Efficient ML
Model compression, pruning, quantization, distillation
20 papers indexed
Efficient Network Inference via Hardware-Aware Architecture Search, Model Pruning & Quantization
This paper investigates efficient network inference for GNSS interference characterization using model compression and hardware-aware design for embedded deployment.
Efficient Audio-Visual Event Recognition via Knowledge Distillation and Dynamic INT8 Quantization of a Hybrid Cross-Attention Network
This paper proposes a compression framework for efficient audio-visual event recognition using transformer-based models, combining architectural compression, knowledge distillation, and dynamic INT8 q…
Collaborative Few-Step Distillation and Low-Bit Quantization for Wan2.2 Dual-Expert Video Diffusion Models
Jinyang Du, Shenghao Jin, Ziqian Xu, Ruihao Gong +4 more
The paper proposes a compression pipeline combining few-step distillation and low-bit quantization to significantly reduce the deployment cost and parameter footprint of large dual-expert video diffus…
SETAREH Transform: A Sorting-Assisted Haar-Wavelet Sparsification Method for Approximate Inner-Product Computation
This paper proposes a Haar-wavelet-based sparsification approach to approximate inner products between high-dimensional vectors.
Does Compression Preserve Uncertainty? A Unified Benchmark for Quantized and Sparse LLMs via Conformal Prediction
Yujia Tong, Yuxi Wang, Yunyang Wan, Tian Zhang +2 more
This paper investigates whether model compression techniques (like quantization and pruning) preserve a Large Language Model's ability to quantify its own uncertainty, finding that accuracy-only evalu…
ERA: Entropy-Guided Visual Token Pruning with Rectified Attention for Efficient MLLMs
Yuhao Wang, Mu Qiao, Haiwen Diao, Yunzhi Zhuge +4 more
This paper proposes ERA, a framework for efficient multimodal large language models using entropy-guided visual token pruning, rectified attention, and bias-aware token recycling.
VertMark: A Unified Training-Free Robust Watermarking Framework for Vertical Domain Pre-trained Language Models
Cong Kong, Xin Cheng, Zhaoxia Yin, Shuai Li +2 more
VertMark introduces a novel, unified, and training-free framework to embed robust watermarks into vertical domain pre-trained language models (VPLMs) for copyright protection across multiple specializ…
Pruning and Distilling Mixture-of-Experts into Dense Language Models
Junhyuck Kim, Jihun Yun, Haechan Kim, Gyeongman Kim +2 more
The paper introduces a systematic framework to convert large Mixture-of-Experts (MoE) models into memory-efficient, fully dense architectures, achieving superior performance compared to traditional pr…
Token Optimization Strategies for LLM-Based Oracle-to-PostgreSQL Migration
This paper formalizes token optimization as a multi-objective constrained transformation problem for LLM-based Oracle-to-PostgreSQL migration, demonstrating that adaptive routing offers the best balan…
CRIMP: Compact & Reliable DNN Inference on In-Memory Processing via Crossbar-Aligned Compression and Non-ideality Adaptation
Shuo Huai, Hao Kong, Xiangzhong Luo, Shiqing Li +4 more
This paper addresses the obstacles of using Crossbar-based In-Memory Processing (IMP) accelerators for deep neural networks (DNNs) by reusing bit-shift units for multiplication, applying pruning metho…
Multi-Teacher Knowledge Distillation via Teacher-Informed Mixture Priors
Luyang Fang, Yongkai Chen, Jiazhang Cai, Ping Ma +1 more
The paper proposes Multi-Teacher Bayesian Knowledge Distillation (MT-BKD), a framework that uses Bayesian inference and teacher-informed priors to improve model compression, enhance predictive accurac…
LightRot: A Light-Weighted Rotation Scheme and Architecture for Accurate Low-Bit Large Language Model Inference
Sangjin Kim, Yuseon Choi, Jungjun Oh, Byeongcheol Kim +1 more
This paper introduces LightRot, a lightweight rotation scheme and dedicated hardware accelerator for energy-efficient and accurate low-bit large language model inference.
Taming the Security-Energy Paradox: A Green AI Approach to Optimized Android Malware Detection
This paper tests different INT8 quantized Multi-Layer Perceptron models for malware detection on Android devices, achieving high accuracy with reduced energy consumption.
CIVIC: End-to-End Sequence Compactness for Efficient Vision-Language Models
Fengze Yang, Bo Yu, Xuewen Luo, Cathy Liu +1 more
CIVIC is a path-consistent compact visual inference framework that achieves genuine hardware efficiency in Vision-Language Models by maintaining contiguous sequence representations across all inferenc…
One Basis to Animate Them All: Gaussian Blendshape Distillation for Real-Time Avatars
This paper presents GALA, a method to accelerate 3D avatar animation by approximating neural inference with a linear combination of blendshapes.
TopoQuant: Topological Framework to Characterize Behavioral Shifts in Quantized Large Language Models
Baha Rababah, Shahzeb Qamar, Lorenz Sparrenberg, Rafet Sifa +3 more
This paper introduces TopoQuant, a topological framework to quantify structural drift in self-attention weights and relate it to behavioral changes in quantized LLMs.
DPE-Rec: Diversity-Preserving and Efficient Diffusion Language Model Recommendation for Bundle Construction
Pingchuan Ma, Bohan Jiang, Chengshuai Zhao, Dawei Li +2 more
This paper introduces DPE-Rec, a diffusion framework for diversity preservation and efficient recommendation in generative bundle construction.
DEX: Digit-Level Early Exit for Energy-Efficient MSDF Neural Network Inference
This paper proposes an MSDF accelerator for quantized U-Net segmentation that reduces computation dynamically and achieves high accuracy.
VibeVoice-ASR-BitNet Technical Report
Songchen Xu, Ting Song, Shaohan Huang, Zhiliang Peng +6 more
The paper introduces VibeVoice-ASR-BitNet, a compressed real-time speech recognition model optimized for edge CPUs using heterogeneous quantization and custom SIMD kernels.
It Takes a MAESTRO To Prune Bad Experts
MAESTRO is a structured pruning framework designed for MoE language models that models autoregressive expert activation trajectories as Ergodic Markov chains, yielding a globally aware importance heur…