Publications (62)
HQ-DM: Single Hadamard Transformation-Based Quantization-Aware Training for Low-Bit Diffusion Models
Shizhuo Mao, Hongtao Zou, Qihu Xie +2
Diffusion models have demonstrated significant applications in the field of image generation. However, their high computational and memory costs pose challenges for deployment. Mod…
Integrated Optimization of Partitioning, Scheduling and Floorplanning for Partially Dynamically Reconfigurable Systems
Song Chen, Jinglei Huang, Xiaodong Xu +1
Confronted with the challenge of high performance for applications and the restriction of hardware resources for field-programmable gate arrays (FPGAs), partial dynamic reconfigura…
Chirality-dependent persistent spin current in single circular helix molecules
Song Chen, Hua-Hua Fu
Since the chiral-induced spin selectivity (CISS) was first observed experimentally, its microscopic mechanism has been continuously explored by the scientific community. Among thes…
Chirality-Induced Majorana Polarization
Song Chen, Hua-Hua Fu
To realize Majorana fermions having novel physical features has been developed as a key while difficult task in topological superconductor. Here we have proposed another platform t…
NicePIM: Design Space Exploration for Processing-In-Memory DNN Accelerators with 3D-Stacked-DRAM
Junpeng Wang, Mengke Ge, Bo Ding +3
With the widespread use of deep neural networks(DNNs) in intelligent systems, DNN accelerators with high performance and energy efficiency are greatly demanded. As one of the feasi…
IOPS: An Unified SpMM Accelerator Based on Inner-Outer-Hybrid Product
Wenhao Sun, Wendi Sun, Song Chen +1
Sparse matrix multiplication (SpMM) is widely applied to numerous domains, such as graph processing, machine learning, and data analytics. However, inner product based SpMM induces…
Fluctuations of differential number counts of radio continuum sources
Song Chen, Dominik J. Schwarz
We investigate the differential number counts of sources in radio continuum surveys, including all terms at linear order in cosmological perturbations. Our framework does not assum…
Accelerated Distributed Aggregative Optimization
Jiaxu Liu, Song Chen, Shengze Cai +1
In this paper, we investigate a distributed aggregative optimization problem in a network, where each agent has its own local cost function which depends not only on the local stat…
Rotated Robustness: A Training-Free Defense against Bit-Flip Attacks on Large Language Models
Deng Liu, Song Chen
Hardware faults, specifically bit-flips in quantized weights, pose a severe reliability threat to Large Language Models (LLMs), often triggering catastrophic model collapses. We de…
Adaptive 3D-IC TSV Fault Tolerance Structure Generation
Song Chen, Qi Xu, Bei Yu
In three dimensional integrated circuits (3D-ICs), through silicon via (TSV) is a critical technique in providing vertical connections. However, the yield and reliability is one of…
The kinematic dipole in galaxy redshift surveys
Roy Maartens, Chris Clarkson, Song Chen
In the concordance model of the Universe, the matter distribution - as observed in galaxy number counts or the intensity of line emission (such as the 21cm line of neutral hydrogen…
A Backstepping Framework for Unconstrained Accelerated Optimization Algorithms
Song Chen, Jiaxu Liu, Chao Xu
This paper introduces a control-theoretic perspective on unconstrained optimization algorithms using the backstepping methods. We model the optimization process as an augmented str…
DORA: Dynamic Online Reinforcement Agent for Token Merging in Vision Transformers
Kaixuan He, Song Chen, Yi Kang
Vision Transformers (ViTs) incur significant computational overhead due to the quadratic complexity of self-attention relative to the token sequence length. While existing token re…
Synergy and Competition of Dual Chirality in the Chirality-Induced Spin Selectivity of Supramolecular Helices
Song Chen, Kai-Yuan Zhang, Xi Sun +2
Recent progress in constructing supramolecular assemblies with hierarchical chirality offers new opportunities to investigate the chirality-induced spin selectivity (CISS) effect a…
Baichuan-Omni-1.5 Technical Report
Yadong Li, Jun Liu, Tao Zhang +89
We introduce Baichuan-Omni-1.5, an omni-modal model that not only has omni-modal understanding capabilities but also provides end-to-end audio generation capabilities. To achieve f…
Graph Attention-Based Symmetry Constraint Extraction for Analog Circuits
Qi Xu, Lijie Wang, Jing Wang +3
In recent years, analog circuits have received extensive attention and are widely used in many emerging applications. The high demand for analog circuits necessitates shorter circu…
