Pre-trained, Scalable, High-performance Reward Models via Policy Discriminative Learning.
☆164Sep 23, 2025Updated 5 months ago
Alternatives and similar repositories for POLAR
Users that are interested in POLAR are comparing it to the libraries listed below
Sorting:
- codes for Efficient Test-Time Scaling via Self-Calibration☆19Sep 13, 2025Updated 5 months ago
- coded with and corrected by Google Anti-Gravity☆13Nov 23, 2025Updated 3 months ago
- a survey of long-context LLMs from four perspectives, architecture, infrastructure, training, and evaluation☆61Mar 31, 2025Updated 11 months ago
- ☆38Jun 12, 2025Updated 8 months ago
- Rethinking the Trust Region in LLM Reinforcement Learning☆38Feb 5, 2026Updated 3 weeks ago
- ☆15Mar 22, 2024Updated last year
- Scaling Preference Data Curation via Human-AI Synergy☆142Jul 3, 2025Updated 7 months ago
- Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination.☆21Jul 18, 2025Updated 7 months ago
- DuoDecoding: Hardware-aware Heterogeneous Speculative Decoding with Dynamic Multi-Sequence Drafting☆17Mar 4, 2025Updated 11 months ago
- Implementation code for ACL2024：Advancing Parameter Efficiency in Fine-tuning via Representation Editing☆15Apr 20, 2024Updated last year
- Vision-Language based Visual Object Tracking☆27Oct 10, 2025Updated 4 months ago
- Physics of Language Models: Part 4.2, Canon Layers at Scale where Synthetic Pretraining Resonates in Reality☆322Jan 5, 2026Updated last month
- Official code for our paper "Reasoning Models Hallucinate More: Factuality-Aware Reinforcement Learning for Large Reasoning Models"☆22Oct 31, 2025Updated 4 months ago
- Socratic-Zero is a fully autonomous framework that generates high-quality training data for mathematical reasoning☆35Oct 26, 2025Updated 4 months ago
- The dataset CoLan-150K and the concept decomposition in the paper Concept Lancet (CVPR 2025)☆20Jan 18, 2026Updated last month
- ☆17Oct 16, 2024Updated last year
- Manages vllm-nccl dependency☆17Jun 3, 2024Updated last year
- [ICML 2025] Differentiable Solver Search for Fast Diffusion Sampling☆21Jul 7, 2025Updated 7 months ago
- BranchGRPO: Stable and Efficient GRPO with Structured Branching in Diffusion Models☆40Oct 30, 2025Updated 4 months ago
- ☆41May 15, 2025Updated 9 months ago
- ☆352Jul 29, 2025Updated 7 months ago
- Face-MakeUp (SD1.5): Multimodal Facial Prompts for Text-to-Image Generation （ECAI-2025）☆26Jan 19, 2025Updated last year
- ☆52Nov 6, 2025Updated 3 months ago
- [ACL 2024 main] Aligning Large Language Models with Human Preferences through Representation Engineering (https://aclanthology.org/2024.…☆28Sep 25, 2024Updated last year
- SuperCLUE-Math6：新一代中文原生多轮多步数学推理数据集的探索之旅☆58Feb 5, 2024Updated 2 years ago
- Best practices for training DeepSeek, Mixtral, Qwen and other MoE models using Megatron Core.☆166Jan 22, 2026Updated last month
- [ICLR 2026] Geometric-Mean Policy Optimization☆100Jan 26, 2026Updated last month
- Universal differential equations for ecologists☆14Feb 4, 2026Updated 3 weeks ago
- TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation☆236Aug 18, 2025Updated 6 months ago
- SWE-Swiss: A Multi-Task Fine-Tuning and RL Recipe for High-Performance Issue Resolution☆104Sep 24, 2025Updated 5 months ago
- Implementation code of the paper MIGE: A Unified Framework for Multimodal Instruction-Based Image Generation and Editing☆72Jul 13, 2025Updated 7 months ago
- ☆58Dec 10, 2025Updated 2 months ago
- Code for ACL 2025 Main paper "Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning…☆46Aug 4, 2025Updated 6 months ago
- ☆87Aug 16, 2025Updated 6 months ago
- VisPlay: Self-Evolving Vision-Language Models☆44Feb 12, 2026Updated 2 weeks ago
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,219Aug 27, 2025Updated 6 months ago
- SSRL: Self-Search Reinforcement Learning☆206Aug 20, 2025Updated 6 months ago
- Official Repository: A Comprehensive Benchmark for Logical Reasoning in MLLMs☆45Jun 17, 2025Updated 8 months ago
- This repository implements our EMNLP 2022 research paper A Dataset for Hyper-Relational Extraction and a Cube-Filling Approach.☆28Dec 13, 2022Updated 3 years ago