to tackle complex reasoning tasks, such as mathematical computations. However, even for the simplest arithmetic calculations, the intrinsic mechanisms behind LLMs remain mysterious, making it challenging to ensure reliability. In this work, we delve into uncovering a specific mechanism by which LLMs execute calculations. Through comprehensive experiments, we find that LLMs frequently involve a small fraction (< 5%) of attention heads, which play a pivotal role in focusing on operands and operators during calculation processes. Subsequently, the information from these operands is processed through multi-layer perceptrons (MLPs), progressively leading to the final solution. These pivotal heads/MLPs, though identified on a specific dataset, exhibit transferability across different datasets and even distinct tasks. This insight prompted us to investigate the potential benefits of selectively fine-tuning these essential heads/MLPs to boost the LLMs' computational performance. We empirically find that such precise tuning can yield notable enhancements on mathematical prowess, without compromising the performance on non-mathematical tasks. Our work serves as a preliminary exploration into the arithmetic calculation abilities inherent in LLMs, laying a solid foundation to reveal more intricate mathematical tasks.

cs.CL↗

arXiv2024

Optimizing OOD Detection in Molecular Graphs: A Novel Approach with Diffusion Models

The open-world test dataset is often mixed with out-of-distribution (OOD) samples, where the deployed models will struggle to make accurate predictions. Traditional detection methods need to trade off OOD detection and in-distribution (ID) classification performance since they share the same representation learning model. In this work, we propose to detect OOD molecules by adopting an auxiliary diffusion model-based framework, which compares similarities between input molecules and reconstructed graphs. Due to the generative bias towards reconstructing ID training samples, the similarity scores of OOD molecules will be much lower to facilitate detection. Although it is conceptually simple, extending this vanilla framework to practical detection applications is still limited by two significant challenges. First, the popular similarity metrics based on Euclidian distance fail to consider the complex graph structure. Second, the generative model involving iterative denoising steps is time-consuming especially when it runs on the enormous pool of drugs. To address these challenges, our research pioneers an approach of Prototypical Graph Reconstruction for Molecular OOD Detection, dubbed as PGR-MOOD and hinges on three innovations: i) An effective metric to comprehensively quantify the matching degree of input and reconstructed molecules; ii) A creative graph generator to construct prototypical graphs that are in line with ID but away from OOD; iii) An efficient and scalable OOD detector to compare the similarity between test samples and pre-constructed prototypical graphs and omit the generative process on every new molecule. Extensive experiments on ten benchmark datasets and six baselines are conducted to demonstrate our superiority.

cs.LG↗

arXiv2023

New vision of convection induced freckle formation theory in Nickel-based superalloys by electron microscopy

Freckles, one of the common defects in blades used in heavy duty gas turbines, hugely deteriorates blades mechanical properties and liability under service conditions. Thermal-solutal convection theory is a widely adopted formation mechanism but few solid experimental evidences were reported. Here for the first time we systematically studied the microstructure of 117 grains in freckle chains from four different Nickel-based superalloys of either single crystal or directionally solidified alloys. The relationship between the internal stress and the misorientation throughout the freckle chains is studied by means of state-of-the-art electron microscopy. All results give new experimental proof to the theory of thermal-solutal convection, which is further supported by the fact that borides at the boundary are randomly orientated to alloys. Our results enrich the methodology of freckle study, providing a new sight of the formation mechanism of casting defects.

cond-mat.mtrl-sci↗

arXiv2023

Increasing Electric Vehicles Utilization in Transit Fleets using Learning, Predictions, Optimization, and Automation

This work presents a novel hierarchical approach to increase Battery Electric Buses (BEBs) utilization in transit fleets. The proposed approach relies on three key components. A learning-based BEB digital twin cloud platform is used to accurately predict BEB charge consumption on a per vehicle, per driver, and per route basis, and accurately predict the time-to-charge BEB batteries to any level. These predictions are then used by a Predictive Block Assignment module to maximize the BEB fleet utilization. This module computes the optimal BEB daily assignment and charge management strategy. A Depot Parking and Charging Queue Management module is used to autonomously park and charge the vehicles based on their charging demands. The paper discusses the technical approach and benefits of each level in architecture and concludes with a realistic simulations study. The study shows that if our approach is employed, BEB fleet utilization can increase by 50% compared to state-of-the-art methods.