Task modules Partitioning, Scheduling and Floorplanning for Partially Dynamically Reconfigurable Systems Based on Modern Heterogeneous FPGAs
Bo Ding, Jinglei Huang, Junpeng Wang +3
Modern field programmable gate array(FPGA) can be partially dynamically reconfigurable with heterogeneous resources distributed on the chip. And FPGA-based partially dynamically re…
YOCO: A Hybrid In-Memory Computing Architecture with 8-bit Sub-PetaOps/W In-Situ Multiply Arithmetic for Large-Scale AI
Zihao Xuan, Yuxuan Yang, Wei Xuan +3
In this paper, we further explore the potential of analog in-memory computing (AiMC) and introduce an innovative artificial intelligence (AI) accelerator architecture named YOCO, f…
SASQ: Static Activation Scaling for Quantization-Aware Training in Large Language Models
Shizhuo Mao, Song Chen, Yi Kang
Large language models (LLMs) excel at natural language tasks but face deployment challenges due to their growing size outpacing GPU memory advancements. Model quantization mitigate…
The angular two-point correlation of NVSS galaxies revisited
Song Chen, Dominik J. Schwarz
We measure the angular two-point correlation and angular power spectrum from the NRAO VLA Sky Survey (NVSS) of radio galaxies. They are found to be consistent with the best-fit cos…
Voltage and Level-Shifter Assignment Driven Floorplanning
Bei Yu, Sheqin Dong, Song Chen +1
Low Power Design has become a significant requirement when the CMOS technology entered the nanometer era. Multiple-Supply Voltage (MSV) is a popular and effective method for both d…
An FPGA Implementation of Displacement Vector Search for Intra Pattern Copy in JPEG XS
Qiyue Chen, Yao Li, Jie Tao +3
Recently, progress has been made on the Intra Pattern Copy (IPC) tool for JPEG XS, an image compression standard designed for low-latency and low-complexity coding. IPC performs wa…
Semantic decoupled representation learning for remote sensing image change detection
Hao Chen, Yifan Zao, Liqin Liu +2
Contemporary transfer learning-based methods to alleviate the data insufficiency in change detection (CD) are mainly based on ImageNet pre-training. Self-supervised learning (SSL)…
SparseMap: Loop Mapping for Sparse CNNs on Streaming Coarse-grained Reconfigurable Array
Xiaobing Ni, Mengke Ge, Jiaheng Ruan +2
Streaming coarse-grained reconfgurable array (CGRA) is a promising architecture for data/computing-intensive applications because of its fexibility, high throughput and efcient mem…
Synthesizing Brain-Network-Inspired Interconnections for Large-Scale Network-on-Chips
Mengke Ge, Xiaobing Ni, Qi Xu +4
Brain network is a large-scale complex network with scale-free, small-world, and modularity properties, which largely supports this high-efficiency massive system. In this paper, w…
Generalized Fault-Tolerance Topology Generation for Application Specific Network-on-Chips
Song Chen, Mengke Ge, Zhigang Li +3
The Network-on-Chips is a promising candidate for addressing communication bottlenecks in many-core processors and neural network processors. In this work, we consider the generali…
Testing foundations of modern cosmology with SKA all-sky surveys
Dominik J. Schwarz, David Bacon, Song Chen +7
Continuum and HI surveys with the Square Kilometre Array (SKA) will allow us to probe some of the most fundamental assumptions of modern cosmology, including the Cosmological Princ…
A Continuous-Time Analysis of Smoothed Matrix-Polar Spectral Gradient Flows for Muon-Type Optimization
Jinlin Liu, Song Chen, Jiaxu Liu +1
This paper studies smoothed matrix-polar spectral gradient flows for unconstrained matrix-valued optimization.The canonical polar-factor map loses smoothness at rank-deficient matr…
Continuous Cross-resolution Remote Sensing Image Change Detection
Hao Chen, Haotian Zhang, Keyan Chen +4
Most contemporary supervised Remote Sensing (RS) image Change Detection (CD) approaches are customized for equal-resolution bitemporal images. Real-world applications raise the nee…
DSSMs: State Space Models with Explicit Memory via Delay Differential Equations
Yixiao Qian, Song Chen, Jiaxu Liu +2
State Space Models (SSMs) have emerged as a powerful paradigm for efficient long-sequence modeling, offering parallel training and fast linear-time recurrent inference. However, li…
BandMap: Application Mapping with Bandwidth Allocation forCoarse-Grained Reconfigurable Array
Xiaobing Ni, Jiaheng Ruan, Mengke Ge +3
This paper proposes an application mapping algorithm, BandMap, for coarse-grained reconfigurable array (CGRA), which allocates the bandwidth in PE array according to the transferri…
Allspark: Workload Orchestration for Visual Transformers on Processing In-Memory Systems
