MingLiiii / Layer_GradientLinks
[ACL'25 Oral] What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective
☆74Updated 3 months ago
Alternatives and similar repositories for Layer_Gradient
Users that are interested in Layer_Gradient are comparing it to the libraries listed below
Sorting:
- [COLING'25] Exploring Concept Depth: How Large Language Models Acquire Knowledge at Different Layers?☆80Updated 8 months ago
- ☆127Updated 6 months ago
- [ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction☆82Updated 6 months ago
- ☆132Updated 3 weeks ago
- A Sober Look at Language Model Reasoning☆83Updated 3 weeks ago
- Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate" [COLM 2025]☆172Updated 2 months ago
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆120Updated last year
- [ICLR 25 Oral] RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style☆62Updated 2 months ago
- [NeurIPS 2024] The official implementation of paper: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.☆128Updated 6 months ago
- RL Scaling and Test-Time Scaling (ICML'25)☆111Updated 8 months ago
- Official repository for Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning [ICLR 2025]☆48Updated 8 months ago
- General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]☆174Updated 3 months ago
- [EMNLP 2025] LightThinker: Thinking Step-by-Step Compression☆104Updated 5 months ago
- Unofficial Implementation of Chain-of-Thought Reasoning Without Prompting☆33Updated last year
- Function Vectors in Large Language Models (ICLR 2024)☆180Updated 5 months ago
- AnchorAttention: Improved attention for LLMs long-context training☆212Updated 8 months ago
- [ICML 2025] Teaching Language Models to Critique via Reinforcement Learning☆111Updated 5 months ago
- RM-R1: Unleashing the Reasoning Potential of Reward Models☆137Updated 3 months ago
- Code and Data for "Long-context LLMs Struggle with Long In-context Learning" [TMLR2025]☆108Updated 7 months ago
- Large Language Models Can Self-Improve in Long-context Reasoning☆73Updated 10 months ago
- [NeurIPS 2024] Knowledge Circuits in Pretrained Transformers☆157Updated 7 months ago
- Code for Heima☆53Updated 5 months ago
- ☆333Updated 2 months ago
- FeatureAlignment = Alignment + Mechanistic Interpretability☆29Updated 6 months ago
- JudgeLRM: Large Reasoning Models as a Judge☆39Updated 2 weeks ago
- Co-LLM: Learning to Decode Collaboratively with Multiple Language Models☆121Updated last year
- Revisiting Mid-training in the Era of Reinforcement Learning Scaling☆176Updated 2 months ago
- This is an official implementation of the Reward rAnked Fine-Tuning Algorithm (RAFT), also known as iterative best-of-n fine-tuning or re…☆37Updated last year
- Official PyTorch Implementation of EMoE: Unlocking Emergent Modularity in Large Language Models [main conference @ NAACL2024]☆35Updated last year
- ☆192Updated 5 months ago