Revisiting Model Stitching to Compare Neural Representations

14 June 2021

Papers citing "Revisiting Model Stitching to Compare Neural Representations"

50 / 79 papers shown

Title
Shared Global and Local Geometry of Language Model Embeddings Andrew Lee Melanie Weber F. Viégas Martin Wattenberg FedML 74 1 0 27 Mar 2025
Understanding the Emergence of Multimodal Representation Alignment Megan Tjandrasuwita Chanakya Ekbote Liu Ziyin Paul Pu Liang 52 1 0 22 Feb 2025
Parameter Symmetry Breaking and Restoration Determines the Hierarchical Learning in AI Systems Liu Ziyin Yizhou Xu T. Poggio Isaac Chuang 50 4 0 07 Feb 2025
Discovering Chunks in Neural Embeddings for Interpretability Shuchen Wu Stephan Alaniz Eric Schulz Zeynep Akata 42 0 0 03 Feb 2025
We're Different, We're the Same: Creative Homogeneity Across LLMs Emily Wenger Yoed Kenett 88 3 0 31 Jan 2025
How not to Stitch Representations to Measure Similarity: Task Loss Matching versus Direct Matching András Balogh Márk Jelasity 85 0 0 15 Dec 2024
Generalization from Starvation: Hints of Universality in LLM Knowledge Graph Learning David D. Baek Yuxiao Li Max Tegmark 44 2 0 10 Oct 2024
Intriguing Properties of Large Language and Vision Models Young-Jun Lee ByungSoo Ko Han-Gyu Kim Yechan Hwang Ho-Jin Choi LRM VLM 43 0 0 07 Oct 2024
Relative Representations: Topological and Geometric Perspectives Alejandro García-Castellanos G. Marchetti Danica Kragic Martina Scolamiero 48 0 0 17 Sep 2024
A deeper look at depth pruning of LLMs Shoaib Ahmed Siddiqui Xin Dong Greg Heinrich Thomas Breuel Jan Kautz David M. Krueger Pavlo Molchanov 38 7 0 23 Jul 2024
All Roads Lead to Rome? Exploring Representational Similarities Between Latent Spaces of Generative Image Models Charumathi Badrinath Usha Bhalla Alexander X. Oesterling Suraj Srinivas Himabindu Lakkaraju DiffM 28 0 0 18 Jul 2024
Latent Space Translation via Inverse Relative Projection Valentino Maiorca Luca Moschella Marco Fumero Francesco Locatello Emanuele Rodolà 34 1 0 21 Jun 2024
Latent Functional Maps Marco Fumero Marco Pegoraro Valentino Maiorca Francesco Locatello Emanuele Rodolà 29 1 0 20 Jun 2024
On Affine Homotopy between Language Encoders Robin SM Chan Reda Boumasmoud Anej Svete Yuxin Ren Qipeng Guo ... Shauli Ravfogel Mrinmaya Sachan Bernhard Schölkopf Mennatallah El-Assady Ryan Cotterell 40 3 0 04 Jun 2024
Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP S. Balasubramanian Samyadeep Basu S. Feizi CLIP 21 3 0 03 Jun 2024
When predict can also explain: few-shot prediction to select better neural latents Kabir Dabholkar Omri Barak BDL 47 0 0 23 May 2024
The Platonic Representation Hypothesis Minyoung Huh Brian Cheung Tongzhou Wang Phillip Isola 77 110 0 13 May 2024
Mechanistic Interpretability for AI Safety -- A Review Leonard Bereska E. Gavves AI4CE 40 111 0 22 Apr 2024
Stitching for Neuroevolution: Recombining Deep Neural Networks without Breaking Them Arthur Guijt D. Thierens T. Alderliesten Peter A. N. Bosman 22 1 0 21 Mar 2024
Training-Free Pretrained Model Merging Zhenxing Xu Ke Yuan Huiqiong Wang Yong Wang Mingli Song Jie Song MoMe 32 15 0 04 Mar 2024
Training Neural Networks from Scratch with Parallel Low-Rank Adapters Minyoung Huh Brian Cheung Jeremy Bernstein Phillip Isola Pulkit Agrawal 35 10 0 26 Feb 2024
T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching Zizheng Pan Bohan Zhuang De-An Huang Weili Nie Zhiding Yu Chaowei Xiao Jianfei Cai A. Anandkumar 28 17 0 21 Feb 2024
On the Emergence of Cross-Task Linearity in the Pretraining-Finetuning Paradigm Zhanpeng Zhou Zijun Chen Yilan Chen Bo-Wen Zhang Junchi Yan MoMe 19 9 0 06 Feb 2024
Universal Neurons in GPT2 Language Models Wes Gurnee Theo Horsley Zifan Carl Guo Tara Rezaei Kheirkhah Qinyi Sun Will Hathaway Neel Nanda Dimitris Bertsimas MILM 96 37 0 22 Jan 2024
Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models Asma Ghandeharioun Avi Caciularu Adam Pearce Lucas Dixon Mor Geva 31 87 0 11 Jan 2024
