arXiv subjects

Haocheng Xu

Publications and source records attributed to Haocheng Xu.

14 recordsLinked to original sources

arXiv2026

LowRank-SSM: Hardware-Software Co-Design for Rank-Reduced Mamba Acceleration on FPGA

State Space Models(SSMs) such as Mamba and Mamba-2 achieve linear-time autoregressive inference, making them attractive for latency-sensitive and resource-constrained deployment. Yet their large input and output projection layers impose quadratic weight memory and off-chip bandwidth costs that bottleneck practical FPGA deployment, accounting for over 60% per-token runtime at sequence lengths of 1,024 and beyond. Existing accelerators reduce this overhead through quantization or activation sparsity, but none treat projection rank as an explicit hardware design variable, leaving a systematic accuracy-throughput trade-off unexplored. We present LowRank-SSM, a hardware-software co-design framework that closes this gap. On the software side, we decompose the input and output projection weights via post-training truncated SVD and introduce a greedy bandwise rank-allocation algorithm that searches for the per-band rank vector that minimizes weight storage while respecting a user-specified accuracy constraint. On the hardware side, we map the resulting factored projections onto a fully-pipelined accelerator on an FPGA, featuring a dual-path projection(low-rank path and full-rank path), a fused selective-scan unit, and five independent AXI master bundles that saturate DDR4 bandwidth without bus contention. A per-band runtime rank mask enables mixed-rank execution across all 64 layers with zero architectural overhead. On Xilinx Versal VC1902 at 400 MHz, the deployed mixed-rank INT8 design achieves 7.89~tokens/s, representing a ${2.19\times}$ throughput improvement and ${2.03\times}$ energy-efficiency improvement over SOTA at comparable power and accuracy.

cs.AR↗

arXiv2026

Characterizing State Space Model and Hybrid Language Model Performance with Long Context

Emerging applications such as AR are driving demands for machine intelligence capable of processing continuous and/or long-context inputs on local devices. However, currently dominant models based on Transformer architecture suffers from the quadratic computational and memory overhead, which hinders applications required to process long contexts. This has spurred a paradigm shift towards new architectures like State Space Models (SSMs) and SSM-Transformer hybrid models, which provide near-linear scaling. The near-linear scaling enabled efficient handling of millions of tokens while delivering high performance in recent studies. Although such works present promising results, their workload characteristics in terms of computational performance and hardware resource requirements are not yet thoroughly explored, which limits our understanding of their implications to the system level optimizations. To address this gap, we present a comprehensive, compara-ive benchmarking of carefully selected Transformers, SSMs, and hybrid models specifically for long-context inference on consumer and embedded GPUs. Our analysis shows that SSMs are well-suited for on-device AI on consumer and embedded GPUs for long context inferences. While Transformers are up to 1.9x faster at short sequences (<8K tokens), SSMs demonstrate a dramatic performance inversion, becoming up to 4x faster at very long contexts (~57K tokens), thanks to their linear computational complexity and ~64% reduced memory footrprint. Our operator-level analysis reveals that custom SSM kernels like selective scan despite being hardware-aware to minimize memory IO, dominate the inference runtime on edge platforms, accounting for over 55% of latency due to their sequential, element-wise nature. SSM-Scope is open-sourced at https://github.com/sapmitra/ssm-scope

cs.AR↗

arXiv2025

Rethinking RoPE Scaling in Quantized LLM: Theory, Outlier, and Channel-Band Analysis with Weight Rescaling

Extending the context window support of large language models (LLMs) is crucial for tasks with long-distance dependencies. RoPE-based interpolation and extrapolation methods, such as linear scaling and frequency-aware schemes, enable longer input length support without retraining, while post-training quantization (PTQ) makes deployment practical. However, we show that combining RoPE position interpolation (PI) with PTQ degrades accuracy due to coupled effects including long-context aliasing, dynamic-range dilation, anisotropy from axis-aligned quantizers vs. rotated RoPE pairs, and outlier shifting that produces position-dependent logit noise. We provide, to the best of our knowledge, the first systematic analysis of the PI+PTQ approach and introduce two practical diagnostics: interpolation pressure (per-band sensitivity to phase scaling) and tail-inflation ratios (outlier shift from short to long contexts). Following the analysis results, we propose Q-ROAR (Quantization, RoPE-interpolation, and Outlier Aware Rescaling), a weight-only, interpolation-aware stabilization of PI for quantized LLMs. Q-ROAR groups RoPE dimensions into a small number of frequency bands and performs a lightweight search over per-band scales for Key and Query weights (with an optional symmetric variant to preserve logit scale). The search is guided by our diagnostics and uses a tiny long-context development dataset, requiring no fine-tuning to the model, no architecture or kernel changes, and no additional deployment overhead. Empirically, Q-ROAR reduces the model's perplexity on long-context workloads by more than 14%, while preserving short-context performance, inference throughput, and compatibility with existing LLM system stacks.

