Activation-Steered Compression
☆18Jan 30, 2026Updated 8 months ago
Alternatives and similar repositories for ASC
Users that are interested in ASC are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆15Nov 7, 2024Updated last year
- Official Implementation of LANTERN (ICLR'25) and LANTERN++(ICLRW-SCOPE'25)☆22Mar 5, 2025Updated last year
- ☆54Jul 12, 2026Updated 3 months ago
- The official codes for Fast Monte Carlo Rendering via Multi-Resolution Sampling☆16Dec 2, 2021Updated 4 years ago
- Designing effective multimodal environment distributions beyond simply environment scaling.☆16Aug 4, 2026Updated 2 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Official implementation of Nemesis: Normalizing the Soft-prompt Vectors of Vision-Language Models (ICLR 2024 Spotlight)☆16Jul 19, 2026Updated 3 months ago
- ☆14Mar 20, 2025Updated last year
- This is the code repository of paper "SFT Conflicts, RL Coexists"☆52Aug 4, 2026Updated 2 months ago
- Accelerator RTL inspired by VEGETA [HPCA'23] and MicroScopiQ [ISCA'25]☆17Nov 11, 2025Updated 11 months ago
- ☆16Jun 4, 2025Updated last year
- This repository contains code for the paper "Layer by Layer: Uncovering Where Multi-Task Learning Happens in Instruction-Tuned Large Lang…☆10Nov 12, 2024Updated last year
- ☆13May 13, 2022Updated 4 years ago
- ☆10Jan 27, 2026Updated 9 months ago
- Code for paper: Optimizing Length Compression in Large Reasoning Models☆29Oct 20, 2025Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- [NeurIPS 2025] The implementation of paper "On Reasoning Strength Planning in Large Reasoning Models"☆33Jul 6, 2025Updated last year
- [BMVC 2024 Oral] PT43D: A Probabilistic Transformer for Generating 3D Shapes from Single Highly-Ambiguous RGB Images☆12Jul 30, 2026Updated 2 months ago
- ☆19Jan 24, 2025Updated last year
- SkillGrad: Optimizing Agent Skills Like Gradient Descent☆28May 28, 2026Updated 5 months ago
- Codebase for layer wise N:M pruning pattern assignment for LLMs☆16Aug 5, 2025Updated last year
- The official repository of the paper Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models☆20Sep 14, 2026Updated last month
- ☆10Aug 29, 2021Updated 5 years ago
- Official implementation of "Can Test-Time Scaling Improve World Foundation Model?"☆15Jul 12, 2025Updated last year
- Notebooks for docarray, Jina, Finetuner, and other products from Jina AI☆12Mar 31, 2022Updated 4 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- [ECCV 2024] CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs☆20Jul 2, 2024Updated 2 years ago
- ☆45Sep 19, 2024Updated 2 years ago
- Automatic differentiable design of photonic tensor cores☆13Feb 26, 2022Updated 4 years ago
- [COLM'25] CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing☆22Jun 25, 2025Updated last year
- Elevating Chess Strategy with Fine-Tuned Large Language Model☆20Dec 8, 2023Updated 2 years ago
- User-friendly implementation of the Mixture-of-Sparse-Attention (MoSA). MoSA selects distinct tokens for each head with expert choice rou…☆30May 3, 2025Updated last year
- T5 model optimized with FlexAttention☆14Sep 30, 2024Updated 2 years ago
- ☆14Mar 20, 2026Updated 7 months ago
- LADMM-Net: An Unrolled Deep Network For Spectral Image Fusion From Compressive Data☆10Jun 10, 2026Updated 4 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆12Jul 25, 2025Updated last year
- Scaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention Residuals☆12Oct 21, 2026Updated last week
- A sample news app shows how to integrate the capabilities of HMS Core into news & reading apps.☆25Jul 30, 2021Updated 5 years ago
- ☆13Nov 17, 2024Updated last year
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆76Oct 2, 2025Updated last year
- Artifact evaluation for HPCA'24 paper Lightening-Transformer: A Dynamically-operated Optically-interconnected Photonic Transformer Accele…☆11Mar 3, 2024Updated 2 years ago
- Official github repo for "Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute"☆18Jun 30, 2025Updated last year