22 papers
NOVA-CIM: Noise- and Correlation-Tolerant Stochastic Interfaces for Analog Compute-in-Memory
Jiachen Ren, Wenshuai Yao, Haobo Liu +6
Analog compute-in-memory (CIM) enables energy-efficient model acceleration, but its reliance on ADC-based readout, which directly quantizes noisy column currents, makes inference a…
PatchINR: Patch-Based Implicit Neural Representations for Efficient and Scalable Inference
Jiachen Ren, Wenyong Zhou, Taiqiang Wu +4
Implicit Neural Representation (INR) provides an effective approach for continuous signal modeling, but classical per-pixel inference results in quadratic growth in inference count…
SAC: Disaggregated KV Cache System for Sparse Attention LLMs with CXL
Ruiyang Ma, Teng Ma, Junru Li +7
The scaling of LLMs toward long-context inference has shifted the primary serving system bottleneck from computation to memory capacity. Traditional solutions for dense attention m…
ROMER: Expert Replacement and Router Calibration for Robust MoE LLMs on Analog Compute-in-Memory Systems
Wenyong Zhou, Yuannuo Feng, Yizhe Chen +6
Large language models (LLMs) with mixture-of-experts (MoE) architectures achieve remarkable scalability by sparsely activating a subset of experts per token, yet their frequent exp…
Can We Trust LLMs on Memristors? Diving into Reasoning Ability under Non-Ideality
Taiqiang Wu, Yuxin Cheng, Chenchen Ding +5
Memristor-based analog compute-in-memory (CIM) architectures provide a promising substrate for the efficient deployment of Large Language Models (LLMs), owing to superior energy ef…
XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression
Zunhai Su, Weihao Ye, Hansen Feng +5
Learning-based 3D visual geometry models have significantly advanced with the advent of large-scale transformers. Among these, StreamVGGT leverages frame-wise causal attention to d…
XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression
Zunhai Su, Weihao Ye, Hansen Feng +5
Learning-based 3D visual geometry models have benefited substantially from large-scale transformers. Among these, StreamVGGT leverages frame-wise causal attention for strong stream…
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
Hengyuan Zhang, Zhihao Zhang, Mingyang Wang +26
Mechanistic Interpretability (MI) has emerged as a vital approach to demystify the opaque decision-making of Large Language Models (LLMs). However, existing reviews primarily treat…
Re-Activating Frozen Primitives for 3D Gaussian Splatting
Yuxin Cheng, Binxiao Huang, Wenyong Zhou +4
3D Gaussian Splatting (3D-GS) achieves real-time photorealistic novel view synthesis, yet struggles with complex scenes due to over-reconstruction artifacts, manifesting as local b…
Perspective-aware 3D Gaussian Inpainting with Multi-view Consistency
Yuxin Cheng, Binxiao Huang, Taiqiang Wu +5
3D Gaussian inpainting, a critical technique for numerous applications in virtual reality and multimedia, has made significant progress with pretrained diffusion models. However, e…
PTQTP: Post-Training Quantization to Trit-Planes for Large Language Models
He Xiao, Runming Yang, Qingyao Yang +6
Post-training quantization (PTQ) of large language models (LLMs) to extremely low bit-widths remains challenging due to the fundamental trade-off between computational efficiency a…
Binary Weight Multi-Bit Activation Quantization for Compute-in-Memory CNN Accelerators
Wenyong Zhou, Zhengwu Liu, Yuan Ren +1
Compute-in-memory (CIM) accelerators have emerged as a promising way for enhancing the energy efficiency of convolutional neural networks (CNNs). Deploying CNNs on CIM platforms ge…
QuadINR: Hardware-Efficient Implicit Neural Representations Through Quadratic Activation
Wenyong Zhou, Boyu Li, Jiachen Ren +4
Implicit Neural Representations (INRs) encode discrete signals continuously while addressing spectral bias through activation functions (AFs). Previous approaches mitigate this bia…
Enhancing Robustness of Implicit Neural Representations Against Weight Perturbations
Wenyong Zhou, Yuxin Cheng, Zhengwu Liu +3
Implicit Neural Representations (INRs) encode discrete signals in a continuous manner using neural networks, demonstrating significant value across various multimedia applications.…
Distribution-Aware Hadamard Quantization for Hardware-Efficient Implicit Neural Representations
Wenyong Zhou, Jiachen Ren, Taiqiang Wu +3
Implicit Neural Representations (INRs) encode discrete signals using Multi-Layer Perceptrons (MLPs) with complex activation functions. While INRs achieve superior performance, they…
MINR: Efficient Implicit Neural Representations for Multi-Image Encoding
Wenyong Zhou, Taiqiang Wu, Zhengwu Liu +3
Implicit Neural Representations (INRs) aim to parameterize discrete signals through implicit continuous functions. However, formulating each image with a separate neural network~(t…
Extending Straight-Through Estimation for Robust Neural Networks on Analog CIM Hardware
Yuannuo Feng, Wenyong Zhou, Yuexi Lyu +4
Analog Compute-In-Memory (CIM) architectures promise significant energy efficiency gains for neural network inference, but suffer from complex hardware-induced noise that poses maj…
HPD: Hybrid Projection Decomposition for Robust State Space Models on Analog CIM Hardware
Yuannuo Feng, Wenyong Zhou, Yuexi Lyu +4
State Space Models (SSMs) are efficient alternatives to traditional sequence models, excelling at processing long sequences with lower computational complexity. Their reliance on m…
Exploring Layer-wise Information Effectiveness for Post-Training Quantization in Small Language Models
He Xiao, Qingyao Yang, Dirui Xie +7
Large language models with billions of parameters are often over-provisioned: many layers contribute little unique information yet dominate the memory and energy footprint during i…
Decomposing Densification in Gaussian Splatting for Faster 3D Scene Reconstruction
Binxiao Huang, Zhengwu Liu, Ngai Wong
3D Gaussian Splatting (GS) has emerged as a powerful representation for high-quality scene reconstruction, offering compelling rendering quality. However, the training process of G…
Nonparametric Teaching for Graph Property Learners
Chen Zhang, Weixin Bu, Zeyi Ren +3
Inferring properties of graph-structured data, e.g., the solubility of molecules, essentially involves learning the implicit mapping from graphs to their properties. This learning…
HaLoRA: Hardware-aware Low-Rank Adaptation for Large Language Models Based on Hybrid Compute-in-Memory Architecture
Taiqiang Wu, Chenchen Ding, Wenyong Zhou +7
Low-rank adaptation (LoRA) is a predominant parameter-efficient finetuning method for adapting large language models (LLMs) to downstream tasks. Meanwhile, Compute-in-Memory (CIM)…