arXiv subjects

Hong Xu

Publications and source records attributed to Hong Xu.

At least 55 records · Page 3Linked to original sources

arXiv2025

A Learn-to-Optimize Approach for Coordinate-Wise Step Sizes for Quasi-Newton Methods

Tuning step sizes is crucial for the stability and efficiency of optimization algorithms. While adaptive coordinate-wise step sizes have been shown to outperform scalar step size in first-order methods, their use in second-order methods is still under-explored and more challenging. Current approaches, including hypergradient descent and cutting plane methods, offer limited improvements or encounter difficulties in second-order contexts. To address these limitations, we first conduct a theoretical analysis within the Broyden-Fletcher-Goldfarb-Shanno (BFGS) framework, a prominent quasi-Newton method, and derive sufficient conditions for coordinate-wise step sizes that ensure convergence and stability. Building on this theoretical foundation, we introduce a novel learn-to-optimize (L2O) method that employs LSTM-based networks to learn optimal step sizes by leveraging insights from past optimization trajectories, while inherently respecting the derived theoretical guarantees. Extensive experiments demonstrate that our approach achieves substantial improvements over scalar step size methods and hypergradient descent-based method, offering up to 4$\times$ faster convergence across diverse optimization tasks.

cs.LG↗

arXiv2025

Easz: An Agile Transformer-based Image Compression Framework for Resource-constrained IoTs

Neural image compression, necessary in various machine-to-machine communication scenarios, suffers from its heavy encode-decode structures and inflexibility in switching between different compression levels. Consequently, it raises significant challenges in applying the neural image compression to edge devices that are developed for powerful servers with high computational and storage capacities. We take a step to solve the challenges by proposing a new transformer-based edge-compute-free image coding framework called Easz. Easz shifts the computational overhead to the server, and hence avoids the heavy encoding and model switching overhead on the edge. Easz utilizes a patch-erase algorithm to selectively remove image contents using a conditional uniform-based sampler. The erased pixels are reconstructed on the receiver side through a transformer-based framework. To further reduce the computational overhead on the receiver, we then introduce a lightweight transformer-based reconstruction structure to reduce the reconstruction load on the receiver side. Extensive evaluations conducted on a real-world testbed demonstrate multiple advantages of Easz over existing compression approaches, in terms of adaptability to different compression levels, computational efficiency, and image reconstruction quality.

eess.IV↗

arXiv2025

Teola: Towards End-to-End Optimization of LLM-based Applications

Large language model (LLM)-based applications consist of both LLM and non-LLM components, each contributing to the end-to-end latency. Despite great efforts to optimize LLM inference, end-to-end workflow optimization has been overlooked. Existing frameworks employ coarse-grained orchestration with task modules, which confines optimizations to within each module and yields suboptimal scheduling decisions. We propose fine-grained end-to-end orchestration, which utilizes task primitives as the basic units and represents each query's workflow as a primitive-level dataflow graph. This explicitly exposes a much larger design space, enables optimizations in parallelization and pipelining across primitives of different modules, and enhances scheduling to improve application-level performance. We build Teola, a novel orchestration framework for LLM-based applications that implements this scheme. Comprehensive experiments show that Teola can achieve up to 2.09x speedup over existing systems across various popular LLM applications. The code is available at https://github.com/NetX-lab/Ayo.

cs.DC↗

arXiv2025

MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks

Large Language Models (LLMs) have showcased impressive capabilities in handling straightforward programming tasks. However, their performance tends to falter when confronted with more challenging programming problems. We observe that conventional models often generate solutions as monolithic code blocks, restricting their effectiveness in tackling intricate questions. To overcome this limitation, we present Module-of-Thought Coder (MoTCoder). We introduce a framework for MoT instruction tuning, designed to promote the decomposition of tasks into logical sub-tasks and sub-modules. Our investigations reveal that, through the cultivation and utilization of sub-modules, MoTCoder significantly improves both the modularity and correctness of the generated solutions, leading to substantial pass@1 improvements of 5.9% on APPS and 5.8% on CodeContests. MoTCoder also achieved significant improvements in self-correction capabilities, surpassing the current SOTA by 3.3%. Additionally, we provide an analysis of between problem complexity and optimal module decomposition and evaluate the maintainability index, confirming that the code generated by MoTCoder is easier to understand and modify, which can be beneficial for long-term code maintenance and evolution. Our codes are available at https://github.com/dvlab-research/MoTCoder.

