[EMNLP 2025π₯] UNComp: Can Matrix Entropy Uncover Sparsity? -- A Compressor Design from an Uncertainty-Aware Perspective
β20Jan 7, 2026Updated 10 months ago
Alternatives and similar repositories for UNComp
Users that are interested in UNComp are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICLR2026π₯Oral] SwingArena: Competitive Programming Arena for Long-context GitHub Issue Solvingβ15Feb 26, 2026Updated 8 months ago
- A hierarchical LM that scales to training on context windows of +5M tokensβ11Apr 14, 2026Updated 7 months ago
- β11May 18, 2025Updated last year
- ThinK: Thinner Key Cache by Query-Driven Pruningβ30Jun 2, 2026Updated 5 months ago
- [ICML 2024] CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformersβ34Dec 30, 2024Updated last year
- Managed hosting for WordPress and PHP on Cloudways β’ AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Video Summarization Transformer: Implementation in PyTorch of the Transformer model for video summarisationβ10Oct 27, 2020Updated 6 years ago
- LONGAGENT: Scaling Language Models to 128k Context through Multi-Agent Collaborationβ11Mar 11, 2024Updated 2 years ago
- Code for ICML21 paper "Learning Self-Modulating Attention in Continuous Time Space with Applications to Sequential Recommendation"β12Feb 8, 2023Updated 3 years ago
- Code for Paper 'DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards'β18May 21, 2026Updated 5 months ago
- [ICLR 2025π₯] D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Modelsβ27Jul 7, 2025Updated last year
- [WWW 2026 Oral] MoE-CL:Self-Evolving LLMs via Continual Instruction Tuningβ22Dec 1, 2025Updated 11 months ago
- Self-Distribution BNNβ10Mar 8, 2022Updated 4 years ago
- Source code of paper ''KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing''β32Oct 24, 2024Updated 2 years ago
- [ACL 2026 Main] Official Repo for Paper "Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Aliβ¦β17Jul 1, 2026Updated 4 months ago
- Managed hosting for WordPress and PHP on Cloudways β’ AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- A transformer model that should be able to solve a simple NER taskβ11Mar 7, 2019Updated 7 years ago
- AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inferenceβ21Jan 24, 2025Updated last year
- IEEE Intelligent Vehicles Symposium (2024)β12Jul 30, 2024Updated 2 years ago
- Official Repo of paper "QUITO: Accelerating Long-Context Reasoning through Query-Guided Context Compression".β15May 6, 2026Updated 6 months ago
- Official repository of paper "Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models"β25May 27, 2025Updated last year
- π First survey on Attention Sink in Transformers β 200+ papers on utilization, interpretation, and mitigation.β145Oct 28, 2026Updated 3 weeks ago
- Adaptive Topology Reconstruction for Robust Graph Representation Learning [Efficient ML Model]β10Feb 11, 2025Updated last year
- Source code of ACM TOIS accepted paper "Spatio-Temporal Contrastive Learning Enhanced GNNs for Session-based Recommendation"β11Sep 24, 2023Updated 3 years ago
- β37Aug 26, 2026Updated 2 months ago
- Deploy on Railway without the complexity - Free Credits Offer β’ AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Official implementation of "X-CoT: Explainable Text-to-Video Retrieval via LLM-based Chain-of-Thought Reasoning (EMNLP 2025)"β11Nov 7, 2026Updated last week
- [ICLR 2025] Official implementation of paper "Dynamic Low-Rank Sparse Adaptation for Large Language Models".β25Mar 16, 2025Updated last year
- [EMNLP 2025 Findings] Familiarity-aware Evidence Compression for Retrieval Augmented Generationβ15Aug 20, 2025Updated last year
- [ICLR25] Official Implementation of "Decoupling Angles and Strength in Low-rank Adaptation"β15Dec 12, 2025Updated 11 months ago
- The official implementations of Intention-conditioned Flow Occupancy Models (InFOM)β36Jun 24, 2026Updated 4 months ago
- My Implementation of Q-Sparse: All Large Language Models can be Fully Sparsely-Activatedβ36Aug 14, 2024Updated 2 years ago
- [ICML 2026] Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Controlβ13Jul 12, 2026Updated 4 months ago
- [NeurIPS-2024] π Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies https://arxiv.org/abs/2407.13623β112Sep 26, 2024Updated 2 years ago
- A text-to-SQL prototype on the northwind sqlite datasetβ13Sep 24, 2024Updated 2 years ago
- 1-Click AI Models by DigitalOcean Gradient β’ AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- β12Dec 10, 2018Updated 7 years ago
- [AAAI 2025] Official pytorch implementation of "Diffusion Model Patching via Mixture-of-Prompts"β14Dec 12, 2024Updated last year
- This is the repository for paper titled as "Convolutional neural network models for cancer type prediction based on gene expression".β12Dec 9, 2020Updated 5 years ago
- β36Jun 3, 2025Updated last year
- This repository presents the source code for the paper "MILLION: Mastering Long-Context LLM Inference Via Outlier-Immunized KV Product Quβ¦β27Sep 1, 2026Updated 2 months ago
- β15Apr 12, 2024Updated 2 years ago
- TFT (Training from Traces) benchmark: 5 scenarios comparing TFT pipeline vs Direct Training on SGD restaurant tracesβ13Sep 7, 2026Updated 2 months ago
Are these results useful?