Copertina

UniQL: Unified Quantization and Low-rank Compression for Adaptive Edge LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chiang, Hung-Yueh, Chang, Chi-Chih, Lu, Yu-Chen, Lin, Chien-Yu, Wu, Kai-Chiang, Abdelfattah, Mohamed S., Marculescu, Diana
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models
di: Chiang, Hung-Yueh, et al.
Pubblicazione: (2025)

Quamba: A Post-Training Quantization Recipe for Selective State Space Models
di: Chiang, Hung-Yueh, et al.
Pubblicazione: (2024)

SCAN-Edge: Finding MobileNet-speed Hybrid Networks for Diverse Edge Devices via Hardware-Aware Evolutionary Search
di: Chiang, Hung-Yueh, et al.
Pubblicazione: (2024)

DARE: Diffusion Language Model Activation Reuse for Efficient Inference
di: Frumkin, Natalia, et al.
Pubblicazione: (2026)

QuarterMap: Efficient Post-Training Token Pruning for Visual State Space Models
di: Chi, Tien-Yu, et al.
Pubblicazione: (2025)

ELANA: A Simple Energy and Latency Analyzer for LLMs
di: Chiang, Hung-Yueh, et al.
Pubblicazione: (2025)

xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction
di: Chang, Chi-Chih, et al.
Pubblicazione: (2025)

V"Mean"ba: Visual State Space Models only need 1 hidden dimension
di: Chi, Tien-Yu, et al.
Pubblicazione: (2024)

Similarity Trajectories: Linking Sampling Process to Artifacts in Diffusion-Generated Images
di: Menn, Dennis, et al.
Pubblicazione: (2024)

Palu: Compressing KV-Cache with Low-Rank Projection
di: Chang, Chi-Chih, et al.
Pubblicazione: (2024)

SkipCat: Rank-Maximized Low-Rank Compression of Large Language Models via Shared Projection and Block Skipping
di: Lu, Yu-Chen, et al.
Pubblicazione: (2025)

Systolic Sparse Tensor Slices: FPGA Building Blocks for Sparse and Dense AI Acceleration
di: Taka, Endri, et al.
Pubblicazione: (2025)

ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transformer Acceleration
di: Huang, Ning-Chi, et al.
Pubblicazione: (2024)

Speculate Deep and Accurate: Lossless and Training-Free Acceleration for Offloaded LLMs via Substitute Speculative Decoding
di: Wang, Pei-Shuo, et al.
Pubblicazione: (2025)

FLRC: Fine-grained Low-Rank Compressor for Efficient LLM Inference
di: Lu, Yu-Chen, et al.
Pubblicazione: (2025)

Spectral Kernels and Holomorphic Morse Inequalities for Sequence of Line Bundles
di: Chiang, Yueh-Lin
Pubblicazione: (2024)

On the existence of extremal solutions for the conjugate discrete-time Riccati equation
di: Chiang, Chun-Yueh
Pubblicazione: (2024)

An often‐overlooked cause of gastrointestinal bleeding
di: Chien‐Ming Chiang, et al.
Pubblicazione: (2025)

Investigating Airflow Transmission Pathways of Respiratory Viruses in High‐Rise Residential Buildings Based on CFD Model
di: Hua-Yueh Liu, et al.
Pubblicazione: (2025)

PrediQL: Automated Testing of GraphQL APIs with LLMs
di: Liu, Shaolun, et al.
Pubblicazione: (2025)

HAVEN: Hybrid Automated Verification ENgine for UVM Testbench Synthesis with LLMs
di: Meng, Chang-Chih, et al.
Pubblicazione: (2026)

Electrochemical/Cobalt Dual Catalysis for Regioselective Tetramerization of Indoles
di: Kuan‐Te Liu, et al.
Pubblicazione: (2024)

Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling
di: Frumkin, Natalia, et al.
Pubblicazione: (2025)

Clinical Trial: The Optimal Timing of the Endoscope Insertion After Oral Lidocaine Spray. A Randomized Controlled Trial
di: Hsueh‐Chien Chiang, et al.
Pubblicazione: (2025)

Adipose Mesenchymal Stem Cells‐Derived Microvesicles Ameliorate Cyclophosphamide‐Induced Cystitis via Inhibiting Pyroptosis and Ferroptosis in Rats
di: Hung‐Keng Li, et al.
Pubblicazione: (2026)

SparAMX: Accelerating Compressed LLMs Token Generation on AMX-powered CPUs
di: AbouElhamayed, Ahmed F., et al.
Pubblicazione: (2025)

Effects of Essential Oil Aromatherapy on Sleep, Depression, and Well‐Being Among Older Adults: Implications for Community Health and Social Care
di: Pei Fen Chiang, et al.
Pubblicazione: (2026)

ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning
di: Huang, Chi-Pin, et al.
Pubblicazione: (2025)

Strontium‐Doped Hydroxyapatite Incorporated With Naringin for Osteoporosis Treatment
di: Chih‐Yung Chiang, et al.
Pubblicazione: (2026)

APreQEL: Adaptive Mixed Precision Quantization For Edge LLMs
di: Bouzouad, Meriem, et al.
Pubblicazione: (2026)

Ada-VE: Training-Free Consistent Video Editing Using Adaptive Motion Prior
di: Mahmud, Tanvir, et al.
Pubblicazione: (2024)

Unified Reinforcement and Imitation Learning for Vision-Language Models
di: Lee, Byung-Kwan, et al.
Pubblicazione: (2025)

Unified Low-rank Compression Framework for Click-through Rate Prediction
di: Yu, Hao, et al.
Pubblicazione: (2024)

Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers
di: Frumkin, Natalia, et al.
Pubblicazione: (2023)

Bypassing the Stiffness Cliff: Biological Impedance Matching for Shoulder Arthroplasty in the Metaboli cally Compromised Host
di: Chi-Ming, Chiang
Pubblicazione: (2026)

Quadratic Gradient: A Unified Framework Bridging Gradient Descent and Newton-Type Methods by Synthesizing Hessians and Gradients
di: Chiang, John
Pubblicazione: (2022)

Mitigating Object and Action Hallucinations in Multimodal LLMs via Self-Augmented Contrastive Alignment
di: Chang, Kai-Po, et al.
Pubblicazione: (2025)

A Sol–Gel Processed Spinel HTL Combined with an Amphiphilic Polymer Interlayer for Stable and Scalable Tin‐perovskite Solar Modules
di: Yin‐Fai Wang, et al.
Pubblicazione: (2025)

Capturing the Risk Dynamics of the A‐Share Market Based on the Markov Regime‐Switching Method
di: Min Liu, et al.
Pubblicazione: (2025)

Efficacy of the Online Interactive Podcast Program “Living With Type 1 Diabetes to Grown‐Up”: A Two‐Arm Randomized Controlled Trial Protocol
di: Yueh-Tao Chiang, et al.
Pubblicazione: (2025)