A curated list of awesome LLM Inference-Time Self-Improvement (ITSI, pronounced "itsy") papers from our recent survey: A Survey on Large Language Model Inference-Time Self-Improvement.
☆110Dec 24, 2024Updated last year
Alternatives and similar repositories for Awesome-LLM-Self-Improvement
Users that are interested in Awesome-LLM-Self-Improvement are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆19Oct 28, 2025Updated 9 months ago
- List of papers on Self-Correction of LLMs.☆82May 19, 2026Updated 2 months ago
- Code of "Regularized Best-of-N Sampling with Minimum Bayes Risk Objective for Language Model Alignment" (2025).☆14Apr 4, 2025Updated last year
- JudgeLRM: Large Reasoning Models as a Judge☆42May 6, 2026Updated 3 months ago
- ☆19Oct 12, 2024Updated 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.
- [NeurIPS'24 LanGame workshop] On The Planning Abilities of OpenAI's o1 Models: Feasibility, Optimality, and Generalizability☆42Apr 10, 2026Updated 4 months ago
- Agentic Keyframe Search for Video Question Answering☆18Jun 30, 2026Updated last month
- A curated list of awesome resources dedicated to Scaling Laws for LLMs☆84Apr 10, 2023Updated 3 years ago
- PyTorch codes for the paper "An Empirical Study of Multimodal Model Merging"☆37Oct 11, 2023Updated 2 years ago
- A simple generate script utils using fastchat conv template for generation of Large Language Models☆21Jun 21, 2023Updated 3 years ago
- Extensive Self-Contrast Enables Feedback-Free Language Model Alignment☆20Apr 2, 2024Updated 2 years ago
- Large Language Models Can Self-Improve in Long-context Reasoning☆72Nov 24, 2024Updated last year
- ☆554Jan 2, 2025Updated last year
- [ICML 2025] Code for "R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts"☆19Mar 10, 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.
- Source code of ACL 2023 Main Conference Paper "PAD-Net: An Efficient Framework for Dynamic Networks".☆14Feb 28, 2026Updated 5 months ago
- Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments (Zhou et al., EMNLP 2024)☆14Oct 3, 2024Updated last year
- ☆54Mar 6, 2025Updated last year
- ☆187Dec 5, 2025Updated 8 months ago
- Ollie is a open information extractor that uses dependency parses.☆12Sep 27, 2013Updated 12 years ago
- ☆311Jul 6, 2025Updated last year
- ☆46Mar 4, 2025Updated last year
- [NeurIPS 2024 D&B Track] DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation☆14Mar 5, 2025Updated last year
- Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning☆39Nov 17, 2024Updated last year
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Codes for DATA: Differentiable ArchiTecture Approximation.☆11Jul 22, 2021Updated 5 years ago
- ☆31Mar 14, 2022Updated 4 years ago
- ☆47Jun 11, 2025Updated last year
- Official code for the paper: DRA-GRPO: Exploring Diversity-Aware Reward Adjustment for R1-Zero-Like Training of Large Language Models☆24Jan 6, 2026Updated 7 months ago
- ☆17Apr 11, 2025Updated last year
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆336Apr 24, 2025Updated last year
- (ACL 2025) MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale☆50Jun 4, 2025Updated last year
- CE-GPPO: Controlling Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning☆16Jan 23, 2026Updated 6 months ago
- official code for "BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning"☆37Jan 21, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆10Feb 13, 2023Updated 3 years ago
- ☆17Aug 1, 2025Updated last year
- Replicating O1 inference-time scaling laws☆94Dec 1, 2024Updated last year
- How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients☆20Jun 17, 2025Updated last year
- [IJCV 2026] HiPrompt: Tuning-free Higher-Resolution Generation with Hierarchical MLLM Prompts☆26Feb 28, 2025Updated last year
- Paper list for the paper "Authorship Attribution in the Era of Large Language Models: Problems, Methodologies, and Challenges (SIGKDD Exp…☆19May 25, 2026Updated 2 months ago
- Code for Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation (EVOL-RL).☆51Mar 31, 2026Updated 4 months ago