bigai-ai / ICELinks
γICLR 2025 π₯γThe code for Consistent In-Context Editing, an approach for tuning language models through contextual distributions, overcoming the limitations of traditional fine-tuning methods that learn towards one-hot targets.
β44Updated 4 months ago
Alternatives and similar repositories for ICE
Users that are interested in ICE are comparing it to the libraries listed below
Sorting:
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.β275Updated 3 weeks ago
- β46Updated 3 months ago
- β322Updated last week
- β155Updated 2 months ago
- β252Updated last month
- [ACL' 25] The official code repository for PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models.β76Updated 5 months ago
- A comprehensive collection of process reward models.β96Updated 2 weeks ago
- Implementation for the research paper "Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision".β56Updated 8 months ago
- β117Updated 4 months ago
- One-shot Entropy Minimizationβ172Updated last month
- Extrapolating RLVR to General Domains without Verifiersβ134Updated last week
- [ICML 2025] M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoningβ63Updated 3 weeks ago
- [NeurIPS 2024] The official implementation of paper: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.β125Updated 4 months ago
- β46Updated 2 months ago
- Official codebase for "GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning".β80Updated 2 months ago
- CoT-Valve: Length-Compressible Chain-of-Thought Tuningβ81Updated 5 months ago
- Paper List of Inference/Test Time Scaling/Computingβ286Updated last month
- Laser: Learn to Reason Efficiently with Adaptive Length-based Reward Shapingβ52Updated 2 months ago
- β203Updated 4 months ago
- [ICML'25] Our study systematically investigates massive values in LLMs' attention mechanisms. First, we observe massive values are concenβ¦β75Updated last month
- β258Updated 2 months ago
- Implementation for the paper "The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning"β83Updated 3 weeks ago
- This repository contains a regularly updated paper list for LLMs-reasoning-in-latent-space.β142Updated 2 weeks ago
- Official Repository of "Learning to Reason under Off-Policy Guidance"β268Updated 3 weeks ago
- RM-R1: Unleashing the Reasoning Potential of Reward Modelsβ118Updated last month
- [2025-TMLR] A Survey on the Honesty of Large Language Modelsβ58Updated 7 months ago
- Reference implementation for Token-level Direct Preference Optimization(TDPO)β143Updated 5 months ago
- [NeurIPS 2024 Oral] Aligner: Efficient Alignment by Learning to Correctβ181Updated 6 months ago
- β78Updated last year
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibratiβ¦β40Updated last year