cs.LG↗

arXiv2025

DSV: Exploiting Dynamic Sparsity to Accelerate Large-Scale Video DiT Training

Diffusion Transformers (DiTs) have shown remarkable performance in generating high-quality videos. However, the quadratic complexity of 3D full attention remains a bottleneck in scaling DiT training, especially with high-definition, lengthy videos, where it can consume up to 95% of processing time and demand specialized context parallelism. This paper introduces DSV to accelerate video DiT training by leveraging the dynamic attention sparsity we empirically observe. DSV uses a two-stage algorithm to capture the dynamic sparsity patterns via low-rank based approximation of the original query and key. It employs custom kernels to efficiently identify critical key-value pairs and compute the sparse attention. To accommodate the new sparsity dimension, DSV adopts a hybrid sparsity-aware context parallelism that re-balances the skewed workload across attention heads and blocks due to sparsity heterogeneity. DSV achieves up to 3.02x higher training throughput, scaling to 128 GPUs and 520k token lengths, without quality loss.

cs.DC↗

arXiv2025

Performance Prediction of On-NIC Network Functions with Multi-Resource Contention and Traffic Awareness

Network function (NF) offloading on SmartNICs has been widely used in modern data centers, offering benefits in host resource saving and programmability. Co-running NFs on the same SmartNICs can cause performance interference due to contention of onboard resources. To meet performance SLAs while ensuring efficient resource management, operators need mechanisms to predict NF performance under such contention. However, existing solutions lack SmartNIC-specific knowledge and exhibit limited traffic awareness, leading to poor accuracy for on-NIC NFs. This paper proposes Yala, a novel performance predictive system for on-NIC NFs. Yala builds upon the key observation that co-located NFs contend for multiple resources, including onboard accelerators and the memory subsystem. It also facilitates traffic awareness according to the behaviors of individual resources to maintain accuracy as the external traffic attributes vary. Evaluation using BlueField-2 SmartNICs shows that Yala improves the prediction accuracy by 78.8% and reduces SLA violations by 92.2% compared to state-of-the-art approaches, and enables new practical usecases.

cs.NI↗

arXiv2024

Echo: Simulating Distributed Training At Scale

Simulation offers unique values for both enumeration and extrapolation purposes, and is becoming increasingly important for managing the massive machine learning (ML) clusters and large-scale distributed training jobs. In this paper, we build Echo to tackle three key challenges in large-scale training simulation: (1) tracing the runtime training workloads at each device in an ex-situ fashion so we can use a single device to obtain the actual execution graphs of 1K-GPU training, (2) accurately estimating the collective communication without high overheads of discrete-event based network simulation, and (3) accounting for the interference-induced computation slowdown from overlapping communication and computation kernels on the same device. Echo delivers on average 8% error in training step -- roughly 3x lower than state-of-the-art simulators -- for GPT-175B on a 96-GPU H800 cluster with 3D parallelism on Megatron-LM under 2 minutes.

cs.LG↗

arXiv2024

Optimization-Driven Statistical Models of Anatomies using Radial Basis Function Shape Representation

