model distillation

Few-step Flow for 3D Generation via Marginal-Data Transport Distillation AAAI 2026 From Prompt to Production: Automating Brand-Safe Marketing Imagery with Text-to-Image Models WACV 2026 Parameter Merging with Gradient-Guided Supermasks in Online Continual Learning AAAI 2026 Phased One-Step Adversarial Equilibrium for Video Diffusion Models AAAI 2026 Powering Verifiable Learning via Automated Evolutionary Data Synthesis ACL 2026 SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured Reasoning EACL 2026 SwiftVideo: A Unified Framework for Few-Step Video Generation Through Trajectory-Distribution Alignment AAAI 2026 Towards Effective and Efficient Multi-Agent Language Model Systems: Foundations, Prospects, and Applications ACL 2026 Training in Step-by-Step Formal Reasoning Improves Pronominal Reasoning in Language Models EACL 2026 When Agents Look the Same: Quantifying Distillation-Induced Similarity in Tool-Use Behaviors ACL 2026 Automatic Evaluation for Text-to-image Generation: Task-decomposed Framework, Distilled Training, and Meta-evaluation Benchmark ACL 2025 Autoregressive Distillation of Diffusion Transformers CVPR 2025 Breaking the Reasoning Barrier A Survey on LLM Complex Reasoning through the Lens of Self-Evolution ACL 2025 Bridging Information Gaps with Comprehensive Answers: Improving the Diversity and Informativeness of Follow-Up Questions EMNLP 2025 Composition and Control with Distilled Energy Diffusion Models and Sequential Monte Carlo AISTATS 2025 Di[M]O: Distilling Masked Diffusion Models into One-step Generator ICCV 2025 Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching ICLR 2025 Distribution Backtracking Builds A Faster Convergence Trajectory for Diffusion Distillation ICLR 2025 Efficient Diffusion as Low Light Enhancer CVPR 2025 Exploring the Potential of Large Language Models for Heterophilic Graphs NAACL 2025 FADA: Fast Diffusion Avatar Synthesis with Mixed-Supervised Multi-CFG Distillation CVPR 2025 Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation AAAI 2025 From Reasoning to Answer: Empirical, Attention-Based and Mechanistic Insights into Distilled DeepSeek R1 Models EMNLP 2025 FVGen: Accelerating Novel-View Synthesis with Adversarial Video Diffusion Distillation ICCV 2025 Improve Speech Translation Through Text Rewrite COLING 2025