[ICML 2025] M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning
☆71Jul 13, 2025Updated 7 months ago
Alternatives and similar repositories for mstar
Users that are interested in mstar are comparing it to the libraries listed below
Sorting:
- [ICLR2026] Laser: Learn to Reason Efficiently with Adaptive Length-based Reward Shaping☆63May 22, 2025Updated 9 months ago
- [ACL' 25] The official code repository for PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models.☆88Feb 15, 2025Updated last year
- B-STAR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners☆86May 21, 2025Updated 9 months ago
- ✈️ [ICCV 2025] Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints☆79Jul 10, 2025Updated 7 months ago
- ☆129Jun 6, 2025Updated 9 months ago
- instruction-following benchmark for large reasoning models☆44Aug 9, 2025Updated 6 months ago
- 🚀 LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training☆91Dec 3, 2024Updated last year
- Code and data for "Timo: Towards Better Temporal Reasoning for Language Models" (COLM 2024)☆25Oct 23, 2024Updated last year
- Open-Pandora: On-the-fly Control Video Generation☆35Nov 28, 2024Updated last year
- ☆16Oct 12, 2025Updated 4 months ago
- ☆122Feb 4, 2026Updated last month
- [ICML 2025] Official Implementation of GLIDER☆72Oct 9, 2025Updated 4 months ago
- 🍼 Official implementation of Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts☆41Sep 29, 2024Updated last year
- ☆66Jul 8, 2025Updated 7 months ago
- The official code repository for the FullFront benchmark☆26May 16, 2025Updated 9 months ago
- [CVPR' 25] Official repo for From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Cal…☆21Jun 6, 2025Updated 9 months ago
- Code and data for "Living in the Moment: Can Large Language Models Grasp Co-Temporal Reasoning?" (ACL 2024)☆32Jul 3, 2024Updated last year
- [KernelGYM & Dr. Kernel] A distributed GPU environment and a collection of RL training methods to support RL for Kernel Generations☆121Feb 6, 2026Updated last month
- Test-time preferenece optimization (ICML 2025).☆178May 8, 2025Updated 9 months ago
- [ICML 2025 Oral] The official repository for the paper "Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchma…☆69Jul 17, 2025Updated 7 months ago
- Code and data for "ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLM" (NeurIPS 2024 Track Datasets and…☆65May 16, 2025Updated 9 months ago
- [ICLR 2026] The official repository for the paper "AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning".☆72Feb 27, 2026Updated last week
- ☆23Oct 30, 2025Updated 4 months ago
- [CVPR 2026] TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models☆64Feb 21, 2026Updated 2 weeks ago
- [FSE'2026] SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks☆156Updated this week
- code for Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning☆20Jul 16, 2024Updated last year
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆417Oct 4, 2025Updated 5 months ago
- Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoning☆136Updated this week
- 😎 A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, Agent, and Beyond☆347Jan 22, 2026Updated last month
- Official Implementation of ACL2023: Don't Parse, Choose Spans! Continuous and Discontinuous Constituency Parsing via Autoregressive Span …☆14Aug 25, 2023Updated 2 years ago
- Codes for ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding [ICML 2025]]☆45Jul 22, 2025Updated 7 months ago
- [NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*☆121Dec 10, 2024Updated last year
- OpenThinkIMG is an end-to-end open-source framework that empowers LVLMs to think with images.☆354Jun 1, 2025Updated 9 months ago
- Aligning Agentic World Models via Knowledgeable Experience Learning☆31Jan 25, 2026Updated last month
- Use the tokenizer in parallel to achieve superior acceleration☆20Mar 21, 2024Updated last year
- (ICML 2025) Rethinking Chain-of-Thought from the Perspective of Self-Training☆13Feb 15, 2025Updated last year
- From Accuracy to Robustness: A Study of Rule- and Model-based Verifiers in Mathematical Reasoning.☆25Oct 7, 2025Updated 5 months ago
- Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]☆589Dec 9, 2024Updated last year
- Revisiting Mid-training in the Era of Reinforcement Learning Scaling☆183Jul 23, 2025Updated 7 months ago