cs.LG↗

arXiv2025

TOP: Time Optimization Policy for Stable and Accurate Standing Manipulation with Humanoid Robots

Humanoid robots have the potential capability to perform a diverse range of manipulation tasks, but this is based on a robust and precise standing controller. Existing methods are either ill-suited to precisely control high-dimensional upper-body joints, or difficult to ensure both robustness and accuracy, especially when upper-body motions are fast. This paper proposes a novel time optimization policy (TOP), to train a standing manipulation control model that ensures balance, precision, and time efficiency simultaneously, with the idea of adjusting the time trajectory of upper-body motions but not only strengthening the disturbance resistance of the lower-body. Our approach consists of three parts. Firstly, we utilize motion prior to represent upper-body motions to enhance the coordination ability between the upper and lower-body by training a variational autoencoder (VAE). Then we decouple the whole-body control into an upper-body PD controller for precision and a lower-body RL controller to enhance robust stability. Finally, we train TOP method in conjunction with the decoupled controller and VAE to reduce the balance burden resulting from fast upper-body motions that would destabilize the robot and exceed the capabilities of the lower-body RL policy. The effectiveness of the proposed approach is evaluated via both simulation and real world experiments, which demonstrate the superiority on standing manipulation tasks stably and accurately. The project page can be found at https://anonymous.4open.science/w/top-258F/.

cs.RO↗

arXiv2025

A Whole-Body Motion Imitation Framework from Human Data for Full-Size Humanoid Robot

Motion imitation is a pivotal and effective approach for humanoid robots to achieve a more diverse range of complex and expressive movements, making their performances more human-like. However, the significant differences in kinematics and dynamics between humanoid robots and humans present a major challenge in accurately imitating motion while maintaining balance. In this paper, we propose a novel whole-body motion imitation framework for a full-size humanoid robot. The proposed method employs contact-aware whole-body motion retargeting to mimic human motion and provide initial values for reference trajectories, and the non-linear centroidal model predictive controller ensures the motion accuracy while maintaining balance and overcoming external disturbances in real time. The assistance of the whole-body controller allows for more precise torque control. Experiments have been conducted to imitate a variety of human motions both in simulation and in a real-world humanoid robot. These experiments demonstrate the capability of performing with accuracy and adaptability, which validates the effectiveness of our approach.

cs.RO↗

arXiv2025

EMP: Executable Motion Prior for Humanoid Robot Standing Upper-body Motion Imitation

To support humanoid robots in performing manipulation tasks, it is essential to study stable standing while accommodating upper-body motions. However, the limited controllable range of humanoid robots in a standing position affects the stability of the entire body. Thus we introduce a reinforcement learning based framework for humanoid robots to imitate human upper-body motions while maintaining overall stability. Our approach begins with designing a retargeting network that generates a large-scale upper-body motion dataset for training the reinforcement learning (RL) policy, which enables the humanoid robot to track upper-body motion targets, employing domain randomization for enhanced robustness. To avoid exceeding the robot's execution capability and ensure safety and stability, we propose an Executable Motion Prior (EMP) module, which adjusts the input target movements based on the robot's current state. This adjustment improves standing stability while minimizing changes to motion amplitude. We evaluate our framework through simulation and real-world tests, demonstrating its practical applicability.

cs.RO↗

arXiv2025

TG-NAS: Generalizable Zero-Cost Proxies with Operator Description Embedding and Graph Learning for Efficient Neural Architecture Search

