[NeurIPS 2025] What Makes a Reward Model a Good Teacher? An Optimization Perspective
☆45Sep 18, 2025Updated last year
Alternatives and similar repositories for what-makes-good-rm
Users that are interested in what-makes-good-rm are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICLR 2025] Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization☆32Jan 7, 2026Updated 10 months ago
- ☆70Jun 18, 2025Updated last year
- Output-Constrained Regression Trees (OCRT)☆13Sep 14, 2026Updated last month
- ☆13Jun 25, 2025Updated last year
- This repo contains code for paper: "Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approach".☆26Oct 21, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- LCA-on-the-line (ICML 2024 Oral)☆14Feb 13, 2025Updated last year
- Towards Understanding the Mixture-of-Experts Layer in Deep Learning☆37Dec 12, 2023Updated 2 years ago
- Based on the R1-Zero method, using rule-based rewards and GRPO on the Code Contests dataset.☆18Apr 22, 2025Updated last year
- [COLM 2025: 1st Workshop on the Application of LLM Explainability to Reasoning and Planning] Latent Chain-of-Thought? Decoding the Depth-…☆23Aug 19, 2026Updated 2 months ago
- [ICML 2026] Process Reward Agents for Steering Knowledge-Intensive Reasoning☆18Oct 5, 2026Updated last month
- This repository contains the replication of the iGSM dataset generation process from the Physics of LLM paper by Zeyuan Zhu.☆17Sep 13, 2024Updated 2 years ago
- MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level Supervision☆30May 26, 2025Updated last year
- [NeurIPS '25] Multi-Token Prediction Needs Registers☆35Dec 14, 2025Updated 10 months ago
- ☆17Aug 1, 2025Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- [ICLR26]GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning☆181Jan 29, 2026Updated 9 months ago
- The official code implementation of the Autodiff algorithm.☆16Nov 10, 2023Updated 2 years ago
- ☆172May 28, 2025Updated last year
- Value model for block-wise search☆14Jul 1, 2025Updated last year
- ☆10Mar 26, 2025Updated last year
- LLMJudge: LLM4Eval workshop data challenge on automatic relevance judgment☆14Jan 6, 2026Updated 10 months ago
- Distributional and Outlier Robust Optimization (ICML 2021)☆28Jul 10, 2021Updated 5 years ago
- Official repository for Beyond Binary Rewards: Training LMs to Reason about Their Uncertainty☆90Aug 20, 2025Updated last year
- official implementation of ICLR'2025 paper: Rethinking Bradley-Terry Models in Preference-based Reward Modeling: Foundations, Theory, and…☆74Apr 2, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- [EMNLP 2024 Main] Official implementation of the paper "The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Langua…☆13Nov 11, 2024Updated last year
- PRD: Peer Rank and Discussion Improve Large Language Model based Evaluations☆14Apr 21, 2024Updated 2 years ago
- [ICML'25] Official code of paper "Fast Large Language Model Collaborative Decoding via Speculation"☆30Jun 23, 2025Updated last year
- Automated Design of Agentic Systems☆10Sep 7, 2024Updated 2 years ago
- Code for paper: "LASeR: Learning to Adaptively Select Reward Models with Multi-Arm Bandits"☆14Sep 19, 2025Updated last year
- [TMLR] Process Reward Models That Think☆94Jul 30, 2026Updated 3 months ago
- The official code of paper 'Not All LLM-Generated Data are Equal'☆12Apr 23, 2025Updated last year
- ☆15Apr 6, 2026Updated 7 months ago
- ☆11Sep 25, 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.
- Multi-task end-to-end predict-then-optimize☆15Apr 28, 2023Updated 3 years ago
- An official repository for paper "Internal Chain-of-Thought: Empirical Evidence for Layer‑wise Subtask Scheduling in LLMs" in EMNLP 2025.☆14Aug 21, 2025Updated last year
- Accompanying code for our NeurIPS 2019 paper☆11Nov 7, 2019Updated 7 years ago
- [TMLR 25] SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models☆148Oct 10, 2025Updated last year
- [AAAI 2026] ReCode: Reinforced Code Knowledge Editing for API Updates☆26Jul 1, 2025Updated last year
- ☆36Apr 12, 2024Updated 2 years ago
- ☆32Jun 12, 2024Updated 2 years ago