Papers with linear transformations
Improving Cross-Lingual Word Embeddings by Meeting in the Middle (D18-1)
Copied to clipboard
| Challenge: | Cross-lingual word embeddings are becoming increasingly important in multilingual NLP. |
| Approach: | They propose to apply an additional transformation after initial alignment to align two disjoint monolingual vector spaces. |
| Outcome: | The proposed approach outperforms state-of-the-art models in monolingual and cross-lingual evaluation tasks. |
Cross-model Transferability among Large Language Models on the Platonic Representations of Concepts (2025.acl-long)
Copied to clipboard
| Challenge: | Prior work has shown that a single LLM’s concept representations can be captured as steering vectors (SVs) prior work has demonstrated that SVs extracted from smaller LLMs can effectively control the behavior of larger LLM. |
| Approach: | They propose a linear transformation method to bridge LLM concept representations using simple linear transformations to enable efficient cross-model transfer and behavioral control via SVs. |
| Outcome: | The proposed method bridges concept representations across different LLMs and enables efficient cross-model transfer and behavioral control via SVs. |
FNet: Mixing Tokens with Fourier Transforms (2022.naacl-main)
Copied to clipboard
| Challenge: | Using simple linear transformations, Transformer encoders can be sped up with limited accuracy costs by replacing the self-attention sublayers with simple linear mixing mechanisms. |
| Approach: | They propose to replace the self-attention sublayer with a linear transformation that "mixes" input tokens. |
| Outcome: | The proposed model outperforms the “efficient Transformers” on the GLUE benchmark at longer input lengths and on smaller models with a light memory footprint. |
Rotate King to get Queen: Word Relationships as Orthogonal Transformations in Embedding Space (D19-1)
Copied to clipboard
| Challenge: | Word embeddings have a notable property that word relationships can exist as linear substructures in the embeddable space. |
| Approach: | They propose an alternative way in which downstream models might learn these relationships: orthogonal and linear transformations. |
| Outcome: | The proposed model can learn such relationships as geometric translations, but there is no evidence that it is exclusively accurate. |
Analyzing the Limitations of Cross-lingual Word Embedding Mappings (P19-1)
Copied to clipboard
| Challenge: | Existing methods for cross-lingual word embeddings have limited results . existing methods require little or no cross-linguistic signal to work . |
| Approach: | They compare offline mapping methods to an extension of skip-gram that jointly learns both embedding spaces. |
| Outcome: | The proposed method yields more isomorphic embeddings, is less sensitive to hubness, and achieves stronger results in bilingual lexicon induction. |
LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering (2025.acl-long)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) enhance visual tasks by integrating visual representations into large language models. |
| Approach: | They propose a method to re-balance modalities by steering visual representations . they propose LLaVA Steering, a platform that enables rapid customization of MLLMs a component-based architecture . |
| Outcome: | The proposed model re-balances the modalities of visual representations in large language models . the model requires 500 times fewer trainable parameters than LoRA while maintaining comparable performance . |
Jump to Conclusions: Short-Cutting Transformers with Linear Transformations (2024.lrec-main)
Copied to clipboard
| Challenge: | Transformer-based language models create hidden representations of inputs at every layer, but only use final-layer representations for prediction. |
| Approach: | They propose a method for casting hidden representations as final representations, bypassing transformer computation in-between. |
| Outcome: | The proposed method produces more accurate predictions from hidden layers across various model scales, architectures, and data distributions. |
Theory-optimal Quantization Based on Flatness (2026.acl-long)
Copied to clipboard
| Challenge: | Recent approaches to quantization of Large Language Models (LLMs) have been widely adopted due to activation outliers, which degrade model performance especially at lower bit precision. |
| Approach: | They propose a new metric for quantization that strategically distributes outlier magnitudes across matrix dimensions via optimized diagonal operations. |
| Outcome: | The proposed framework achieves less than 1% accuracy drop in W4A4 quantization on the LLaMA-3-8B model and reduces the performance gap by 39.1% on the more challenging W2A4KV16 model. |