Dynamic Inference

Dynamic inference focuses on improving the efficiency and accuracy of inference processes where the estimation of a quantity influences its future evolution. Current research emphasizes developing methods for dynamic model selection and efficient computation, often utilizing neural networks (including transformers and graph neural networks) and Bayesian approaches to manage uncertainty and optimize resource allocation. This field is significant because it addresses computational bottlenecks in large-scale models and improves the reliability of predictions in applications ranging from code completion and natural language processing to robotics and real-time computer vision.

Papers

November 4, 2024

DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution
Yang Yue, Yulin Wang, Bingyi Kang, Yizeng Han, Shenzhi Wang, Shiji Song, Jiashi Feng, Gao Huang
Non Humanoid Robot Multimodal Large Language Model LLM Based Real Robot Vision Language Action Dynamic Inference

October 26, 2024

Dynamic layer selection in decoder-only transformers
Theodore Glavas, Joud Chataoui, Florence Regol, Wassim Jabbour, Antonios Valkanas, Boris N. Oreshkin, Mark Coates
Language Generation Decoder Only Transformer Layer Selection Dynamic Inference Pre Trained Decoder

October 4, 2024

Dynamic Evidence Decoupling for Trusted Multi-view Learning
Ying Liu, Lihong Liu, Cai Xu, Xiangyu Song, Ziyu Guan, Wei Zhao
Multi View Learning Different Perspective Dynamic Inference Evidential Neural Network Human Belief Network

June 5, 2024

Degrees of Freedom Matter: Inferring Dynamics from Point Trajectories
Yan Zhang, Sergey Prokudin, Marko Mihajlovic, Qianli Ma, Siyu Tang
Different Degree Multiple Trajectory Freedom Matter Motion Field Long Range Motion Dynamic Inference Generalizable Neural Field

March 29, 2024

On Large Language Models' Hallucination with Regard to Known Facts
Che Jiang, Biqing Qi, Xiangyu Hong, Dayuan Fu, Yang Cheng, Fandong Meng, Mo Yu, Bowen Zhou, Jie Zhou
Large Language Model Content Hallucination Type II Hallucination Dynamic Inference

January 18, 2024

When Neural Code Completion Models Size up the Situation: Attaining Cheaper and Faster Completion through Dynamic Model Inference
Zhensu Sun, Xiaoning Du, Fu Song, Shangwen Wang, Li Li
Code Completion Cost Effective Situation Understanding Code Completion Model Dynamic Inference Neural Code Completion

September 23, 2023

Early-Exit with Class Exclusion for Efficient Inference of Neural Networks
Jingcun Wang, Bing Li, Grace Li Zhang
Neural Network Deep Neural Network Efficient Inference Early Exit Early eXit Dynamic Inference Class Interference

September 16, 2023

Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference
Parsa Kavehzadeh, Mojtaba Valipour, Marzieh Tahaei, Ali Ghodsi, Boxing Chen, Mehdi Rezagholizadeh
Large Language Model Natural Language Processing Full Potential Auxiliary Sorting Network Rearranges Intermediate Layer Generative Task Whispering Llama Dynamic Inference

February 28, 2023

AccelTran: A Sparsity-Aware Accelerator for Dynamic Inference with Transformers
Shikhar Tuli, Niraj K. Jha
Transformer Megatron Decepticons Transformer Model Transformer Inference Dynamic Inference Accelerator Architecture Transformer Accelerator Sparse Accelerator

December 30, 2022

Bayesian Learning for Dynamic Inference
Aolin Xu, Peng Guan
Bayesian Learning Inference Problem Bayes Optimal Dynamic Inference Sequential Estimation

December 21, 2022

The Inverse of Exact Renormalization Group Flows as Statistical Inference
David S. Berman, Marc S. Klinger
Diffusion Probabilistic Model Statistical Inference Renormalization Group Inverse Task Dynamic Inference

December 6, 2022

Vision Transformer Computation and Resilience for Dynamic Inference
Kavya Sreedhar, Jason Clemons, Rangharajan Venkatesan, Stephen W. Keckler, Mark Horowitz
Vision Transformer Deep Learning Model Transformer Architecture Tiny Refinement Elicit Resilience Transformer Inference CNN Accelerator Dynamic Inference

September 29, 2022

Dynamic Inference on Graphs using Structured Transition Models
Saumya Saxena, Oliver Kroemer
Graph Neural Network Graph Drawing Dynamic Graph Linear Dynamical System Transition Model Dynamic Inference Interaction Dynamic

June 16, 2022

Fault-Tolerant Collaborative Inference through the Edge-PRUNE Framework
Jani Boutellier, Bo Tan, Jari Nurmi
Collaborative Inference Dynamic Inference

March 1, 2022

E-LANG: Energy-Based Joint Inferencing of Super and Swift Language Models
Mohammad Akbari, Amin Banitalebi-Dehkordi, Yong Zhang
Language Model Encoder Decoder Joint Learning BERT Based Code Language Model Dynamic Inference

November 29, 2021

Dynamic Inference
Aolin Xu
Reinforcement Learning Optimal Estimation Dynamic Inference Sequential Estimation