Copertina

Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Inferix Team, Feng, Tianyu, Han, Yizeng, He, Jiahao, He, Yuanyu, Lin, Xi, Liu, Teng, Lu, Hanfeng, Tang, Jiasheng, Wang, Wei, Wang, Zhiyuan, Wu, Jichao, Yang, Mingyang, Yu, Yinghao, Zhang, Zeyu, Zhuang, Bohan
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

BlockVid: Block Diffusion for High-Quality and Consistent Minute-Long Video Generation
di: Zhang, Zeyu, et al.
Pubblicazione: (2025)

FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion
di: Liu, Akide, et al.
Pubblicazione: (2025)

Few-Step Distillation for Text-to-Image Generation: A Practical Guide
di: Pu, Yifan, et al.
Pubblicazione: (2025)

Neighboring Autoregressive Modeling for Efficient Visual Generation
di: He, Yefei, et al.
Pubblicazione: (2025)

ZipAR: Parallel Auto-regressive Image Generation through Spatial Locality
di: He, Yefei, et al.
Pubblicazione: (2024)

RAPID^3: Tri-Level Reinforced Acceleration Policies for Diffusion Transformer
di: Zhao, Wangbo, et al.
Pubblicazione: (2025)

Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation
di: Zhao, Wangbo, et al.
Pubblicazione: (2024)

Less Detail, Better Answers: Degradation-Driven Prompting for VQA
di: Han, Haoxuan, et al.
Pubblicazione: (2026)

World-R1: Reinforcing 3D Constraints for Text-to-Video Generation
di: Wang, Weijie, et al.
Pubblicazione: (2026)

FlashBlock: Attention Caching for Efficient Long-Context Block Diffusion
di: Chen, Zhuokun, et al.
Pubblicazione: (2026)

Continuous-time Riemannian SGD and SVRG Flows on Wasserstein Probabilistic Space
di: Yi, Mingyang, et al.
Pubblicazione: (2024)

From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs
di: Tian, Yuchuan, et al.
Pubblicazione: (2025)

ME-Switch: A Memory-Efficient Expert Switching Framework for Large Language Models
di: Liu, Jing, et al.
Pubblicazione: (2024)

RTP-LLM: High-Performance Alibaba LLM Inference Engine
di: Tan, Boyu, et al.
Pubblicazione: (2026)

Covert Multicast in UAV-Enabled Wireless Communication Systems With One-hop and Two-hop Strategies
di: Zhang, Wenhao, et al.
Pubblicazione: (2024)

OmniSparse: Training-Aware Fine-Grained Sparse Attention for Long-Video MLLMs
di: Chen, Feng, et al.
Pubblicazione: (2025)

Dynamic Diffusion Transformer
di: Zhao, Wangbo, et al.
Pubblicazione: (2024)

A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs
di: Zhao, Wangbo, et al.
Pubblicazione: (2024)

Utility-Aware Progressive Inference over UDP Packet Blocks for Emergency Communications
di: Wang, Jiayue, et al.
Pubblicazione: (2026)

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference
di: He, Yongchao, et al.
Pubblicazione: (2025)

SIMPLE: Disaggregating Sampling from GPU Inference into a Decision Plane for Faster Distributed LLM Serving
di: Zhao, Bohan, et al.
Pubblicazione: (2025)

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation
di: Zhou, Junkang, et al.
Pubblicazione: (2026)

Captain Safari: A World Engine with Pose-Aligned 3D Memory
di: Chou, Yu-Cheng, et al.
Pubblicazione: (2025)

GigaWorld-0: World Models as Data Engine to Empower Embodied AI
di: GigaWorld Team, et al.
Pubblicazione: (2025)

Block Flow: Learning Straight Flow on Data Blocks
di: Wang, Zibin, et al.
Pubblicazione: (2025)

R-Stitch: Dynamic Trajectory Stitching for Efficient Reasoning
di: Chen, Zhuokun, et al.
Pubblicazione: (2025)

Playing with Transformer at 30+ FPS via Next-Frame Diffusion
di: Cheng, Xinle, et al.
Pubblicazione: (2025)

Beyond Meta-Reasoning: Metacognitive Consolidation for Self-Improving LLM Reasoning
di: Zhuang, Ziqing, et al.
Pubblicazione: (2026)

eSapiens's DEREK Module: Deep Extraction & Reasoning Engine for Knowledge with LLMs
di: Shi, Isaac, et al.
Pubblicazione: (2025)

Analysis of Building Indoor Earthquake Evacuation Considering Collaborative Collapse and Debris Distributions of Suspended Ceilings and Masonry Infill Walls
di: Yinghao Duan, et al.
Pubblicazione: (2026)

DyDiT++: Diffusion Transformers with Timestep and Spatial Dynamics for Efficient Visual Generation
di: Zhao, Wangbo, et al.
Pubblicazione: (2025)

BLADE: Block-Sparse Attention Meets Step Distillation for Efficient Video Generation
di: Gu, Youping, et al.
Pubblicazione: (2025)

PSA: Pyramid Sparse Attention for Efficient Video Understanding and Generation
di: Li, Xiaolong, et al.
Pubblicazione: (2025)

Do Engine‐Specific Tax Programs Work? A Structural Analysis of Market Spillovers and Welfare Implications
di: Jiasheng Li, et al.
Pubblicazione: (2025)

Your Co-Workers Matter: Evaluating Collaborative Capabilities of Language Models in Blocks World
di: Wu, Guande, et al.
Pubblicazione: (2024)

A group testing based exploration of age-varying factors in chlamydia infections among Iowa residents
di: Li, Yizeng, et al.
Pubblicazione: (2024)

LP-Spec: Leveraging LPDDR PIM for Efficient LLM Mobile Speculative Inference with Architecture-Dataflow Co-Optimization
di: He, Siyuan, et al.
Pubblicazione: (2025)

SAGE: Strategy-Adaptive Generation Engine for Query Rewriting
di: Wang, Teng, et al.
Pubblicazione: (2025)

Next Tokens Denoising for Speech Synthesis
di: Liu, Yanqing, et al.
Pubblicazione: (2025)

When Do Symbolic Solvers Enhance Reasoning in Large Language Models?
di: He, Zhiyuan, et al.
Pubblicazione: (2025)