Particle-based shape modeling (PSM) is a popular approach to automatically quantify shape variability in populations of anatomies. The PSM family of methods employs optimization to automatically populate a dense set of corresponding particles (as pseudo landmarks) on 3D surfaces to allow subsequent shape analysis. A recent deep learning approach leverages implicit radial basis function representations of shapes to better adapt to the underlying complex geometry of anatomies. Here, we propose an adaptation of this method using a traditional optimization approach that allows more precise control over the desired characteristics of models by leveraging both an eigenshape and a correspondence loss. Furthermore, the proposed approach avoids using a black-box model and allows more freedom for particles to navigate the underlying surfaces, yielding more informative statistical models. We demonstrate the efficacy of the proposed approach to state-of-the-art methods on two real datasets and justify our choice of losses empirically.

cs.CV↗

arXiv2024

Lightweight holographic near-eye display system with self-charging capability using solar energy

Near-eye display plays an important role in emerging spatial computing systems, providing a distinctive visual effect of virtual-real fusion. However, its application for all-day wear is greatly limited by the bulky structure, energy expenditure, and continuous battery heating. Here, we propose a lightweight holographic near-eye display system that takes advantage of solar energy for self-charging. To achieve the collection of solar energy and near-eye display without crosstalk, holographic optical elements (HOE) are used to diffract sunlight and signal light into a common waveguide. Then, small-area solar cells convert the collected solar energy and power the system. Compact power supply components replace heavy batteries, contributing to the lightweight design. The simple acquisition of solar energy provides the system with sustainable self-charging capability. We believe that the lightweight design and continuous energy input solution will significantly promote the popularity of near-eye display in our daily lives.

physics.optics↗

arXiv2024

BlockLLM: Multi-tenant Finer-grained Serving for Large Language Models

The increasing demand for Large Language Models (LLMs) across various applications has led to a significant shift in the design of deep learning serving systems. Deploying LLMs, particularly in multi-tenant environments, poses substantial challenges due to their high computational and memory demands. We introduce BlockLLM, a serving system that leverages component sharing among fine-tuned LLM models to provide an efficient and flexible solution for LLM workloads. BlockLLM partitions models into finer-grained blocks, enabling the reuse of model components and independent provisioning to improve computation efficiency. BlockLLM comprises an offline block zoo for storing blocks and an online system to serve requests through chains of blocks. It offers multi-fold flexibilities: (1) Adaptive assembly of blocks on-the-fly through equivalence evaluation among blocks in the zoo; (2) Per-block batch size configuration and best-effort KV cache coordination at the individual block level; (3) Speculative execution and locality-aware block placement to reduce communication costs from dynamic block resource allocation. Our evaluation shows that BlockLLM reduces memory and storage footprints and improves computational efficiency, outperforming existing serving approach in 95%ile latency and GPU utilization by 33.5% and 20.1%, respectively, with minimal impact on accuracy

cs.DC↗

arXiv2024

RTLRewriter: Methodologies for Large Models aided RTL Code Optimization

Register Transfer Level (RTL) code optimization is crucial for enhancing the efficiency and performance of digital circuits during early synthesis stages. Currently, optimization relies heavily on manual efforts by skilled engineers, often requiring multiple iterations based on synthesis feedback. In contrast, existing compiler-based methods fall short in addressing complex designs. This paper introduces RTLRewriter, an innovative framework that leverages large models to optimize RTL code. A circuit partition pipeline is utilized for fast synthesis and efficient rewriting. A multi-modal program analysis is proposed to incorporate vital visual diagram information as optimization cues. A specialized search engine is designed to identify useful optimization guides, algorithms, and code snippets that enhance the model ability to generate optimized RTL. Additionally, we introduce a Cost-aware Monte Carlo Tree Search (C-MCTS) algorithm for efficient rewriting, managing diverse retrieved contents and steering the rewriting results. Furthermore, a fast verification pipeline is proposed to reduce verification cost. To cater to the needs of both industry and academia, we propose two benchmarking suites: the Large Rewriter Benchmark, targeting complex scenarios with extensive circuit partitioning, optimization trade-offs, and verification challenges, and the Small Rewriter Benchmark, designed for a wider range of scenarios and patterns. Our comparative analysis with established compilers such as Yosys and E-graph demonstrates significant improvements, highlighting the benefits of integrating large models into the early stages of circuit design. We provide our benchmarks at https://github.com/yaoxufeng/RTLRewriter-Bench.

