conftrace_

knowledge distillation

3725 papers

Explore in graph

Also known as

KD

Co-occurring keywords

model compression (3302) large language model (13587) transfer learning (5449) domain adaptation (4595) representation learning (6206) neural network (6616) language model (4599) catastrophic forgetting (958) continual learning (1181) contrastive learning (4032)

Papers

Distilling Parallel Gradients for Fast ODE Solvers of Diffusion Models ICCV 2025

Revisiting Intermediate-Layer Matching in Knowledge Distillation: Layer-Selection Strategy Doesn’t Matter (Much) IJCNLP 2025

Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation ACL 2025

Enhancing Cross-Tokenizer Knowledge Distillation with Contextual Dynamical Mapping ACL 2025

BayesKD: Bayesian Knowledge Distillation for Compact LLMs in Constrained Fine-tuning Scenarios ACL 2025

AIDE: Attribute-Guided MultI-Hop Data Expansion for Data Scarcity in Task-Specific Fine-tuning ACL 2025

Depth Any Event Stream: Enhancing Event-based Monocular Depth Estimation via Dense-to-Sparse Distillation ICCV 2025

Emo Pillars: Knowledge Distillation to Support Fine-Grained Context-Aware and Context-Less Emotion Classification ACL 2025

Adversarial Reconstruction Feedback for Robust Fine-grained Generalization ICCV 2025

Multi-Level Feature Distillation of Joint Teachers Trained on Distinct Image Datasets WACV 2025

Building a Family of Data Augmentation Models for Low-cost LLM Fine-tuning on the Cloud COLING 2025

Rethinking the Roles of Large Language Models in Chinese Grammatical Error Correction ACL 2025

What to Distill? Fast Knowledge Distillation with Adaptive Sampling ICCV 2025

Revisiting Weak-to-Strong Generalization in Theory and Practice: Reverse KL vs. Forward KL ACL 2025

Beyond Decoder-only: Large Language Models Can be Good Encoders for Machine Translation ACL 2025

Knowledge Distillation for Learned Image Compression ICCV 2025

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

Beyond Output Matching: Bidirectional Alignment for Enhanced In-Context Learning ACL 2025

Distilling an End-to-End Voice Assistant Without Instruction Training Data ACL 2025

You Are Your Own Best Teacher: Achieving Centralized-level Performance in Federated Learning under Heterogeneous and Long-tailed Data ICCV 2025

Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis ICCV 2025

LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs ACL 2025

KOEnsAttack: Towards Efficient Data-Free Black-Box Adversarial Attacks via Knowledge-Orthogonalized Substitute Ensembles ICCV 2025

Dual-Process Image Generation ICCV 2025

SKIntern: Internalizing Symbolic Knowledge for Distilling Better CoT Capabilities into Small Language Models COLING 2025