TIGER-AI-Lab / One-Shot-CFTLinks
The official repo for “Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem”
☆19Updated last month
Alternatives and similar repositories for One-Shot-CFT
Users that are interested in One-Shot-CFT are comparing it to the libraries listed below
Sorting:
- Official Repo for RuleReasoner.☆24Updated last month
- Resa: Transparent Reasoning Models via SAEs☆41Updated last month
- A Recipe for Building LLM Reasoners to Solve Complex Instructions☆20Updated 2 weeks ago
- The official implementation of Regularized Policy Gradient (RPG) (https://arxiv.org/abs/2505.17508)☆35Updated this week
- AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents☆25Updated last month
- A holistic benchmark for LLM abstention☆41Updated last week
- CLaMR: Contextualized Late-Interaction for Multimodal Content Retrieval☆17Updated last month
- [ACL2025 Findings] Benchmarking Multihop Multimodal Internet Agents☆46Updated 5 months ago
- Code for Paper: Harnessing Webpage Uis For Text Rich Visual Understanding☆52Updated 7 months ago
- ☆37Updated last month
- Nexusflow function call, tool use, and agent benchmarks.☆27Updated 7 months ago
- ☆19Updated 5 months ago
- ☆24Updated last month
- ☆47Updated last month
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆33Updated last week
- [ACL 2025] Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems☆97Updated last month
- Official Repo for SwS: A Weakness-driven Problem Synthesis Framework in RL for LLM Reasoning☆24Updated last month
- [ACL 2025] A Generalizable and Purely Unsupervised Self-Training Framework☆67Updated 2 months ago
- Official Repository for Task-Circuit Quantization☆21Updated 2 months ago
- ☆20Updated 3 months ago
- Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning☆33Updated last month
- Pytorch implementation of HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models☆28Updated last year
- C^3-Bench: The Things Real Disturbing LLM based Agent in Multi-Tasking☆26Updated last month
- OpenVLThinker: An Early Exploration to Vision-Language Reasoning via Iterative Self-Improvement☆102Updated last week
- ☆13Updated 7 months ago
- Repository for the Q-Filters method (https://arxiv.org/pdf/2503.02812)☆34Updated 4 months ago
- [NeurIPS 2024] A task generation and model evaluation system for multimodal language models.☆72Updated 8 months ago
- Code for "From Ideal to Real: Unified and Data-Efficient Dense Prediction for Real-World Scenarios"☆26Updated 3 weeks ago
- ☆14Updated last month
- ☆47Updated 5 months ago