No article text was recorded for this version.
cross-architecture feature alignment
Version 2 of 2266 papers290 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Cross-Architecture Knowledge Distillation
- Blog: Cross-Task Representation Learning for Anatomical Landmark Detection
- Blog: Progressive multi-level distillation learning for pruning network
- Blog: No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier
- Blog: CompoDistill: Attention Distillation for Compositional Reasoning in Multimodal LLMs
- Blog: Generalized Linear Mode Connectivity for Transformers
- Blog: Kernel Based Progressive Distillation for Adder Neural Networks
- Blog: Projected Latent Distillation for Data-Agnostic Consolidation in Distributed Continual Learning
- Blog: Mutual Information-Empowered Task-Oriented Communication: Principles, Applications and Challenges
- Blog: Cross-Architecture Knowledge Distillation
- Blog: CoNet: Collaborative Cross Networks for Cross-Domain Recommendation
- Blog: LightVessel: Exploring Lightweight Coronary Artery Vessel Segmentation via Similarity Knowledge Distillation
- Blog: DetKDS: Knowledge Distillation Search for Object Detectors
- Blog: Target Speech Extraction with Pre-trained AV-HuBERT and Mask-And-Recover Strategy
- Blog: ScaleKD: Strong Vision Transformers Could Be Excellent Teachers
- Blog: CustomKD: Customizing Large Vision Foundation for Edge Model Improvement via Knowledge Distillation
- Blog: Attention-based Cross-Layer Domain Alignment for Unsupervised Domain Adaptation
- Blog: C2KD: Cross-layer and Cross-head Knowledge Distillation for Small Language Model-based Recommendation
- Blog: Knowledge Distillation with Multi-granularity Mixture of Priors for Image Super-Resolution
- Blog: A Good Student is Cooperative and Reliable: CNN-Transformer Collaborative Learning for Semantic Segmentation
- Blog: Amalgamating Multi-Task Models with Heterogeneous Architectures
- Blog: Stitching for Neuroevolution: Recombining Deep Neural Networks without Breaking Them
- Blog: Efficient Knowledge Distillation via Curriculum Extraction
- Blog: A Comprehensive Overhaul of Feature Distillation
- Blog: FedLoRA: Model-Heterogeneous Personalized Federated Learning with LoRA Tuning
- Blog: dFLMoE: Decentralized Federated Learning via Mixture of Experts for Medical Data Analysis
- Blog: Credit assignment for trained neural networks based on Koopman operator theory
- Blog: Transporting Task Vectors across Different Architectures without Training
- Blog: EmBrace: A Collective Knowledge Fusion Framework Toward Unified EEG Foundation Models
- Blog: Can't Hide Behind the API: Stealing Black-Box Commercial Embedding Models
- Blog: Language Model Knowledge Distillation for Efficient Question Answering in Spanish
- Blog: A Good Student is Cooperative and Reliable: CNN-Transformer Collaborative Learning for Semantic Segmentation
- Blog: All-in-One: Transferring Vision Foundation Models into Stereo Matching
- Blog: Model Stitching: Looking For Functional Similarity Between Representations
- Blog: UHKD: A Unified Framework for Heterogeneous Knowledge Distillation via Frequency-Domain Representations
- Blog: HKT: A Biologically Inspired Framework for Modular Hereditary Knowledge Transfer in Neural Networks
- Blog: CoTuning: A Large-Small Model Collaborating Distillation Framework for Better Model Generalization
- Blog: Student Becoming the Master: Knowledge Amalgamation for Joint Scene Parsing, Depth Estimation, and More
- Blog: Pretrained Hybrids with MAD Skills
- Blog: Towards Black-box Iterative Machine Teaching
- Blog: Towards Efficient Task-Driven Model Reprogramming with Foundation Models
- Blog: Plug-in and Fine-tuning: Bridging the Gap between Small Language Models and Large Language Models
- Blog: Towards Personalized Federated Learning via Heterogeneous Model Reassembly
- Blog: LLM-based Embeddings: Attention Values Encode Sentence Semantics Better Than Hidden States
- Blog: Cross-Image Relational Knowledge Distillation for Semantic Segmentation
- Blog: Amalgamating Knowledge towards Comprehensive Classification
- Blog: Transferability Estimation using Bhattacharyya Class Separability
- Blog: Orchestrate Latent Expertise: Advancing Online Continual Learning with Multi-Level Supervision and Reverse Self-Distillation
- Blog: iMacSR: Intermediate Multi-Access Supervision and Regularization in Training Autonomous Driving Models
- Blog: Distilling Knowledge from Heterogeneous Architectures for Semantic Segmentation
- Blog: Cross-Layer Distillation with Semantic Calibration
- Blog: PromptKD: Unsupervised Prompt Distillation for Vision-Language Models
- Blog: An Embarrassingly Simple Approach for Knowledge Distillation
- Blog: Feature-map-level Online Adversarial Knowledge Distillation
- Blog: Hilbert Distillation for Cross-Dimensionality Networks
- Blog: AM-RADIO: Agglomerative Model - Reduce All Domains Into One
- Blog: Model Recycling Framework for Multi-Source Data-Free Supervised Transfer Learning
- Blog: Multi-head Knowledge Distillation for Model Compression
- Blog: Hierarchical Residuals Exploit Brain-Inspired Compositionality
- Blog: BlockLLM: Multi-tenant Finer-grained Serving for Large Language Models
Showing 60 of 266 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_cross_architecture_feature_alignment_d5a7e27d,
title = {cross-architecture feature alignment},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cross-architecture-feature-alignment/rdr_d5a7e27df3f1417d94861fd597d6d088},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_cross_architecture_feature_alignment_d5a7e27d_v2,
title = {cross-architecture feature alignment},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cross-architecture-feature-alignment/rdr_d5a7e27df3f1417d94861fd597d6d088/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}