Neural Architecture Search (NAS) is a powerful technique for discovering high-performing CNN architectures, but most existing methods rely on costly training or extensive sampling. Zero-shot NAS offers a training-free alternative by using proxies to predict architecture performance. However, existing proxies are often suboptimal -- frequently outperformed by simple metrics like parameter count or FLOPs -- and they generalize poorly across different search spaces. Moreover, current model-based proxies struggle to adapt to new operators without access to ground-truth accuracy, limiting their transferability. We propose TG-NAS, a universal, model-based zero-cost (ZC) proxy that combines a Transformer-based operator embedding generator with a Graph Convolutional Network (GCN) to predict architecture performance. Unlike prior model-based predictors, TG-NAS requires no retraining and generalizes across arbitrary search spaces. It serves as a standalone ZC proxy with strong data efficiency, robustness, and cross-space consistency. Extensive evaluations across diverse NAS benchmarks demonstrate TG-NAS's superior rank correlation and generalizability compared to existing proxies. Additionally, it improves search efficiency by up to 300x and discovers architectures achieving 93.75% CIFAR-10 accuracy on NAS-Bench-201 and 74.9% ImageNet top-1 accuracy on the DARTS space, establishing TG-NAS as a promising foundation for efficient, generalizable NAS.

cs.LG↗

arXiv2025

RSEND: Retinex-based Squeeze and Excitation Network with Dark Region Detection for Efficient Low Light Image Enhancement

Images captured under low-light scenarios often suffer from low quality. Previous CNN-based deep learning methods often involve using Retinex theory. Nevertheless, most of them cannot perform well in more complicated datasets like LOL-v2 while consuming too much computational resources. Besides, some of these methods require sophisticated training at different stages, making the procedure even more time-consuming and tedious. In this paper, we propose a more accurate, concise, and one-stage Retinex theory based framework, RSEND. RSEND first divides the low-light image into the illumination map and reflectance map, then captures the important details in the illumination map and performs light enhancement. After this step, it refines the enhanced gray-scale image and does element-wise matrix multiplication with the reflectance map. By denoising the output it has from the previous step, it obtains the final result. In all the steps, RSEND utilizes Squeeze and Excitation network to better capture the details. Comprehensive quantitative and qualitative experiments show that our Efficient Retinex model significantly outperforms other CNN-based models, achieving a PSNR improvement ranging from 0.44 dB to 4.2 dB in different datasets and even outperforms transformer-based models in the LOL-v2-real dataset.

cs.CV↗

arXiv2024

Optimizing High-Level Synthesis Designs with Retrieval-Augmented Large Language Models

High-level synthesis (HLS) allows hardware designers to create hardware designs with high-level programming languages like C/C++/OpenCL, which greatly improves hardware design productivity. However, existing HLS flows require programmers' hardware design expertise and rely on programmers' manual code transformations and directive annotations to guide compiler optimizations. Optimizing HLS designs requires non-trivial HLS expertise and tedious iterative process in HLS code optimization. Automating HLS code optimizations has become a burning need. Recently, large language models (LLMs) trained on massive code and programming tasks have demonstrated remarkable proficiency in comprehending code, showing the ability to handle domain-specific programming queries directly without labor-intensive fine-tuning. In this work, we propose a novel retrieval-augmented LLM-based approach to effectively optimize high-level synthesis (HLS) programs. Our proposed method leverages few-shot learning, enabling large language models to adopt domain-specific knowledge through natural language prompts. We propose a unique framework, Retrieve Augmented Large Language Model Aided Design (RALAD), designed to enhance LLMs' performance in HLS code optimization tasks. RALAD employs advanced embedding techniques and top-\emph{k} search algorithms to dynamically source relevant knowledge from extensive databases, thereby providing contextually appropriate responses to complex programming queries. Our implementation of RALAD on two specialized domains, utilizing comparatively smaller language models, achieves an impressive 80\% success rate in compilation tasks and outperforms general LLMs by 3.7 -- 19$\times$ in latency improvement.

