[NeurIPS 2025] Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models
☆62Sep 29, 2025Updated last year
Alternatives and similar repositories for TON
Users that are interested in TON are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆23May 5, 2026Updated 5 months ago
- code for "CoMT: A Novel Benchmark for Chain of Multi-modal Thought on Large Vision-Language Models"☆19Mar 10, 2025Updated last year
- ☆18Jun 3, 2025Updated last year
- ☆19Jul 21, 2025Updated last year
- Evaluation code for RBench-V. Based on https://github.com/open-compass/VLMEvalKit.☆12May 24, 2025Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- [ICML 2026] Heima☆78May 20, 2026Updated 5 months ago
- ☆13Jan 5, 2026Updated 9 months ago
- This is the code repo for the paper AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play (NeurIPS 2025 Spotl…☆25Sep 29, 2025Updated last year
- ☆12May 20, 2026Updated 5 months ago
- ☆189Dec 5, 2025Updated 10 months ago
- Make reasoning models scalable☆51Jun 2, 2026Updated 5 months ago
- [ICML 2026] What Does Vision Tool-Use Reinforcement Learning Really Learn? Disentangling Tool-Induced and Intrinsic Effects for Crop-and-…☆23May 15, 2026Updated 5 months ago
- The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning" [NeurIPS25]☆192Jun 5, 2025Updated last year
- ☆70Jun 18, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Code for paper "CAPO: Towards Enhancing LLM Reasoning through Verifiable Generative Credit Assignment"☆12Dec 5, 2025Updated 10 months ago
- ☆17Apr 20, 2026Updated 6 months ago
- Chain-of-Frames [CVPR 2026]☆42Jul 2, 2025Updated last year
- OpenVLThinker [NeurIPS 2025] & OpenVLThinkerV2 [COLM 2026]☆159May 25, 2026Updated 5 months ago
- SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward☆95Aug 8, 2025Updated last year
- ☆82Jul 31, 2026Updated 3 months ago
- ☆76May 22, 2025Updated last year
- This is the implementation for the NeurIPS 2022 paper: ZIN: When and How to Learn Invariance Without Environment Partition?☆22Dec 3, 2022Updated 3 years ago
- Optimizing Anytime Reasoning via Budget Relative Policy Optimization☆54Jul 15, 2025Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Official code for AAAI2026 {Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Extreme Reasoning Efficiency in Large Languag…☆13Nov 24, 2025Updated 11 months ago
- Reinforcing General Reasoning without Verifiers☆103Jun 24, 2025Updated last year
- This is the office repository for ACL 2024 paper "Learning or Self-aligning? Rethinking Instruction Fine-tuning"☆11Aug 11, 2024Updated 2 years ago
- [ICLR' 26] Implementation of "Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning"☆24May 28, 2026Updated 5 months ago
- iLLaVA: An Image is Worth Fewer Than 1/3 Input Tokens in Large Multimodal Models (ICLR2026)☆23Jun 24, 2026Updated 4 months ago
- Repository for the paper: Aligning LLMs to Ask Good Questions A Case Study in Clinical Reasoning☆18Feb 21, 2025Updated last year
- Code and data for ACL 2024 paper on 'Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space'☆19Jul 21, 2024Updated 2 years ago
- [ICML 2026 Spotlight] Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback☆75Jun 3, 2026Updated 4 months ago
- 👾 E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding (NeurIPS 2024)☆73Jan 20, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- [NeurIPS'25] Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning☆17Dec 12, 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 last year
- ☆56Updated this week
- ☆138Jul 22, 2025Updated last year
- [ICLR 2023, ICLR DG oral] PAIR, the optimizer and model selection criteria for OOD Generalization☆54Apr 12, 2024Updated 2 years ago
- Resources for the Enigmata Project.☆86Aug 13, 2025Updated last year
- [EMNLP 2025 Findings] MEXA: Towards General Multimodal Reasoning with Dynamic Multi-Expert Aggregation☆15Aug 22, 2025Updated last year