survey

29 posts tagged with "survey"

July 8, 2026

World Model for Robot Learning: A Comprehensive Survey

A comprehensive survey of world models from a robot-learning perspective, examining policy coupling, learned simulators for RL and evaluation, robotic video generation, and benchmarks/datasets across embodied applications

multimodal robotics world-model survey vision-language diffusion-model

July 4, 2026

A Survey on Vision-Language-Action Models: An Action Tokenization Perspective

从动作 tokenization 视角统一审视 VLA 模型的综述。提出 VLA 模块 + 动作 token 的统一框架，将现有 VLA 模型归为 8 种动作 token 类型（语言描述/代码/可供性/轨迹/目标状态/隐表示/原始动作/推理），逐一分析每种类型的优势、局限与未来方向，并提出分层架构趋势与从 VLA 模型到 VLA 智能体的演进路径。

robotics vision-language survey reasoning rlhf

July 4, 2026

Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications

面向真实世界部署的 VLA 全栈综述。系统梳理 VLA 三大挑战（数据稀缺 / 具身迁移 / 算力成本）、架构演进（CNN→Transformer→VLM→Diffusion/Flow→分层控制），并给出三类核心架构（sensorimotor 7 变体 / world model 3 模式 / affordance 3 模式）、模态处理（视觉/语言/动作/音频/触觉/3D）、训练范式（SL/SSL/RL + 预训练/后训练/梯度隔离/LoRA）、数据采集（遥操作/代理设备/人类视频）、公开数据集（Ego4D/OXE/DROID/AgiBot World）、机器人平台与评测基准（LIBERO/CALVIN/ManiSkill/SIMPLER/RoboArena）。最后给出面向实践者的 6 条建议与 8 个未来方向。

survey

World Model for Robot Learning: A Comprehensive Survey

A Survey on Vision-Language-Action Models: An Action Tokenization Perspective

Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications

Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities

Efficient Training of Large Language Models on Distributed Infrastructures: A Survey

[论文精读] Efficient Training of LLMs on Distributed Infrastructures: A Survey

Full Stack Optimization of Transformer Inference: a Survey

A Survey on Mixture of Experts in Large Language Models

Large Language Models for Generative Recommendation: A Survey and Visionary Discussions

Denoising Diffusion Probabilistic Models (DDPM)

Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling

EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design

ProRL Agent: Rollout-as-a-Service for RL Training of Multi-Turn LLM Agents

Understanding Stragglers in Large Model Training Using What-if Analysis

KPerfIR: Towards an Open and Compiler-centric Ecosystem for GPU Kernel Performance

Quake: Adaptive Indexing for Vector Search

BlitzScale: Fast and Live Large Model Autoscaling with O(1) Host Caching

CasMoE: A Cascaded Framework for Efficient MoE Inference on Resource-constrained

EnViT: Enhancing the Performance of Early-Exit Vision Transformers via Exit-Aware Structured Dropout-Enabled Self-Distillation

PipeThreader: Software-Defined Pipelining for Efficient DNN Execution

Principles and Methodologies for Serial Performance Optimization

XSched: Preemptive Scheduling for Diverse XPUs

Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms

A Survey of Low-bit Large Language Models

Ideas in Inference-time Scaling can Benefit Generative Pre-training Algorithms

Getting Started with Astro: A Practical Guide

Denoising Diffusion Implicit Models (DDIM)