cs.AR↗

arXiv2024

Optimized Spatial Architecture Mapping Flow for Transformer Accelerators

Recent innovations in Transformer-based large language models have significantly advanced the field of general-purpose neural language understanding and generation. With billions of trainable parameters, deployment of these large models relies on high-performance hardware accelerators to efficiently deliver the required computation. Spatial architectures, such as TPUs, offer a promising solution to accelerating computation-intensive workloads. However, the design process for existing spatial architectures is predominantly manual, and it often involves time-consuming redesigns for new applications and new problem dimensions, which greatly limits the development of optimally designed accelerators for Transformer models. To address these challenges, we propose SAMT (Spatial Architecture Mapping for Transformers), a comprehensive framework designed to optimize the dataflow mapping of Transformer inference workloads onto spatial accelerators. We demonstrate the effectiveness of SAMT in improving the performance of spatial accelerators for Transformer models. We propose and leverage the dynamic operator fusion schemes for the Transformer models and co-search the optimal dataflow mapping strategies for spatial accelerators. SAMT significantly reduces inference latency by 12% to 91% and energy consumption by 3% to 23% for evaluated Transformer models compared to traditional spatial accelerator designs among edge, mobile and cloud settings.

cs.AR↗

arXiv2024

MONAS: Efficient Zero-Shot Neural Architecture Search for MCUs

Neural Architecture Search (NAS) has proven effective in discovering new Convolutional Neural Network (CNN) architectures, particularly for scenarios with well-defined accuracy optimization goals. However, previous approaches often involve time-consuming training on super networks or intensive architecture sampling and evaluations. Although various zero-cost proxies correlated with CNN model accuracy have been proposed for efficient architecture search without training, their lack of hardware consideration makes it challenging to target highly resource-constrained edge devices such as microcontroller units (MCUs). To address these challenges, we introduce MONAS, a novel hardware-aware zero-shot NAS framework specifically designed for MCUs in edge computing. MONAS incorporates hardware optimality considerations into the search process through our proposed MCU hardware latency estimation model. By combining this with specialized performance indicators (proxies), MONAS identifies optimal neural architectures without incurring heavy training and evaluation costs, optimizing for both hardware latency and accuracy under resource constraints. MONAS achieves up to a 1104x improvement in search efficiency over previous work targeting MCUs and can discover CNN models with over 3.23x faster inference on MCUs while maintaining similar accuracy compared to more general NAS approaches.

cs.LG↗

arXiv2024

Semantics-aware Motion Retargeting with Vision-Language Models

Capturing and preserving motion semantics is essential to motion retargeting between animation characters. However, most of the previous works neglect the semantic information or rely on human-designed joint-level representations. Here, we present a novel Semantics-aware Motion reTargeting (SMT) method with the advantage of vision-language models to extract and maintain meaningful motion semantics. We utilize a differentiable module to render 3D motions. Then the high-level motion semantics are incorporated into the motion retargeting process by feeding the vision-language model with the rendered images and aligning the extracted semantic embeddings. To ensure the preservation of fine-grained motion details and high-level semantics, we adopt a two-stage pipeline consisting of skeleton-aware pre-training and fine-tuning with semantics and geometry constraints. Experimental results show the effectiveness of the proposed method in producing high-quality motion retargeting results while accurately preserving motion semantics.

cs.CV↗

arXiv2024

MicroNAS: Zero-Shot Neural Architecture Search for MCUs

Neural Architecture Search (NAS) effectively discovers new Convolutional Neural Network (CNN) architectures, particularly for accuracy optimization. However, prior approaches often require resource-intensive training on super networks or extensive architecture evaluations, limiting practical applications. To address these challenges, we propose MicroNAS, a hardware-aware zero-shot NAS framework designed for microcontroller units (MCUs) in edge computing. MicroNAS considers target hardware optimality during the search, utilizing specialized performance indicators to identify optimal neural architectures without high computational costs. Compared to previous works, MicroNAS achieves up to 1104x improvement in search efficiency and discovers models with over 3.23x faster MCU inference while maintaining similar accuracy

cs.LG↗

arXiv2022

CEPC Cost Model Study and Circumference Optimization

The CEPC is a proposed high luminosity Higgs/Z factory, with the potential to be upgraded to top factory at center-of-mass energy of 360GeV. We perform an optimization study on the circumference of CEPC. We calculate the instant luminosity, the construction and operation cost for different circumferences. With respect to the total cost and average cost per particle, we conclude that the optimal circumference for the CEPC Higgs operation is 80 km. Taking into account of the Z pole operation, the potential high-energy upgrade of CEPC (top factory), the optimal circumference increased to 100 km. The long future proton-proton upgrade of CEPC (SPPC) also favors a larger circumference, and we conclude that 100 km is the global optimized circumference for this facility.

physics.acc-ph↗