SFT+RL boosts multimodal reasoning
☆47Jun 27, 2025Updated last year
Alternatives and similar repositories for RL-with-Cold-Start
Users that are interested in RL-with-Cold-Start are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [NeurIPS 2025] First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training☆88Oct 29, 2025Updated 9 months ago
- ☆22Jan 9, 2026Updated 7 months ago
- (ArXiv25) Vision Matters: Simple Visual Perturbations Can Boost Multimodal Math Reasoning☆60Sep 30, 2025Updated 10 months ago
- Archer2.0 evolves from its predecessor by introducing ASPO, which overcomes fundamental PPO-Clip limitations to prevent premature converg…☆31Oct 10, 2025Updated 10 months ago
- [NeurIPS 2024] A Novel Rank-Based Metric for Evaluating Large Language Models☆59May 28, 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.
- [AAAI 2026] Relation-R1: Progressively Cognitive Chain-of-Thought Guided Reinforcement Learning for Unified Relation Comprehension☆20Mar 6, 2026Updated 5 months ago
- ☆20May 20, 2025Updated last year
- [ICLR 2026]🚀ReVisual-R1 is a 7B open-source multimodal language model that follows a three-stage curriculum—cold-start pre-training, mul…☆211Dec 10, 2025Updated 8 months ago
- Your efficient and accurate answer verification system for RL training.☆42Jun 23, 2025Updated last year
- DeepDubber-V1: Towards High Quality and Dialogue, Narration, Monologue Adaptive Movie Dubbing Via Multi-Modal Chain-of-Thoughts Reasoning…☆30Sep 7, 2025Updated 11 months ago
- Reproduction of the first step in the text-to-video model Phenaki. Code and model weights for the Transformer-based autoencoder for video…☆29Aug 4, 2023Updated 3 years ago
- The official repository of UniHGKR: Unified Instruction-aware Heterogeneous Knowledge Retrievers☆27Jun 12, 2025Updated last year
- Official code for DeepSound-V1☆12May 14, 2025Updated last year
- ☆72Feb 27, 2026Updated 5 months 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.
- [ICCV 2025] A Benchmark for Multi-Step Reasoning in Long Narrative Videos☆28Jun 4, 2026Updated 2 months ago
- [ICLR 2025] "Understanding Constraint Inference in Safety-Critical Inverse Reinforcement Learning"☆16Nov 30, 2025Updated 8 months ago
- (NIPS 2025) OpenOmni: Official implementation of Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Align…☆143May 9, 2026Updated 3 months ago
- [ACL'25] UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench☆36Aug 12, 2025Updated last year
- ☆17May 13, 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
- ☆20Nov 27, 2025Updated 8 months ago
- ☆18May 14, 2025Updated last year
- [ICML2025] Official Code of From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection☆27Jun 27, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆16Aug 11, 2025Updated last year
- Official code repository of Shuffle-R1☆26Feb 23, 2026Updated 5 months ago
- AdaRFT: Efficient Reinforcement Finetuning via Adaptive Curriculum Learning☆57Jun 13, 2025Updated last year
- [EMNLP 2025] Official code for the paper "SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning"☆16May 12, 2026Updated 3 months ago
- ArcherCodeR is an open-source initiative enhancing code reasoning in large language models through scalable, rule-governed reinforcement …☆44Aug 6, 2025Updated last year
- [NeurIPS'25] Backdoor Cleaning without External Guidance in MLLM Fine-tuning☆20Oct 13, 2025Updated 10 months ago
- 一个基于LLaMA-Factory框架对Qwen3-4B模型进行监督微调(SFT)的项目，专注于中文医疗健康领域的问答任务。项目使用QLoRA方法（4-bit量化+LoRA）对模型进行高效微调，训练数据来自Huatuo26M-Lite中文医疗问答数据集，包含约26000个医…☆16Jul 4, 2026Updated last month
- Official implementation of GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents☆254May 5, 2025Updated last year
- Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme☆149Apr 9, 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.
- ☆17Feb 4, 2026Updated 6 months ago
- SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward☆94Aug 8, 2025Updated last year
- This repository provides valuable reference for researchers in the field of multimodality, please start your exploratory travel in RL-bas…☆1,440Aug 2, 2026Updated last week
- [NeurIPS'25] Official Repository for the Paper "SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning"☆145Nov 20, 2025Updated 8 months ago
- finetune script for SDXL adapted from waifu-diffusion trainer☆11Aug 21, 2023Updated 2 years ago
- Codes for ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding [ICML 2025]]☆50Jul 22, 2025Updated last year
- Code for paper: Reinforced Vision Perception with Tools☆73Oct 3, 2025Updated 10 months ago