Research map / Architectures and efficiency / RNNs and normalization
A Generalized Language Model in Tensor Space
Lipeng Zhang, Peng Zhang, Xindian Ma, Shuqin Gu, Zhan Su, Dawei Song
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use TSLM instead of reimplemented RNN | Language modeling · PTB test | perplexity: 124.1 -> 108.1 | Improved |
| Use TSLM instead of reimplemented LSTM | Language modeling · PTB test | perplexity: 110.3 -> 108.1 | Improved |
| Use TSLM instead of reimplemented RNN | Language modeling · WikiText-2 test | perplexity: 120.4 -> 100.4 | Improved |
| Use TSLM instead of reimplemented LSTM | Language modeling · WikiText-2 test | perplexity: 101.4 -> 100.4 | Improved |
| Use TSLM+MoS instead of RNN+MoS | MoS language modeling · PTB test | perplexity: 84.3 -> 83.6 | Improved |
| Use TSLM+MoS instead of RNN+MoS | MoS language modeling · WikiText-2 test | perplexity: 81.8 -> 81.0 | Improved |
| Increase tensor order / maximum sequence length up to the dataset-specific optimum (ablation) | TSLM · PTB and WikiText-2 | perplexity | Mixed |
| Increase decomposition rank up to the dataset-specific optimum (ablation) | TSLM · PTB and WikiText-2 | perplexity | Mixed |
Closest papers by meaning
- Tensor Product Attention Is All You Need (NeurIPS 2025 · similarity 0.86)
- tnGPS: Discovering Unknown Tensor Network Structure Search Algorithms via Large Language Models (LLMs) (ICML 2024 · similarity 0.85)
- TNCSE: Tensor Norm Constraints for Unsupervised Contrastive Learning of Sentence Embeddings (AAAI 2025 · similarity 0.84)
- Correlation and Navigation in the Vocabulary Key Representation Space of Language Models (ICLR 2025 · similarity 0.84)
- Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models (NeurIPS 2024 · similarity 0.84)
- Tensor-Parallelism with Partially Synchronized Activations (NeurIPS 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
