model distillation

105 papers

Explore in graph

Also known as

PMD

Co-occurring keywords

knowledge distillation (3680) model compression (3283) diffusion model (3720) large language model (12755) image generation (2069) generative model (2889) federated learning (1320) neural network (6616) one-step generation (20) transfer learning (5442)

Papers

From Prompt to Production: Automating Brand-Safe Marketing Imagery with Text-to-Image Models WACV 2026

Few-step Flow for 3D Generation via Marginal-Data Transport Distillation AAAI 2026

SwiftVideo: A Unified Framework for Few-Step Video Generation Through Trajectory-Distribution Alignment AAAI 2026

Training in Step-by-Step Formal Reasoning Improves Pronominal Reasoning in Language Models EACL 2026

Parameter Merging with Gradient-Guided Supermasks in Online Continual Learning AAAI 2026

Phased One-Step Adversarial Equilibrium for Video Diffusion Models AAAI 2026

SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured Reasoning EACL 2026

From Reasoning to Answer: Empirical, Attention-Based and Mechanistic Insights into Distilled DeepSeek R1 Models EMNLP 2025

POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion EMNLP 2025

Turbo3D: Ultra-fast Text-to-3D Generation CVPR 2025

FADA: Fast Diffusion Avatar Synthesis with Mixed-Supervised Multi-CFG Distillation CVPR 2025

Intervening in Black Box: Concept Bottleneck Model for Enhancing Human Neural Network Mutual Understanding ICCV 2025

Inference-Time Diffusion Model Distillation ICCV 2025

Autoregressive Distillation of Diffusion Transformers CVPR 2025

Exploring the Potential of Large Language Models for Heterophilic Graphs NAACL 2025

Incremental Transformer: Efficient Encoder for Incremented Text Over MRC and Conversation Tasks COLING 2025

SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models ACL 2025

Teach Small Models to Reason by Curriculum Distillation EMNLP 2025

MaTVLM: Hybrid Mamba-Transformer for Efficient Vision-Language Modeling ICCV 2025

FVGen: Accelerating Novel-View Synthesis with Adversarial Video Diffusion Distillation ICCV 2025

Di[M]O: Distilling Masked Diffusion Models into One-step Generator ICCV 2025

TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolution CVPR 2025

Automatic Evaluation for Text-to-image Generation: Task-decomposed Framework, Distilled Training, and Meta-evaluation Benchmark ACL 2025

Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation AAAI 2025

Who Taught You That? Tracing Teachers in Model Distillation ACL 2025