cs.AR↗

arXiv2024

QuickLLaMA: Query-aware Inference Acceleration for Large Language Models

The capacity of Large Language Models (LLMs) to comprehend and reason over long contexts is pivotal for advancements in diverse fields. Yet, they still stuggle with capturing long-distance dependencies within sequences to deeply understand semantics. To address this issue, we introduce Query-aware Inference for LLMs (Q-LLM), a system designed to process extensive sequences akin to human cognition. By focusing on memory data relevant to a given query, Q-LLM can accurately capture pertinent information within a fixed window size and provide precise answers to queries. It doesn't require extra training and can be seamlessly integrated with any LLMs. Q-LLM using LLaMA3 (QuickLLaMA) can read Harry Potter within 30s and accurately answer the questions. On widely recognized benchmarks, Q-LLM improved by 7.17% compared to the current state-of-the-art on LLaMA3, and by 3.26% on Mistral on the $\infty$-bench. In the Needle-in-a-Haystack and BABILong task, Q-LLM improved upon the current SOTA by 7.0% and 6.1%. Our code can be found in https://github.com/dvlab-research/Q-LLM.

cs.LG↗

arXiv2024

Design and Construction of a Test-Stand for the Split and Delay Line at the European XFEL

This work presents the design and construction of a test-stand for the Split and Delay Line (SDL) at the European X-ray Free Electron Laser (XFEL) in Hamburg, Germany. The advancements in Free Electron Laser technology have now made it possible to investigate ultra-fast dynamics in materials science, biology, chemistry, etc. In the SDL, an incident free electron laser pulse is split into two parts by a beam splitter: one half travels along the upper branch, and the other half travels along the lower branch. These two pulses can either merge again in the collinear mode or travel along different optical paths toward the sample in the inclined mode. This setup achieves a temporal separation of a few femtoseconds between the X-ray pulse pairs, which is crucial for ultra-fast X-ray pump-probe experiments investigating rapid dynamics. This report provides detailed documentation of the mechanical and electronic configuration of the test-stand, vacuum testing, the manufacturing of supporting cables, and the challenges encountered during the project. Finally, the SDL was successfully assembled and initially validated under ultra-high vacuum (UHV) operating conditions.

physics.acc-ph↗

arXiv2024

Meili: Enabling SmartNIC as a Service in the Cloud

SmartNICs are touted as an attractive substrate for network application offloading, offering benefits in programmability, host resource saving, and energy efficiency. The current usage restricts offloading to local hosts and confines SmartNIC ownership to individual application teams, resulting in poor resource efficiency and scalability. This paper presents Meili, a novel system that realizes SmartNIC as a service to address these issues. Meili organizes heterogeneous SmartNIC resources as a pool and offers a unified one-NIC abstraction to application developers. This allows developers to focus solely on the application logic while dynamically optimizing their performance needs. Our evaluation on NVIDIA BlueField series and AMD Pensando SmartNICs demonstrates that Meili achieves scalable single-flow throughput with a maximum 8 μs latency overhead and enhances resource efficiency by 3.07$\times$ compared to standalone deployments and 1.44$\times$ compared to state-of-the-art microservice deployments.

cs.NI↗

arXiv2024

RoboCoder: Robotic Learning from Basic Skills to General Tasks with Large Language Models

