Knowledge Distillation

FOCUS: Towards Universal Foreground Segmentation AAAI 2025 Font-Agent: Enhancing Font Understanding with Large Language Models CVPR 2025 Form-aware Poetic Generation for Bangla AACL 2025 Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecasting ICCV 2025 From Crafting Text to Crafting Thought: Grounding Intelligent Writing Support to Writing Center Pedagogy NAACL 2025 From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systems EMNLP 2025 From Schema to State: Zero-Shot Scheme-Only Dialogue State Tracking via Diverse Synthetic Dialogue and Step-by-Step Distillation EMNLP 2025 From Scores to Steps: Diagnosing and Improving LLM Performance in Evidence-Based Medical Calculations EMNLP 2025 From Teacher to Student: Tracking Memorization Through Model Distillation ACL 2025 Fuse Before Transfer: Knowledge Fusion for Heterogeneous Distillation ICCV 2025 FuseChat: Knowledge Fusion of Chat Models EMNLP 2025 G2D: Boosting Multimodal Learning with Gradient-Guided Distillation ICCV 2025 Gamma-Guard: Lightweight Residual Adapters for Robust Guardrails in Large Language Models EMNLP 2025 GARuD: Guided Alignment of Representations using Distillation for Ultra-Low-Resource Languages IJCNLP 2025 GCD: Advancing Vision-Language Models for Incremental Object Detection via Global Alignment and Correspondence Distillation AAAI 2025 GE-Chat: A Graph Enhanced RAG Framework for Evidential Response Generation of LLMs IJCAI 2025 Generative Prompt Internalization NAACL 2025 GeoDistill: Geometry-Guided Self-Distillation for Weakly Supervised Cross-View Localization ICCV 2025 GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost ICLR 2025 Global-Semantic Alignment Distillation for Partial Multi-view Classification AAAI 2025 GradOT: Training-free Gradient-preserving Offsite-tuning for Large Language Models ACL 2025 Graph-Based Cross-Domain Knowledge Distillation for Cross-Dataset Text-to-Image Person Retrieval AAAI 2025 Ground-V: Teaching VLMs to Ground Complex Instructions in Pixels CVPR 2025 Growing Through Experience: Scaling Episodic Grounding in Language Models ACL 2025 Guided Score identity Distillation for Data-Free One-Step Text-to-Image Generation ICLR 2025