文生图 Prompt

从论文上下文和图注生成可直接发表的学术图，无需输入图。

全部

143 prompts

排序:

文生图

文生图 Prompt

Any2Graph: Supervised Graph Prediction Poster

ArbGraph Credibility Arbitration Framework Overview

ArXivDoc LaTeX-Native Scientific Document Retrieval

AudioHijack Attack Framework

Bayesian Model of Haptic Stimulus Perception

Behavior Understanding Alignment (BUA) Framework

CausalRivers: Causal Discovery Benchmark Poster

CFAT Triangular-Attention Super-Resolution — Poster

CinDM: Compositional Inverse Design Poster

CLARITY Framework Overview with Rule and LLM Components

Compressive Transformer Memory Slots for Long Context

Counterfactual Randomization Sampling — Poster

CROTTC-IF Architecture Overview

CS-ARM-BN Meta-Learning Method and Comparison

D-Persona Medical Image Segmentation — Poster

DAS: Diffusion Alignment as Sampling Poster

DEADiff Diffusion for Stylized Generation — Poster

DEPT: Decoupling Embeddings from Transformers — ICLR Poster

DFA Class Bias in Cross-Attention Layers

DLM4G Graph-Conditioned Diffusion Language Framework

Document Agentic RAG Workflow Overview

DP-FTRL Privacy Amplification Analysis — Conference Poster

DSPO Score-Matching Alignment for Diffusion Models

Dual-Glob Contrastive F0 Contour Framework

E-SRResNet Super-Resolution Network Architecture

EEG Stop-Signal Task Classification Pipeline

EigenVI: Score-Based Variational Inference Poster

FastGen: Adaptive KV Cache Compression for LLMs

FlowVid Consistent Video-to-Video Synthesis — Poster

FoL++ Visual Place Recognition Training Pipeline

Fourier Latent Dynamics for Motion Learning — Poster

GeoLink 3D Structure Anchors for Cross-View Geo-Localization

GFlowState Visualization Workflow Diagram

gMatch Method Overview

GOPSA EEG Domain Adaptation Method — Poster

GPipe Pipeline Parallelism with Microbatches

GROOT Self-Supervised Pre-Training in Minecraft — Poster

Hammer Function-Calling Models with Masking — Poster

Hi-WM Human-in-the-World-Model Pipeline

HistDiT: Transformer Diffusion Architecture for Histology

How Algorithm Distillation (AD) Works

How DeceptionNet Works: Domain Randomization Overview

How to Build Toolformer: Tool-Use Training Pipeline

Human Expertise in Algorithmic Prediction — Poster

HumanGaussian Text-to-3D Human Generation — Poster

HydraLoRA Asymmetric Fine-Tuning Method — Poster

HyPeR Framework for Audio Reasoning Overview

IAM-CL2R Compatible Learning Framework — Poster

Implicit Variant Architecture with InternVL3 and LoRA

JKO Scheme for Learning Diffusion Processes — Poster

Joint 1-D and 2-D Audio Modeling Framework Schematic

JudgeLM Fine-Tuning LLMs as Scalable Judges — Poster

Lateral-Axial Factorization Architecture

Leverage SHAP: Shapley Values via Leverage Sampling

LLM Pipeline for Deriving AV Driving Requirements

LLM.int8() Mixed-Precision Decompositions

LOKI Synthetic Data Detection Benchmark — Poster

Long-Term 3D Dynamics Parsing Pipeline — Poster

LORS Method for Efficient Network Stacking Poster

LucidDreamer Text-to-3D with ISM — Poster

Mapping Deep Networks to Human Visual Brain Poster

MASA: Label-Free Any-Object Tracking — Poster

Mathematical Framework for Platelet Plug Coagulation

MCR-RNNT Dual-Mode Unified Transducer Training

MCSC Multimodal Context-to-Script Task Overview

MDP Sample Complexity Bounds — NeurIPS Poster

MeshRet Skinned Motion Retargeting — Poster

Meta-Learning System: Supervisory and Subordinate RNNs

Meta-RL with Outer and Inner Optimization Loops

MILLET Interpretable Time Series Classifier — Poster

MindBridge: Cross-Subject Brain Decoding Poster

Molecular Property Prediction Survey Overview

MOMENTA Architecture: Pipeline and Optimization

Multi-Agent Adversarial Synthesis and Defense Pipeline

Multi-Grained Video Anomaly Detection — CVPR Poster

Muscle-Driven Piano Playing System Overview

MVFA Visual Feature Adaptation for Medical Anomaly Detection

NAS Cell Blocks and Per-Step Operation Decisions

NASNet Search Space: Repeated Cell Stack Architecture