Staleness-Adaptive Trust Region (SAT), a directional, token-adaptive clipping method for stabilizing asynchronous reinforcement learning of large language models.
☆22Jul 22, 2026Updated 3 months ago
Alternatives and similar repositories for SAT
Users that are interested in SAT are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Very simple regulation can mitigate reconstruction-generation gap.☆17Oct 1, 2026Updated 3 weeks ago
- Official Codebase of "Terminal-RSI: Recursive Self-Improving Terminal Agents via Recursive Self-Rewrite and Policy-Refine"☆31Updated this week
- 🔥[ICLR'26] Official repository for the paper "Long-Document QA with Chain-of-Structured-Thought and Fine-Tuned SLMs"☆12Apr 16, 2026Updated 6 months ago
- Advancing Foundation GUI Agents with In-Context Demonstrations☆112Sep 1, 2026Updated last month
- [NeurIPS 2026] Code for our resarch paper "SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking"☆67Sep 14, 2026Updated last month
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Repo for "AutoTrainess: Teaching Language Models to Improve Language Models Autonomously"☆22Aug 3, 2026Updated 2 months ago
- Official repository for “From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning”“☆25Jun 15, 2026Updated 4 months ago
- ☆37Sep 21, 2026Updated last month
- Benchmarking Multi-Image Understanding in Vision and Language Models☆11Jul 29, 2024Updated 2 years ago
- Multimodal Video Generation Model, research, unified models, applications collection.☆13Aug 21, 2026Updated 2 months ago
- Open-X-Tactile Quality Check☆21Updated this week
- Exploring Multi-Session Agentic Reinforcement Learning☆38Oct 16, 2026Updated last week
- BeeDrive: Open Source Privacy File Transfering System for Teams and Individual Developers☆12Mar 12, 2024Updated 2 years ago
- The paper list of the survey "The Past Frames the Future: Memory Mechanisms for Autoregressive Video Generation"☆97Oct 18, 2026Updated last week
- 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.
- [TACL/EMNLP'24] Do Vision and Language Models Share Concepts? A Vector Space Alignment Study☆16Nov 22, 2024Updated last year
- UI-MOPD Official Implementation☆61Aug 10, 2026Updated 2 months ago
- ☆16Sep 13, 2026Updated last month
- CoCoFL: Communication- and Computation-Aware Federated Learning via Partial NN Freezing and Quantization☆12Aug 3, 2024Updated 2 years ago
- A code base for the third place solution of Ego-Exo4D bodypose challenge for CVPR2024 workshop☆12Jun 16, 2024Updated 2 years ago
- grpo to train long form QA and instructions with long-form reward model☆17Jul 17, 2025Updated last year
- Code for Trajectory-Level Speculation with Semantic Verification for Tool-Using Agents☆26Oct 16, 2026Updated last week
- Official code for HiLS-Attention☆151Aug 13, 2026Updated 2 months ago
- Community Implementation of paper "Inference-Time Scaling for Generalist Reward Modeling"☆11Apr 21, 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.
- A second brain for your business or personal needs☆13Jan 21, 2026Updated 9 months ago
- Agentic Long-Horizon Planning☆16Jul 27, 2026Updated 3 months ago
- ☆17Jun 15, 2026Updated 4 months ago
- Weekly seminar on computational theory☆14Oct 16, 2025Updated last year
- A curated, domain-organized list of robotics benchmarks—manipulation, locomotion, navigation, HRI, safety, simulation—summarized in conci…☆17Aug 23, 2025Updated last year
- Implementation for PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs☆24Jun 6, 2024Updated 2 years ago
- Find source context and trace calls across languages in Claude Code, Codex and other MCP agents.☆87Updated this week
- ☆18Oct 5, 2025Updated last year
- An implement of guandan game, known as 掼蛋.☆10Jan 7, 2026Updated 9 months ago
- 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.
- From original DROPBOX code☆13Sep 18, 2023Updated 3 years ago
- ☆17Jun 13, 2026Updated 4 months ago
- ☆339Aug 11, 2026Updated 2 months ago
- Leetcode & 剑指offer 解题☆15Apr 27, 2022Updated 4 years ago
- [NeurIPS2023] Black-box Backdoor Defense via Zero-shot Image Purification☆17Oct 31, 2023Updated 2 years ago
- COS-PLAY: Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Game Play☆31Jul 11, 2026Updated 3 months ago
- [NeurIPS 2024] Self-Optimization Improves the Efficiency of Code Generation☆15May 10, 2025Updated last year