Official implementation of "Focus-dLLM: Accelerating Long-Context Diffusion LLM Inference via Confidence-Guided Context Focusing".
☆12Feb 19, 2026Updated 8 months ago
Alternatives and similar repositories for Focus-dLLM
Users that are interested in Focus-dLLM are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- We introduce UltraLLaDA , a scaled variant of LLaDA-8B-Base that extends the context length up to 128K tokens with light-weight post-trai…☆15Oct 23, 2025Updated last year
- 2021秋北航计算机组成原理☆22Mar 31, 2022Updated 4 years ago
- compiler design for 2021-BUAA-Compiler-lecture☆17Jan 8, 2022Updated 4 years ago
- 🧂[Preprint] Salt++: Context-Aligned Post-Training for Few-Step Streaming Multimodal Generation☆24Oct 2, 2026Updated 3 weeks ago
- A training-free framework that accelerates diffusion language models through dynamic cache eviction and sparse attention☆30Oct 16, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Diverse Demonstrations Improve In-context Compositional Generalization☆13Jul 7, 2023Updated 3 years ago
- 东南大学 2021 级计算机专业操作系统课程实验 - Operating System Labwork source code in Dr.Kai Dong's Operating System Class. Based on OSTEP.☆15Jun 17, 2023Updated 3 years ago
- Summary of system papers/frameworks/codes/tools on training or serving large model☆57Dec 17, 2023Updated 2 years ago
- ☆14Nov 18, 2025Updated 11 months ago
- ☆13Dec 13, 2022Updated 3 years ago
- [ICML2025] Official Code of From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection☆27Jun 27, 2025Updated last year
- [ICML 2025] This is the official PyTorch implementation of "🎵 HarmoniCa: Harmonizing Training and Inference for Better Feature Caching i…☆46Jul 10, 2025Updated last year
- A rejection-sampling based distribution alignment method for extreme actor-policy mismatch RL Training☆14Feb 11, 2026Updated 8 months ago
- Methods and code for extending the context length of diffusion language models☆56Dec 7, 2025Updated 10 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Generate presentation slides automatically using AI from text, PDFs, or structured content.☆18Mar 17, 2026Updated 7 months ago
- A living literature repository for Token Economics for LLM Agents: A Dual-View Study from Computing and Economics.☆42May 13, 2026Updated 5 months ago
- [ICML 2026] Official codebase for "Flash-VAED: Plug-and-Play VAE Decoders for Efficient Video Generation"☆46Aug 5, 2026Updated 2 months ago
- Built upon Megatron-Deepspeed and HuggingFace Trainer, EasyLLM has reorganized the code logic with a focus on usability. While enhancing …☆48Sep 18, 2024Updated 2 years ago
- Open-source AR makeup try-on for the web: foundation, lipstick, blush, eyeliner, mascara, eyeshadow + face reshaping — MediaPipe + WebGL,…☆23Jun 16, 2026Updated 4 months ago
- ☆17Feb 23, 2025Updated last year
- BUAA Computer Organization 北航 计组☆14Apr 10, 2022Updated 4 years ago
- [EMNLP 2025 Oral] 🎉 Shallow Focus, Deep Fixes: Enhancing Shallow Layers Vision Attention Sinks to Alleviate Hallucination in LVLMs☆14Dec 10, 2025Updated 10 months ago
- 百词斩打卡图片生成器☆20Feb 27, 2022Updated 4 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- 北航编译技术2022☆14Feb 28, 2023Updated 3 years ago
- Official Code For Dual Grained Quantization: Efficient Fine-Grained Quantization for LLM☆14Dec 27, 2023Updated 2 years ago
- [NeurIPS 2025] Official code for paper: Latent Chain-of-Thought for Visual Reasoning☆37Oct 16, 2025Updated last year
- [ACCV 2026] OTT3R: Multi-View 3D Reconstruction and Fast Dataset Generation at 1% Compute.☆14Oct 14, 2026Updated last week
- [CVPR 2024] How to Configure Good In-Context Sequence for Visual Question Answering☆21May 28, 2025Updated last year
- ☆22Jun 18, 2026Updated 4 months ago
- [ACL'25] The official repo of "DAGCD", an approach that mitigates context faithfulness hallucinations in LLMs.☆14Feb 18, 2026Updated 8 months ago
- SWE-Serve: an agentic benchmark of 53 production inference-engineering tasks derived from merged SGLang pull requests, run with Harbor.☆20Oct 9, 2026Updated 2 weeks ago
- 适用于东南大学学生的工具集合☆18Sep 10, 2025Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- A tool for model sparse based on torch.fx☆13Jun 3, 2024Updated 2 years ago
- [CoRL2026] MotionVLA: Injecting Geometric Motion into Vision-Language-Action Model☆20Sep 7, 2026Updated last month
- Official implementation of "Diffusion Language Models Know the Answer Before Decoding"☆61Apr 28, 2026Updated 5 months ago
- ☆11Jul 30, 2025Updated last year
- MIPS OS on R3000 (course assignment for BUAA-Operating-System)☆23Mar 16, 2022Updated 4 years ago
- (ICLR 2026 🔥) Code for "The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs"☆79Feb 9, 2026Updated 8 months ago
- code for the paper: Beyond Appearances: Material Segmentation with Embedded Spectral Information from RGB-D imagery☆10Jun 19, 2024Updated 2 years ago