[NeurIPS 2025] First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training
☆86Oct 29, 2025Updated 6 months ago
Alternatives and similar repositories for MM-UPT
Users that are interested in MM-UPT are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- SFT+RL boosts multimodal reasoning☆49Jun 27, 2025Updated 10 months ago
- The official implement of paper 《DaMo: Data Mixing Optimizer in Fine-tuning Multimodal LLMs for Mobile Phone Agents》☆31Oct 23, 2025Updated 6 months ago
- ☆23Jan 9, 2026Updated 4 months ago
- ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL (ICLR 2025 Pytorch Code)☆17May 15, 2025Updated last year
- ☆17Dec 23, 2025Updated 4 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.
- Code for Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation (EVOL-RL).☆50Mar 31, 2026Updated last month
- [NeurIPS 2025] NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation☆111Sep 18, 2025Updated 8 months ago
- Official repo for "PAPO: Perception-Aware Policy Optimization for Multimodal Reasoning"☆136Feb 4, 2026Updated 3 months ago
- (ArXiv25) Vision Matters: Simple Visual Perturbations Can Boost Multimodal Math Reasoning☆60Sep 30, 2025Updated 7 months ago
- Official implementation for the paper "Can Large Reasoning Models Self-Train?"☆75Oct 10, 2025Updated 7 months ago
- [AAAI 2026] Relation-R1: Progressively Cognitive Chain-of-Thought Guided Reinforcement Learning for Unified Relation Comprehension☆20Mar 6, 2026Updated 2 months ago
- ☆19Mar 10, 2025Updated last year
- This repository contains the code for our ICML 2025 paper——LENSLLM: Unveiling Fine-Tuning Dynamics for LLM Selection🎉☆26May 29, 2025Updated 11 months ago
- ☆16May 30, 2025Updated 11 months 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.
- ☆44Jan 4, 2026Updated 4 months ago
- TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models☆40Nov 10, 2024Updated last year
- The code for our paper "Label-Specific Feature Augmentation for Long-Tailed Multi-Label Text Classification”☆13Apr 20, 2023Updated 3 years ago
- LOCO-Edit☆28Oct 20, 2024Updated last year
- ☆13Jul 10, 2024Updated last year
- This is an implementation of the paper "Are We Done with Object-Centric Learning?"☆12Apr 12, 2026Updated last month
- ☆14Jan 22, 2025Updated last year
- [CVPR 2023] This repository contains code for the paper "FCC: Feature Clusters Compression for Long-Tailed Visual Recognition", accepted …☆23May 22, 2023Updated 3 years ago
- Scaling Multi-modal Instruction Fine-tuning with Tens of Thousands Vision Task Types☆32Jul 16, 2025Updated 10 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- [ACL 2026] R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning☆29Jan 4, 2026Updated 4 months ago
- ☆18Aug 19, 2025Updated 9 months ago
- [ICRA 2024]This is the official repo of paper "HR-APR: APR-agnostic Framework with Uncertainty Estimation and Hierarchical Refinement for…☆11Feb 10, 2025Updated last year
- Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoning☆15Jun 28, 2025Updated 10 months ago
- ☆133Jul 8, 2024Updated last year
- ☆24Jun 18, 2025Updated 11 months ago
- The first comprehensive multimodal language analysis benchmark for evaluating foundation models☆31Sep 22, 2025Updated 8 months ago
- [ACM MM25] LongWriter-V: Enabling Ultra-Long and High-Fidelity Generation in Vision-Language Models☆22Mar 29, 2025Updated last year
- This is the code for the paper Embrace the Gap: VAEs perform Independent Mechanism Analysis, showing that optimizing the ELBO is equivale…☆22Apr 22, 2024Updated 2 years 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.
- ABC: Achieving Better Control of Multimodal Embeddings using VLMs [TMLR2025]☆21Aug 21, 2025Updated 9 months ago
- Official implementation of Self-Taught Agentic Long Context Understanding (ACL 2025).☆13Sep 22, 2025Updated 8 months ago
- [ICLR 2025] Official Implementation of Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection☆51Jul 30, 2025Updated 9 months ago
- ☆13Jul 5, 2024Updated last year
- [ICLR 2026] RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling☆38Feb 25, 2026Updated 2 months ago
- Github repository for ACL 2025 paper: VoxEval: Benchmarking the Knowledge Understanding Capabilities of End-to-End Spoken Language Models☆24Jun 16, 2025Updated 11 months ago
- The open-source Mixture of Depths code and the official implementation of the paper "Router-Tuning: A Simple and Effective Approach for E…☆31May 12, 2026Updated last week