Do Vision and Language Encoders Represent the World Similarly? Mayug Maniparambil Raiymbek Akshulakov Y. A. D. Djilali Sanath Narayan M. Seddik K. Mangalam Noel E. O'Connor VLM 21 11 0 10 Jan 2024
MoSECroT: Model Stitching with Static Word Embeddings for Crosslingual Zero-shot Transfer Haotian Ye Yihong Liu Chunlan Ma Hinrich Schütze 21 1 0 09 Jan 2024
Efficient Stitchable Task Adaptation Haoyu He Zizheng Pan Jing Liu Jianfei Cai Bohan Zhuang 24 3 0 29 Nov 2023
Exploring the Relationship between In-Context Learning and Instruction Tuning Hanyu Duan Yixuan Tang Yi Yang Ahmed Abbasi K. Tam 35 11 0 17 Nov 2023
Probing clustering in neural network representations Thao Nguyen Simon Kornblith 27 1 0 14 Nov 2023
The Fairness Stitch: Unveiling the Potential of Model Stitching in Neural Network De-Biasing Modar Sulaiman Kallol Roy 24 0 0 06 Nov 2023
Latent Space Translation via Semantic Alignment Valentino Maiorca Luca Moschella Antonio Norelli Marco Fumero Francesco Locatello Emanuele Rodolà 24 20 0 01 Nov 2023
Understanding the Inner Workings of Language Models Through Representation Dissimilarity Davis Brown Charles Godfrey N. Konz Jonathan Tu Henry Kvinge 34 7 0 23 Oct 2023
Mode Combinability: Exploring Convex Combinations of Permutation Aligned Models Adrián Csiszárik M. Kiss Péter Korösi-Szabó Márton Muntag Gergely Papp D. Varga MoMe 22 1 0 22 Aug 2023
Towards Personalized Federated Learning via Heterogeneous Model Reassembly Jiaqi Wang Xingyi Yang Suhan Cui Liwei Che Lingjuan Lyu Dongkuan Xu Fenglong Ma FedML 18 44 0 16 Aug 2023
Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity Zhanpeng Zhou Yongyi Yang Xiaojiang Yang Junchi Yan Wei Hu 23 26 0 17 Jul 2023
Layer-wise Linear Mode Connectivity Linara Adilova Maksym Andriushchenko Michael Kamp Asja Fischer Martin Jaggi FedML FAtt MoMe 30 15 0 13 Jul 2023
Exploring new ways: Enforcing representational dissimilarity to learn new features and reduce error consistency Tassilo Wald Constantin Ulrich Fabian Isensee David Zimmerer Gregor Koehler Michael Baumgartner Klaus H. Maier-Hein OOD 28 1 0 05 Jul 2023
Stitched ViTs are Flexible Vision Backbones Zizheng Pan Jing Liu Haoyu He Jianfei Cai Bohan Zhuang 18 2 0 30 Jun 2023
Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models A. Jaiswal Shiwei Liu Tianlong Chen Ying Ding Zhangyang Wang VLM 32 22 0 18 Jun 2023
Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning Nikhil Vyas Depen Morwani Rosie Zhao Gal Kaplun Sham Kakade Boaz Barak MLT 13 4 0 14 Jun 2023
Text-To-Concept (and Back) via Cross-Model Alignment Mazda Moayeri Keivan Rezaei Maziar Sanjabi S. Feizi CLIP 31 39 0 10 May 2023
Similarity of Neural Network Models: A Survey of Functional and Representational Measures Max Klabunde Tobias Schumacher M. Strohmaier Florian Lemmerich 52 64 0 10 May 2023
How good are variational autoencoders at transfer learning? Lisa Bonheme M. Grzes OOD DRL 23 2 0 21 Apr 2023
Model Stitching: Looking For Functional Similarity Between Representations Adriano Hernandez Rumen Dangovski Peter Y. Lu Marin Soljacic 15 3 0 20 Mar 2023
Eliciting Latent Predictions from Transformers with the Tuned Lens Nora Belrose Zach Furman Logan Smith Danny Halawi Igor V. Ostrovsky Lev McKinney Stella Biderman Jacob Steinhardt 22 192 0 14 Mar 2023
Bootstrapping Parallel Anchors for Relative Representations Irene Cannistraci Luca Moschella Valentino Maiorca Marco Fumero Antonio Norelli Emanuele Rodolà 31 4 0 01 Mar 2023
Stress and Adaptation: Applying Anna Karenina Principle in Deep Learning for Image Classification Nesma Mahmoud Hanna Antson Jaesik Choi O. Shimmi K. Roy 9 1 0 22 Feb 2023
Task-Specific Skill Localization in Fine-tuned Language Models A. Panigrahi Nikunj Saunshi Haoyu Zhao Sanjeev Arora MoMe 21 67 0 13 Feb 2023
Stitchable Neural Networks Zizheng Pan Jianfei Cai Bohan Zhuang 50 22 0 13 Feb 2023