HJYao00 / Mulberry
Mulberry, an o1-like Reasoning and Reflection MLLM Implemented via Collective MCTS
β1,158Updated this week
Alternatives and similar repositories for Mulberry:
Users that are interested in Mulberry are comparing it to the libraries listed below
- [NeurIPS2024] Twin-Merging: Dynamic Integration of Modular Expertise in Model Mergingβ133Updated 2 weeks ago
- SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writingβ127Updated 2 weeks ago
- DeepRetrieval - Hacking π₯Real Search Engines and Text/Data Retrievers with LLM + RLβ201Updated this week
- R1-like Computer-use Agentβ63Updated last week
- [NeurIPS 2024] Matryoshka Query Transformer for Large Vision-Language Modelsβ102Updated 9 months ago
- Codebase for Iterative DPO Using Rule-based Rewardsβ230Updated this week
- Improving Generalist Model with Domain-Specific Expertsβ85Updated 2 months ago
- Intervening Anchor Token: Decoding Strategy in Alleviating Hallucinations for MLLMsβ154Updated 3 weeks ago
- adds Sequence Parallelism into LLaMA-Factoryβ437Updated last week
- β52Updated 3 weeks ago
- [NeurIPS'24] Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategyβ64Updated 2 months ago
- Official repository of MMGenBenchβ119Updated 3 weeks ago
- [ICLR 2025] Vision-Centric Evaluation for Retrieval-Augmented Multimodal Modelsβ36Updated 2 months ago
- Unified KV Cache Compression Methods for Auto-Regressive Modelsβ966Updated 2 months ago
- The codes about "Uni-MoE: Scaling Unified Multimodal Models with Mixture of Experts"β709Updated this week
- BIRD-CRITIC 1.0: Can Large Language Models Solve USER SQL Issues in Real-World Database Applications?β396Updated last month
- β¨ A synthetic dataset generation framework that produces diverse coding questions and verifiable solutions - all in one framworkβ176Updated last week
- [NeurIPS 2022] Official Code for REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answeringβ100Updated 6 months ago
- π₯ π₯ π₯ [NeurIPS 2024] Hawk: Learning to Understand Open-World Video Anomaliesβ190Updated 3 weeks ago
- DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Modelsβ129Updated 2 months ago
- [CVPR 2025] Official code for "Olympus: A Universal Task Router for Computer Vision Tasks"β54Updated this week
- β160Updated 5 months ago
- β1,380Updated 5 months ago
- The official implementation of MARS: Unleashing the Power of Variance Reduction for Training Large Modelsβ586Updated last month
- The Official Repo of ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code (https://aβ¦β292Updated 4 months ago
- (AAAI 2024) BLIVA: A Simple Multimodal LLM for Better Handling of Text-rich Visual Questionsβ256Updated 11 months ago
- Efficient DiT architecture for text2any tasks, ICLR2025β406Updated last month
- [Arxiv 2024] Official code for Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptationβ63Updated 8 months ago
- [ ICLR 2024 ] Official Codebase for "InstructCV: Instruction-Tuned Text-to-Image Diffusion Models as Vision Generalists"β462Updated 11 months ago
- [ICLR Workshop 2025] An official source code for paper "GuardReasoner: Towards Reasoning-based LLM Safeguards".β130Updated 3 weeks ago