eess.SY↗

arXiv2023

Reinforcement Learning and Distributed Model Predictive Control for Conflict Resolution in Highly Constrained Spaces

This work presents a distributed algorithm for resolving cooperative multi-vehicle conflicts in highly constrained spaces. By formulating the conflict resolution problem as a Multi-Agent Reinforcement Learning (RL) problem, we can train a policy offline to drive the vehicles towards their destinations safely and efficiently in a simplified discrete environment. During the online execution, each vehicle first simulates the interaction among vehicles with the trained policy to obtain its strategy, which is used to guide the computation of a reference trajectory. A distributed Model Predictive Controller (MPC) is then proposed to track the reference while avoiding collisions. The preliminary results show that the combination of RL and distributed MPC has the potential to guide vehicles to resolve conflicts safely and smoothly while being less computationally demanding than the centralized approach.

cs.RO↗

arXiv2023

ParkPredict+: Multimodal Intent and Motion Prediction for Vehicles in Parking Lots with CNN and Transformer

The problem of multimodal intent and trajectory prediction for human-driven vehicles in parking lots is addressed in this paper. Using models designed with CNN and Transformer networks, we extract temporal-spatial and contextual information from trajectory history and local bird's eye view (BEV) semantic images, and generate predictions about intent distribution and future trajectory sequences. Our methods outperform existing models in accuracy, while allowing an arbitrary number of modes, encoding complex multi-agent scenarios, and adapting to different parking maps. To train and evaluate our method, we present the first public 4K video dataset of human driving in parking lots with accurate annotation, high frame rate, and rich traffic scenarios.

cs.CV↗

arXiv2022

Harder-Narasimhan strata and $p$-adic period domains

We revisit the Harder-Narasimhan stratification on a minuscule $p$-adic flag variety, by the theory of modifications of $G$-bundles on the Fargues-Fontaine curve. We compare the Harder-Narasimhan strata with the Newton strata introduced by Caraiani-Scholze. As a consequence, we get further equivalent conditions in terms of $p$-adic Hodge-Tate period domains for fully Hodge-Newton decomposable pairs. Moreover, we generalize these results to arbitrary cocharacters case by considering the associated $B_{dR}^+$-affine Schubert varieties. Applying Hodge-Tate period maps, our constructions give applications to $p$-adic geometry of Shimura varieties and their local analogues.

math.AG↗

arXiv2022

Multi-vehicle Conflict Resolution in Highly Constrained Spaces by Merging Optimal Control and Reinforcement Learning

We present a novel method to address the problem of multi-vehicle conflict resolution in highly constrained spaces. An optimal control problem is formulated to incorporate nonlinear, non-holonomic vehicle dynamics and exact collision avoidance constraints. A solution to the problem can be obtained by first learning configuration strategies with reinforcement learning (RL) in a simplified discrete environment, and then using these strategies to shape the constraint space of the original problem. Simulation results show that our method can explore efficient actions to resolve conflicts in confined space and generate dexterous maneuvers that are both collision-free and kinematically feasible.

cs.RO↗

arXiv2022

Meta Clustering Learning for Large-scale Unsupervised Person Re-identification

Unsupervised Person Re-identification (U-ReID) with pseudo labeling recently reaches a competitive performance compared to fully-supervised ReID methods based on modern clustering algorithms. However, such clustering-based scheme becomes computationally prohibitive for large-scale datasets. How to efficiently leverage endless unlabeled data with limited computing resources for better U-ReID is under-explored. In this paper, we make the first attempt to the large-scale U-ReID and propose a "small data for big task" paradigm dubbed Meta Clustering Learning (MCL). MCL only pseudo-labels a subset of the entire unlabeled data via clustering to save computing for the first-phase training. After that, the learned cluster centroids, termed as meta-prototypes in our MCL, are regarded as a proxy annotator to softly annotate the rest unlabeled data for further polishing the model. To alleviate the potential noisy labeling issue in the polishment phase, we enforce two well-designed loss constraints to promise intra-identity consistency and inter-identity strong correlation. For multiple widely-used U-ReID benchmarks, our method significantly saves computational cost while achieving a comparable or even better performance compared to prior works.

cs.CV↗