The official repository for Trust-Region Adaptive Policy Optimization (TRAPO) – a novel hybrid framework designed to enhance large language models' reasoning abilities by interleaving SFT and RL within each training instance.
☆16Mar 2, 2026Updated 7 months ago
Alternatives and similar repositories for TRAPO
Users that are interested in TRAPO are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ACL 2026] G2RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance☆16Sep 15, 2026Updated last month
- ☆11Dec 26, 2025Updated 10 months ago
- [ICLR' 26] The PyTorch implementation of our paper: "Getting Your LLMs Ready for Reinforcement Learning with Lightweight SFT".☆14Feb 15, 2026Updated 8 months ago
- ☆29Sep 7, 2026Updated last month
- ☆14Aug 7, 2023Updated 3 years 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.
- ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models☆19Sep 17, 2026Updated last month
- Data World: Scaling Data Environments from Scratch☆30Oct 18, 2026Updated last week
- UFT: Unifying Supervised and Reinforcement Fine-Tuning☆34Jun 30, 2025Updated last year
- [COLING2022] A Multi-turn Machine Reading Comprehension Framework with Rethink Mechanism for Emotion-Cause Pair Extraction☆18Oct 13, 2022Updated 4 years ago
- Official implementation for "Pruning Large Language Models with Semi-Structural Adaptive Sparse Training" (AAAI 2025)☆20Jul 1, 2025Updated last year
- UECA-Prompt: Universal Prompt for Emotion Cause Analysis（COLING 2022）☆16Jun 6, 2023Updated 3 years ago
- [EMNLP 2025] Self-Guided Function Calling in Large Language Models via Stepwise Experience Recall☆11Sep 29, 2025Updated last year
- Official repository of paper "Context-DPO: Aligning Language Models for Context-Faithfulness"☆24Feb 17, 2025Updated last year
- A reproducible evaluation toolkit on spatial and embodied-intelligence benchmarks.☆26Sep 15, 2026Updated last month
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- 基于深度学习的文本分类，实现基于CNN和RNN的文本分类☆11Sep 20, 2021Updated 5 years ago
- ☆18Jul 8, 2025Updated last year
- ☆14Jun 18, 2026Updated 4 months ago
- Eat your GPUs☆26Dec 31, 2020Updated 5 years ago
- cheatbench.ai☆18Updated this week
- ☆13May 20, 2026Updated 5 months ago
- Code for ICML 2021 submission☆35Mar 24, 2021Updated 5 years ago
- [NeurIPS 2026 Verify-Agents] SWE-Touch: Benchmarking Coding Agents When Users Touch the Code☆18Aug 4, 2026Updated 2 months ago
- ☆10Jul 10, 2025Updated last year
- 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.
- ☆12May 14, 2026Updated 5 months ago
- WideSeek: Advancing Wide Research via Multi-Agent Scaling☆14Feb 4, 2026Updated 8 months ago
- Initial Exploratory Works on Knowledge Tracing in Transformer Based Language Models☆12Feb 21, 2024Updated 2 years ago
- PhysBrain 1.5: From General VLMs to Physical Foundation Model☆50Sep 15, 2026Updated last month
- Evaluation harness and tooling for measuring model compliance with the OpenAI Model Spec.☆22Mar 24, 2026Updated 7 months ago
- ☆28Aug 4, 2026Updated 2 months ago
- Designing effective multimodal environment distributions beyond simply environment scaling.☆16Aug 4, 2026Updated 2 months ago
- fastapi langchain javascript, streaming response 手写效果流式响应☆15Oct 27, 2023Updated 3 years ago
- ☆18Aug 7, 2026Updated 2 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- [NeurIPS 2024 poster] Cross-model Control: Improving Multiple Large Language Models in One-time Training☆15Oct 25, 2024Updated 2 years ago
- Materials for "Multi-property Steering of Large Language Models with Dynamic Activation Composition"☆14Nov 22, 2024Updated last year
- ☆24Sep 12, 2023Updated 3 years ago
- Official Repository for our paper: AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constra…☆28Sep 19, 2026Updated last month
- [NeurIPS 2026 Meta-Agents] PostTrainBench⁰ — Can LLM agents automate LLM post-training without gradients?☆16Sep 4, 2026Updated last month
- [AAAI2024] Debiasing Multimodal Sarcasm Detection with Contrastive Learning☆17Jan 5, 2024Updated 2 years ago
- [NeurIPS 2026 Meta-Agents] SAEScientist-Bench: Can AI agents conduct autonomous SAE interpretability research?☆21Sep 10, 2026Updated last month