Methods › General › Attention Modules › LAMA
Low-Rank Factorization-based Multi-Head Attention
LAMA
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Low-Rank Factorization-based Multi-head Attention Mechanism, or LAMA, is a type of attention module that uses low-rank factorization to reduce computational complexity. It uses low-rank bilinear pooling to construct a structured sentence representation that attends to multiple aspects of a sentence.
Papers archive 2025-07-28
30 shown of 42, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation 31 Mar 2025 · 0 repositories · arXiv:2503.24026
-
SenseExpo: Efficient Autonomous Exploration with Prediction Information from Lightweight Neural Networks 20 Mar 2025 · 0 repositories · arXiv:2503.16000
-
One Mind, Many Tongues: A Deep Dive into Language-Agnostic Knowledge Neurons in Large Language Models 26 Nov 2024 · 0 repositories · arXiv:2411.17401
-
LAMA: Stable Dual-Domain Deep Reconstruction For Sparse-View CT 28 Oct 2024 · 0 repositories · arXiv:2410.21111
-
Discovering Leitmotifs in Multidimensional Time Series 16 Oct 2024 · 1 repository · arXiv:2410.12293
-
Consolidating LAMA with Best-First Width Search 26 Apr 2024 · 0 repositories · arXiv:2404.17648
-
Return to Tradition: Learning Reliable Heuristics with Classical Machine Learning 25 Mar 2024 · 1 repository · arXiv:2403.16508
-
Take Care of Your Prompt Bias! Investigating and Mitigating Prompt Bias in Factual Knowledge Extraction 15 Mar 2024 · 1 repository · arXiv:2403.09963
-
The Cost of Compression: Investigating the Impact of Compression on Parametric Knowledge in Language Models 1 Dec 2023 · 1 repository · arXiv:2312.00960Syntology ran 1 of 2 samples · 1 unverified · 2 pointer-only (licence)
-
The minimal computational substrate of fluid intelligence 14 Aug 2023 · 0 repositories · arXiv:2308.07039
-
DLAMA: A Framework for Curating Culturally Diverse Facts for Probing the Knowledge of Pretrained Language Models 8 Jun 2023 · 1 repository · arXiv:2306.05076
-
Learned Alternating Minimization Algorithm for Dual-domain Sparse-View CT Reconstruction 5 Jun 2023 · 1 repository · arXiv:2306.02644
-
Locomotion-Action-Manipulation: Synthesizing Human-Scene Interactions in Complex 3D Environments 9 Jan 2023 · 0 repositories · arXiv:2301.02667
-
Rethinking Fast Fourier Convolution in Image Inpainting 1 Jan 2023 · 0 repositories
-
In-context Learning Distillation: Transferring Few-shot Learning Ability of Pre-trained Language Models 20 Dec 2022 · 0 repositories · arXiv:2212.10670
-
Context Variance Evaluation of Pretrained Language Models for Prompt-based Biomedical Knowledge Probing 18 Nov 2022 · 0 repositories · arXiv:2211.10265
-
SPE: Symmetrical Prompt Enhancement for Fact Probing 14 Nov 2022 · 0 repositories · arXiv:2211.07078
-
KAMEL : Knowledge Analysis with Multitoken Entities in Language Models 1 Nov 2022 · 1 repository
-
InforMask: Unsupervised Informative Masking for Language Model Pretraining 21 Oct 2022 · 1 repository · arXiv:2210.11771Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
-
The Effectiveness of Masked Language Modeling and Adapters for Factual Knowledge Injection 3 Oct 2022 · 1 repository · arXiv:2210.00907
-
Inpainting at Modern Camera Resolution by Guided PatchMatch with Auto-Curation 6 Aug 2022 · 0 repositories · arXiv:2208.03552
-
GLaMa: Joint Spatial and Frequency Loss for General Image Inpainting 15 May 2022 · 0 repositories · arXiv:2205.07162
-
Comparison of CoModGANs, LaMa and GLIDE for Art Inpainting- Completing M.C Escher's Print Gallery 3 May 2022 · 0 repositories · arXiv:2205.01741
-
Meta-learning via Language Model In-context Tuning 16 Nov 2021 · 0 repositories
-
SPE: Symmetrical Prompt Enhancement for Factual Knowledge Retrieval 16 Oct 2021 · 0 repositories
-
Meta-learning via Language Model In-context Tuning 15 Oct 2021 · 1 repository · arXiv:2110.07814
-
Rewire-then-Probe: A Contrastive Recipe for Probing Biomedical Knowledge of Pre-trained Language Models 15 Oct 2021 · 1 repository · arXiv:2110.08173
-
P-Adapters: Robustly Extracting Factual Information from Language Models with Diverse Prompts 14 Oct 2021 · 1 repository · arXiv:2110.07280
-
Resolution-robust Large Mask Inpainting with Fourier Convolutions 15 Sep 2021 · 8 repositories · arXiv:2109.07161Syntology ran 0 of 4 samples · 4 unverified
-
No Need to Know Everything! Efficiently Augmenting Language Models With External Knowledge 3 Sep 2021 · 0 repositories
Tasks archive 2025-07-28
20 shown of 56 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections