ZBox1005 / CoT-UQLinks
[arXiv 2025] "CoT-UQ: Improving Response-wise Uncertainty Quantification in LLMs with Chain-of-Thought"
☆11Updated 2 months ago
Alternatives and similar repositories for CoT-UQ
Users that are interested in CoT-UQ are comparing it to the libraries listed below
Sorting:
- ☆116Updated last month
- Code for Heima☆44Updated last month
- The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning"☆103Updated 2 weeks ago
- OpenVLThinker: An Early Exploration to Vision-Language Reasoning via Iterative Self-Improvement☆88Updated 2 weeks ago
- [Preprint 2025] Thinkless: LLM Learns When to Think☆125Updated this week
- [ACL 2025] A Generalizable and Purely Unsupervised Self-Training Framework☆60Updated this week
- ☆27Updated last month
- NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation☆65Updated this week
- What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective☆64Updated 3 months ago
- Auto Interpretation Pipeline and many other functionalities for Multimodal SAE Analysis.☆132Updated 4 months ago
- (CVPR 2025) Official implementation to DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation which outperforms SOTA…☆22Updated last month
- Github repository for "Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging" (ICML 2025)☆51Updated last week
- [ACL 2025 Findings] Implicit Reasoning in Transformers is Reasoning through Shortcuts☆14Updated 2 months ago
- This is the repository for NAACL'25 paper "TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoning"☆53Updated last month
- Ruler: A Model-Agnostic Method to Control Generated Length for Large Language Models☆35Updated 8 months ago
- [ACL 2025] Knowledge Unlearning for Large Language Models☆34Updated last month
- official code for "BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning"☆35Updated 4 months ago
- Pixel-Level Reasoning Model trained with RL☆92Updated this week
- Code for paper "Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models."☆42Updated 7 months ago
- Initialization using Update Approximation is a Silver Bullet for Extremely Efficient Low-Rank Fine-Tuning☆47Updated 3 months ago
- The code implementation of Symbolic-MoE☆31Updated 2 months ago