[๐๐๐ ๐ ๐ฎ๐ฌ๐ฎ๐ฒ] Dispersion loss counteracts embedding condensation and improves generalization in small language models
โ15May 21, 2026Updated last month
Alternatives and similar repositories for LM-Dispersion
Users that are interested in LM-Dispersion are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Creating multi-resolution embeddings and clusters from high dimensional dataโ58Sep 27, 2024Updated last year
- Benchmark and analysis of 165 pretrained SSL models. Code for "Evaluating Self-Supervised Learning via Risk Decomposition".โ14Jul 26, 2023Updated 2 years ago
- Visual bag of words for fast image matchingโ25Apr 27, 2023Updated 3 years ago
- โ21Apr 16, 2024Updated 2 years ago
- MLSys ่ชๅญฆ็ฌ่ฎฐ โ with hand-written runnable codeโ17Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer โข AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [๐๐๐๐ฆ๐ฆ๐ฃ ๐ฎ๐ฌ๐ฎ๐ฑ ๐ข๐ฟ๐ฎ๐น] ImageFlowNet: Forecasting Multiscale Image-Level Trajectories of Disease Progression with Irregularly-Saโฆโ15May 2, 2026Updated 2 months ago
- [NeurIPS 2024 Spotlight] A cell-ontology guided transcriptome foundation modelโ25Mar 12, 2025Updated last year
- Linear Attention for Efficient Bidirectional Sequence Modelingโ18May 13, 2025Updated last year
- TTG: Template Task Graph C++ APIโ26May 9, 2026Updated 2 months ago
- โ13Apr 23, 2025Updated last year
- Calling disease-related genesโ17Apr 1, 2026Updated 3 months ago
- Official repo for โRethinking Token-Level Policy Optimization for Multimodal Chain-of-Thoughtโโ25Mar 29, 2026Updated 3 months ago
- โ17Oct 17, 2024Updated last year
- โ21Jan 23, 2026Updated 5 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer โข AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- d3heatmap is a Python package to create interactive heatmaps based on d3js.โ11Sep 14, 2023Updated 2 years ago
- [NeurIPS 2024] BEACON: Benchmark for Comprehensive RNA Tasks and Language Modelsโ65Aug 2, 2024Updated last year
- Official implementation of Diffusion LMs Can Approximate Optimal Infilling Lengths Implicitlyโ39Feb 10, 2026Updated 5 months ago
- Heritability Estimation with high Efficiency using LD and Summary Statisticsโ14Feb 14, 2024Updated 2 years ago
- PathPiece tokenizerโ14Nov 10, 2024Updated last year
- โ24Jun 14, 2025Updated last year
- Library to extract embeddings for DNA sequences using BioFM genomics foundation modelโ21Aug 13, 2025Updated 11 months ago
- โ14Jun 26, 2025Updated last year
- โ20Aug 14, 2025Updated 11 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer โข AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ArXiv ๆฏๆฅ่ฎบๆๆจ้ๅฉๆ ่ชๅจๆๅ ArXiv ๆๆฐ AI ่ฎบๆ๏ผไฝฟ็จ DeepSeek ่ฟ่กๆทฑๅบฆๅๆ๏ผๅนถๆจ้ๅฐ้ฃไนฆใโ57Feb 5, 2026Updated 5 months ago
- โ12May 24, 2024Updated 2 years ago
- [ICASSP 2025 Oral] ImageFlowNet: Forecasting Multiscale Image-Level Trajectories of Disease Progression with Irregularly-Sampled Longitudโฆโ30Feb 14, 2026Updated 5 months ago
- โ12May 16, 2023Updated 3 years ago
- [ICML 2025] Fast and Low-Cost Genomic Foundation Models via Outlier Removal.โ19Jun 19, 2025Updated last year
- โ28Dec 15, 2025Updated 6 months ago
- Code of the paper "Universal Morphology Control via Contextual Modulation" at ICML 2023โ15Aug 3, 2023Updated 2 years ago
- Python Quadratic Majorization-Minimization (MM) optimization algorithms of half-quadratic criteria. Inverses problems, image restoration,โฆโ18Jan 30, 2026Updated 5 months ago
- [NeurIPS 2025 Spotlight] E2Former: An Efficient and Equivariant Transformer with Linear-Scaling Tensor Productsโ29Feb 16, 2026Updated 4 months ago
- Open source password manager - Proton Pass โข AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- A C++based implementation of the TeaLeaf heat conduction mini-app. This implementation of TeaLeaf replicates the functionality of the refโฆโ25Aug 11, 2024Updated last year
- โ13Aug 30, 2025Updated 10 months ago
- KGANCDA is effective to predict associations between circRNA and cancer, which is based on knowledge graph attention network. The detail โฆโ13Dec 12, 2022Updated 3 years ago
- Push-to-See: Learning Non-Prehensile Manipulation to Enhance Instance Segmentation via Deep Q-Learningโ13Sep 2, 2022Updated 3 years ago
- The code impliments for paper "MHNF: Multi-hop Heterogeneous Neighborhood information Fusion graph representation learning.โโ11Oct 29, 2023Updated 2 years ago
- Benchmark gene representations from different model familiesโ16May 29, 2025Updated last year
- [๐ง๐๐ญ๐ฎ๐ซ๐ ๐ฆ๐๐๐ก๐ข๐ง๐ ๐ข๐ง๐ญ๐๐ฅ๐ฅ๐ข๐ ๐๐ง๐๐] ImmunoStruct enables multimodal deep learning for immunogenicity predictionโ46Mar 5, 2026Updated 4 months ago