[NeurIPS-2026] The PyTorch Implementation of RFT-Inf. The algorithms are based on our paper: "Understanding Data Influence in Reinforcement Finetuning". To the best of our knowledge, this is the first work to analyze data influence in Reinforcement Learning (RL).
☆23May 21, 2026Updated 4 months ago
Alternatives and similar repositories for RFT-INF
Users that are interested in RFT-INF are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICLR-2026] The PyTorch Implementation of FastMix. The algorithms are based on our paper: "Fast Data Mixture Optimization via Gradient De…☆32Jun 10, 2026Updated 4 months ago
- [CVPR-2026] The PyTorch Implementation of DIEM. The algorithms are based on our paper: "Dynamic Important Example Mining for Reinforcemen…☆51Sep 1, 2026Updated last month
- Local-first OCR-VLM multimodal document retrieval and independent evaluation prototype.☆41Aug 13, 2026Updated 2 months ago
- A jelly-glass, themeable Windows desktop task board with calendar, notes, and local data storage.☆99Aug 17, 2026Updated 2 months ago
- ACL 2026 Code and Skills for “AMA: Adaptive Memory via Multi-Agent Collaboration”.☆114Sep 8, 2026Updated last month
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- A Mini-vLLM optimization project for Qwen3-32B TP=2 serving, Prefix Cache, and Triton PagedAttention.☆102Aug 6, 2026Updated 2 months ago
- AI coding agent harness. Five modes: practice to playoffs. Stop your AI from over-engineering. Code like a man. Elbow out bloat. Score cl…☆359Sep 20, 2026Updated 3 weeks ago
- ☆114Jul 10, 2026Updated 3 months ago
- Graybox camera previs tool driven by natural-language shot descriptions.☆239Aug 11, 2026Updated 2 months ago
- [ICML 2026] Official Repo For "Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models"☆87Jul 1, 2026Updated 3 months ago
- 基于 Java、Spring Boot 与 LangChain4j 的长视频 Agent，支持 ASR/OCR 多模态解析、重叠分块 RAG、RocketMQ 异步任务与可恢复分析。☆37Updated this week
- ☆96Updated this week
- AI动画制作☆97May 26, 2026Updated 4 months ago
- Have a good life☆197Sep 12, 2026Updated last month
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- AI-powered rehabilitation platform for guided triage, personalized daily rehab, and clinician-supported recovery.☆30Oct 11, 2026Updated last week
- A local-first AI companion for books and films, with memory, ratings, reflections, and personalized recommendations.☆100Jul 24, 2026Updated 2 months ago
- ☆20Sep 28, 2026Updated 3 weeks ago
- ☆114Oct 3, 2026Updated 2 weeks ago
- A compact, schema-driven open source alternative to OpenAI ChatKit widgets.☆297Oct 8, 2026Updated last week
- A Kotlin Multiplatform starter project with Compose Multiplatform UI, shared modules, and a Ktor backend.☆33Jul 29, 2026Updated 2 months ago
- Community desktop companion for DeepSeek Harness — one-click Electron app for macOS and Windows☆705Sep 13, 2026Updated last month
- Lightweight, rule-based checks for missing, weak, and uncovered tests in pull requests.☆158Oct 5, 2026Updated 2 weeks ago
- Local AI PR workbench — Claude/Codex review in isolated git worktrees, human-gated GitHub comments☆489Sep 22, 2026Updated 3 weeks 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.
- GEO第一性原理：面向企业负责人的开源 GEO 分析 Skill。从行业竞争、客户需求与成交逻辑出发，判断是否适合做 GEO、价值在哪里、怎样投入，并提供重点场景、五题实测指引与行动建议。支持 Agent Skills 格式。☆305Sep 14, 2026Updated last month
- Official repository for the ACM MM 2026 Oral paper “Remember-R1: Mitigating Long-Context Visual Forgetting through Reinforcement Learning…☆419Aug 28, 2026Updated last month
- AntNest 是一个采用蚁后 / 工蚁架构（或蜂后 / 工蜂）的 AI 编程助手。你可以把它想象成一个蚁群： 蚁后（本体）：只负责思考、规划、决策。蚁后从不亲自执行任何命令。 工蚁（复制体）：蚁后需要干活时，会生成一只工蚁——把自身代码复制一份，派到隔离的临时目录里执行…☆40Updated this week
- ☆979Jul 22, 2026Updated 2 months ago
- Adversarial patch training and evaluation for YOLO with visible-to-infrared mapping☆31Aug 21, 2026Updated last month
- stock_trading_sim☆146Jul 24, 2026Updated 2 months ago
- A Benchmark Evaluating Triple-View Embodied World Models☆236Sep 23, 2026Updated 3 weeks ago
- OceanScale — GPU-native ocean simulator for underwater robotics (source alpha)☆102Aug 8, 2026Updated 2 months ago
- A professional web-based Rubik's Cube and speedcubing timer with official WCA scrambles and Stackmat support.☆98Sep 6, 2026Updated last month
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Book answer — 经典著作与导师人物 AI 思想蒸馏平台（React 19 + Express + SQLite，用户端支持简体中文 / 繁體中文 / English）☆101Oct 2, 2026Updated 2 weeks ago
- A digital minimalism prototype: Android/ADB, physical and camera inputs, BLE, Raspberry Pi and Waveshare e-paper.☆32Oct 10, 2026Updated last week
- Tracking the untrackable: A reinforcement learning framework for dynamic tracing of chromatin fountains/stripes☆15Jun 2, 2026Updated 4 months ago
- Reconcile stuck AI-agent tasks after restarts and timeouts. Preview SQLite changes, close stale delivery states, and never guess success.☆930Aug 25, 2026Updated last month
- Neighborhood-scale surface heat research pipeline and interactive Los Angeles atlas☆61Sep 21, 2026Updated 3 weeks ago
- ☆226Aug 27, 2026Updated last month
- GraphRAG Agent 是一个面向私有知识库的全栈图谱问答系统。它将文档上传、文本解析、分块、知识图谱抽取、索引任务编排、可视化编辑和问答记录整合在一个受认证保护的工作流中，并为多用户场景提供用户自带 API Key（BYOK）能力。☆33Sep 24, 2026Updated 3 weeks ago