Official implementation of BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning. BandPO replaces canonical clipping (PPO/GRPO) with dynamic bounds to resolve exploration bottlenecks and prevent entropy collapse.
☆49Apr 8, 2026Updated 4 months ago
Alternatives and similar repositories for BandPO
Users that are interested in BandPO are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICML'25] "Rethinking Addressing in Language Models via Contextualized Equivariant Positional Encoding" by Jiajun Zhu, Peihao Wang, Ruisi…☆15Jun 6, 2025Updated last year
- ☆143Jun 24, 2026Updated last month
- ☆25Jul 20, 2025Updated last year
- Official Repository for paper "HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding" [ACL 2026]☆94May 8, 2026Updated 3 months ago
- ☆24Nov 16, 2025Updated 8 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.
- MOSS-Audio-Tokenizer is a Causal Transformer-based audio tokenizer built on the CAT architecture. Trained on 3M hours of diverse audio, i…☆250Jun 16, 2026Updated last month
- [ICML 2026] Prism: Spectral-Aware Block-Sparse Attention☆27May 22, 2026Updated 2 months ago
- Official code for paper "GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable R…☆67Mar 29, 2026Updated 4 months ago
- ☆34Sep 15, 2025Updated 10 months ago
- Source Code for our ICLR'26 paper☆17Feb 22, 2026Updated 5 months ago
- ☆22Jan 29, 2026Updated 6 months ago
- MOSS-VL is the core multimodal model series within the OpenMOSS ecosystem, dedicated to visual understanding.☆410Updated this week
- A tool for better use of Inspire platform (Beta: Codeberg version is more up-to-date)☆29Apr 2, 2026Updated 4 months ago
- We introduce 'Thinking with Video', a new paradigm leveraging video generation for multimodal reasoning. Our VideoThinkBench shows that S…☆316Jun 21, 2026Updated last month
- 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.
- Official Repo for DAC-RL: Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability☆16Feb 26, 2026Updated 5 months ago
- The demo page for ALMTokenizer☆59Apr 14, 2025Updated last year
- [arxiv: 2604.14142] From P(y|x) to P(y): Investigating Reinforcement Learning in Pre-train Space☆17Apr 16, 2026Updated 3 months ago
- MOSS-Music is an open-source music understanding model for targeting musical captioning, lyrics ASR, structural analysis, chord / key / t…☆128May 9, 2026Updated 3 months ago
- Agent-Omit: Training Efficient LLM Agents for Adaptive Thought and Observation Omission via Reinforcement Learning☆33May 11, 2026Updated 2 months ago
- MOSS-Audio is an open-source foundation model for unified audio understanding, enabling speech, sound, music, captioning, QA, and reasoni…☆627Jun 2, 2026Updated 2 months ago
- The official repository for the paper “NonVerbalSpeech-38K: A Scalable Pipeline for Enabling Non-Verbal Speech Generation and Understandi…☆68Dec 26, 2025Updated 7 months ago
- ☆54Jun 25, 2025Updated last year
- We propose Reinforcement Learning from Community Feedback (RLCF), a training paradigm that uses large-scale community signals as supervis…☆428Jul 22, 2026Updated 2 weeks ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- A Rust library that converts TeX code to Typst code.☆15Jun 19, 2026Updated last month
- ☆27Jan 22, 2026Updated 6 months ago
- 启智平台任务管理 CLI：资源查询、任务提交、日志查看和 MCP/agent workflow☆117Updated this week
- 小程序反编译(支持分包)☆14May 7, 2021Updated 5 years ago
- Synth-Empathy: Towards High-Quality Synthetic Empathy Data☆18Feb 28, 2025Updated last year
- UnifiedToolHub is a comprehensive project supporting LLM-based tool use, designed to unify various tool-use dataset formats and provide t…☆22Jul 23, 2025Updated last year
- Drop-in async file-based handoff protocol for two AI coding agents (Claude Code + Codex), installed as one shared .handoff/ in your proje…☆31Jul 4, 2026Updated last month
- ☆19Jul 1, 2026Updated last month
- ☆19Oct 28, 2025Updated 9 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- [arXiv] "Linear Dynamics in the RLVR Training of Large Language Models"☆17May 25, 2026Updated 2 months ago
- Modular OSINT and attack surface analysis platform for authorized security research, with risk scoring, attack paths, and report generati…☆84Jun 4, 2026Updated 2 months ago
- LEMAS‑Edit is a multilingual speech editing system, supporting 10 languages: Chinese English Spanish Russian French German Italian Portug…☆21Mar 31, 2026Updated 4 months ago
- [CVPR 2025] DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval☆22Jun 23, 2025Updated last year
- Benchmark suit for large scale socio-technical datasets in open collaboration☆12Oct 12, 2024Updated last year
- [ICML2026] Official Implementation of AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in Unified Multimodal Models via Decompo…☆73Jul 27, 2026Updated 2 weeks ago
- 一个面向启智平台（Inspire）的 awesome list☆37Mar 29, 2026Updated 4 months ago