The emergence of Large Language Models (LLMs) has improved the prospects for robotic tasks. However, existing benchmarks are still limited to single tasks with limited generalization capabilities. In this work, we introduce a comprehensive benchmark and an autonomous learning framework, RoboCoder aimed at enhancing the generalization capabilities of robots in complex environments. Unlike traditional methods that focus on single-task learning, our research emphasizes the development of a general-purpose robotic coding algorithm that enables robots to leverage basic skills to tackle increasingly complex tasks. The newly proposed benchmark consists of 80 manually designed tasks across 7 distinct entities, testing the models' ability to learn from minimal initial mastery. Initial testing revealed that even advanced models like GPT-4 could only achieve a 47% pass rate in three-shot scenarios with humanoid entities. To address these limitations, the RoboCoder framework integrates Large Language Models (LLMs) with a dynamic learning system that uses real-time environmental feedback to continuously update and refine action codes. This adaptive method showed a remarkable improvement, achieving a 36% relative improvement. Our codes will be released.

cs.RO↗

arXiv2024

LingML: Linguistic-Informed Machine Learning for Enhanced Fake News Detection

Nowadays, Information spreads at an unprecedented pace in social media and discerning truth from misinformation and fake news has become an acute societal challenge. Machine learning (ML) models have been employed to identify fake news but are far from perfect with challenging problems like limited accuracy, interpretability, and generalizability. In this paper, we enhance ML-based solutions with linguistics input and we propose LingML, linguistic-informed ML, for fake news detection. We conducted an experimental study with a popular dataset on fake news during the pandemic. The experiment results show that our proposed solution is highly effective. There are fewer than two errors out of every ten attempts with only linguistic input used in ML and the knowledge is highly explainable. When linguistics input is integrated with advanced large-scale ML models for natural language processing, our solution outperforms existing ones with 1.8% average error rate. LingML creates a new path with linguistics to push the frontier of effective and efficient fake news detection. It also sheds light on real-world multi-disciplinary applications requiring both ML and domain expertise to achieve optimal performance.

cs.CL↗

arXiv2024

Accelerating Distributed MoE Training and Inference with Lina

Scaling model parameters improves model quality at the price of high computation overhead. Sparsely activated models, usually in the form of Mixture of Experts (MoE) architecture, have sub-linear scaling of computation cost with model size, thus providing opportunities to train and serve a larger model at lower cost than their dense counterparts. However, distributed MoE training and inference is inefficient, mainly due to the interleaved all-to-all communication during model computation. This paper makes two main contributions. First, we systematically analyze all-to-all overhead in distributed MoE and present the main causes for it to be the bottleneck in training and inference, respectively. Second, we design and build Lina to address the all-to-all bottleneck head-on. Lina opportunistically prioritizes all-to-all over the concurrent allreduce whenever feasible using tensor partitioning, so all-to-all and training step time is improved. Lina further exploits the inherent pattern of expert selection to dynamically schedule resources during inference, so that the transfer size and bandwidth of all-to-all across devices are balanced amid the highly skewed expert popularity in practice. Experiments on an A100 GPU testbed show that Lina reduces the training step time by up to 1.73x and reduces the 95%ile inference time by an average of 1.63x over the state-of-the-art systems.

cs.DC↗

arXiv2024

VLPose: Bridging the Domain Gap in Pose Estimation with Language-Vision Tuning

Thanks to advances in deep learning techniques, Human Pose Estimation (HPE) has achieved significant progress in natural scenarios. However, these models perform poorly in artificial scenarios such as painting and sculpture due to the domain gap, constraining the development of virtual reality and augmented reality. With the growth of model size, retraining the whole model on both natural and artificial data is computationally expensive and inefficient. Our research aims to bridge the domain gap between natural and artificial scenarios with efficient tuning strategies. Leveraging the potential of language models, we enhance the adaptability of traditional pose estimation models across diverse scenarios with a novel framework called VLPose. VLPose leverages the synergy between language and vision to extend the generalization and robustness of pose estimation models beyond the traditional domains. Our approach has demonstrated improvements of 2.26% and 3.74% on HumanArt and MSCOCO, respectively, compared to state-of-the-art tuning strategies.

cs.CV↗