Mengke Ge, Junpeng Wang, Binhan Chen +4
The advent of Transformers has revolutionized computer vision, offering a powerful alternative to convolutional neural networks (CNNs), especially with the local attention mechanis…
Semantic-aware Dense Representation Learning for Remote Sensing Image Change Detection
Hao Chen, Wenyuan Li, Song Chen +1
Supervised deep learning models depend on massive labeled data. Unfortunately, it is time-consuming and labor-intensive to collect and annotate bitemporal samples containing desire…
Distributed physics-informed neural networks via domain decomposition for fast flow reconstruction
Yixiao Qian, Jiaxu Liu, Zewei Xia +3
Physics-Informed Neural Networks (PINNs) offer a powerful paradigm for flow reconstruction, seamlessly integrating sparse velocity measurements with the governing Navier-Stokes equ…
Correlated diffusion of colloidal particles near a liquid-liquid interface
Wei Zhang, Song Chen, Na Li +2
Optical microscopy and multi-particle tracking are used to investigate the cross-correlated diffusion of quasi two-dimensional (2D) colloidal particles near an oil-water interface.…
DART: Decoded Attention over Recurrent States for Efficient Long-Context Sequence Modeling
Yixiao Qian, Song Chen, Pengkai Wang +3
Modern language models are built primarily from Transformers, recurrent models, and their hybrid architectures. Transformers rely on token-level attention memories, while recurrent…
Effect of thermal fluctuations on spectra and predictability in compressible decaying isotropic turbulence
Qihan Ma, Chunxin Yang, Song Chen +3
This study investigates the impact of molecular thermal fluctuations on compressible decaying isotropic turbulence using the unified stochastic particle (USP) method, encompassing…
Baichuan-Omni Technical Report
Yadong Li, Haoze Sun, Mingan Lin +23
The salient multimodal capabilities and interactive experience of GPT-4o highlight its critical role in practical applications, yet it lacks a high-performing open-source counterpa…
Cosmology with Phase 1 of the Square Kilometre Array; Red Book 2018: Technical specifications and performance forecasts
Square Kilometre Array Cosmology Science Working Group, David J. Bacon, Richard A. Battye +44
We present a detailed overview of the cosmological surveys that will be carried out with Phase 1 of the Square Kilometre Array (SKA1), and the science that they will enable. We hig…
Swarm-Inspired Generation of Collective Behaviors in Graph Dynamical Systems
Ji Chen, Song Chen, Chengzhang Gong +2
Collective behavior arises when locally interacting units produce coordinated global organization, from synchronization in dynamical systems to task-relevant information flow on gr…
VeriGRAG: Enhancing LLM-Based Verilog Code Generation with Structure-Aware Soft Prompts
Jiayu Zhao, Song Chen
Large language models (LLMs) have demonstrated strong capabilities in generating Verilog code from natural language descriptions. However, Verilog code inherently encodes structura…
Sentiment Word Aware Multimodal Refinement for Multimodal Sentiment Analysis with ASR Errors
Yang Wu, Yanyan Zhao, Hao Yang +4
Multimodal sentiment analysis has attracted increasing attention and lots of models have been proposed. However, the performance of the state-of-the-art models decreases sharply wh…
Accelerated Distributed Aggregative Optimization
Jiaxu Liu, Song Chen, Shengze Cai +2
This paper delves into the investigation of a distributed aggregative optimization problem within a network. In this scenario, each agent possesses its own local cost function, whi…
FullAnno: A Data Engine for Enhancing Image Comprehension of MLLMs
Jing Hao, Yuxiang Zhao, Song Chen +6
Multimodal Large Language Models (MLLMs) have shown promise in a broad range of vision-language tasks with their strong reasoning and generalization capabilities. However, they hea…
Tuning of perpendicular magnetic anisotropy in Bi-substituted yttrium iron garnet films by He ion irradiation
Sreeveni Das, Rhodri Mansell, Lukáš Flajšman +6
We report the continuous tuning of magnetic anisotropy in perpendicularly magnetized bismuth-substituted yttrium iron garnet (Bi-YIG) films via He ion irradiation. Our findings…
PiRD: Physics-informed Residual Diffusion for Flow Field Reconstruction
Siming Shan, Pengkai Wang, Song Chen +3
The use of machine learning in fluid dynamics is becoming more common to expedite the computation when solving forward and inverse problems of partial differential equations. Yet,…
Spin-dependent Destructive Quantum Interference Associated with Chirality-induced Spin Selectivity in Circular Single Helix Molecules
Song Chen, Hua-Hua Fu
Theoretical studies on spin-dependent transport through helical molecules with straight spiral geometry have received intense research interest in the past decade, however, the phy…
Fully-Bayesian stacking in the presence of confusion
Song Chen, Jonathan T. L. Zwart, Mario G. Santos
Multi-wavelength astronomical studies brings a wealth of science within reach. One way to achieve a cross-wavelength analysis is via `stacking', i.e. combining precise positional i…
Doppler magnification in flux-limited galaxy number counts with finite redshift bin width
Song Chen
In this paper, I investigated the Doppler magnification effect in the flux-limited galaxy number counts with finite redshift bin width. In contradiction with our intuition, the num…
Realtime CNN-based Keypoint Detector with Sobel Filter and CNN-based Descriptor Trained with Keypoint Candidates
Xun Yuan, Ke Hu, Song Chen
The local feature detector and descriptor are essential in many computer vision tasks, such as SLAM and 3D reconstruction. In this paper, we introduce two separate CNNs, lightweigh…
Floorplanning and Topology Generation for Application-Specific Network-on-Chip
Bei Yu, Sheqin Dong, Song Chen +1
Network-on-chip (NoC) architectures have been proposed as a promising alternative to classical bus-based communication architectures. In this paper, we propose a two phases framewo…
Ocean-OCR: Towards General OCR Application via a Vision-Language Model
Song Chen, Xinyu Guo, Yadong Li +10
Multimodal large language models (MLLMs) have shown impressive capabilities across various domains, excelling in processing and understanding information from multiple modalities.…
Neural Observer with Lyapunov Stability Guarantee for Uncertain Nonlinear Systems
Song Chen, Shengze Cai, Tehuan Chen +2
In this paper, we propose a novel nonlinear observer based on neural networks, called neural observer, for observation tasks of linear time-invariant (LTI) systems and uncertain no…
Sense: Model Hardware Co-design for Accelerating Sparse CNN on Systolic Array
Wenhao Sun, Deng Liu, Zhiwei Zou +3
Sparsity is an intrinsic property of convolutional neural network(CNN) and worth exploiting for CNN accelerators, but extra processing comes with hardware overhead, causing many ar…
BitsMoE: Efficient Spectral Energy-Guided Bit Allocation for MoE LLM Quantization
Jiayu Zhao, Zihan Teng, Minhao Fan +4
Mixture-of-Experts (MoE) large language models reduce per-token computation through sparse expert activation, but their deployment remains memory-intensive because all expert weigh…
SecAgent: Efficient Mobile GUI Agent with Semantic Context
Yiping Xie, Song Chen, Jingxuan Xing +7
Mobile Graphical User Interface (GUI) agents powered by multimodal large language models have demonstrated promising capabilities in automating complex smartphone tasks. However, e…
Bit-balance: Model-Hardware Co-design for Accelerating NNs by Exploiting Bit-level Sparsity
Wenhao Sun, Zhiwei Zou, Deng Liu +3
Bit-serial architectures can handle Neural Networks (NNs) with different weight precisions, achieving higher resource efficiency compared with bit-parallel architectures. Besides,…
VICX: Generalizable Robot Manipulation via Video Generation and In-Context Operator Network
Song Chen, Linyan Xiang, Ying Zhou +1
Generalizable robot manipulation requires not only task-level reasoning over unseen scenes, but also reliable grounding of visual plans into embodiment-specific execution. To bridg…
Reversible magneto ionics in crystallized W Co20Fe60B20 MgO HfO2 ultra-thin films with perpendicular magnetic anisotropy
Song Chen, Elmer Monteblanco, Benjamin Borie +2
We have investigated electric field (E-field) induced modulation of perpendicular magnetic anisotropy (PMA) in both amorphous and crystalline W/CoFeB/MgO/HfO2 ultra-thin films. We…
The Novel Adaptive Fractional Order Gradient Decent Algorithms Design via Robust Control
Jiaxu Liu, Song Chen, Shengze Cai +1
The vanilla fractional order gradient descent may oscillatively converge to a region around the global minimum instead of converging to the exact minimum point, or even diverge, in…
Network flow-based simultaneous retiming and slack budgeting for low power design
Bei Yu, Sheqin Dong, Yuchun Ma +4
Low power design has become one of the most significant requirements when CMOS technology entered the nanometer era. Therefore, timing budget is often performed to slow down as man…
Language-aware Multiple Datasets Detection Pretraining for DETRs
Jing Hao, Song Chen, Xiaodi Wang +1
Pretraining on large-scale datasets can boost the performance of object detectors while the annotated datasets for object detection are hard to scale up due to the high labor cost.…