ZhangXJ199 / EDGE-GRPOLinks
Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity
☆18Updated 3 weeks ago
Alternatives and similar repositories for EDGE-GRPO
Users that are interested in EDGE-GRPO are comparing it to the libraries listed below
Sorting:
- ☆14Updated 9 months ago
- ACL'2025: SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs. and preprint: SoftCoT++: Test-Time Scaling with Soft Chain-of…☆46Updated 3 months ago
- ☆24Updated 4 months ago
- [ACL 2025 Findings] Official implementation of the paper "Unveiling the Key Factors for Distilling Chain-of-Thought Reasoning".☆19Updated 6 months ago
- ☆15Updated 3 months ago
- ☆26Updated 3 months ago
- Code, Data and Model for Paper "Learning from Peers in Reasoning Models"☆26Updated 4 months ago
- Code for "CREAM: Consistency Regularized Self-Rewarding Language Models", ICLR 2025.☆26Updated 7 months ago
- [arXiv2505] Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains☆50Updated last month
- Official Repo for SvS: A Self-play with Variational Problem Synthesis strategy for RLVR training☆36Updated 3 weeks ago
- [arxiv: 2505.02156] Adaptive Thinking via Mode Policy Optimization for Social Language Agents☆42Updated 2 months ago
- ☆18Updated 2 months ago
- [ICML'25] Our study systematically investigates massive values in LLMs' attention mechanisms. First, we observe massive values are concen…☆79Updated 3 months ago
- ☆19Updated 4 months ago
- ☆22Updated last year
- ☆36Updated last month
- Code repo for "Harnessing Negative Signals: Reinforcement Distillation from Teacher Data for LLM Reasoning"☆28Updated last month
- [ACL 2024 Findings] Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning☆12Updated last year
- Code and data for paper "Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation".☆21Updated 4 months ago
- ☆15Updated 10 months ago
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆85Updated 7 months ago
- [ICML 2025] M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning☆69Updated 2 months ago
- TreeRL: LLM Reinforcement Learning with On-Policy Tree Search in ACL'25☆61Updated 3 months ago
- Official Repository of LatentSeek☆60Updated 3 months ago
- ☆25Updated last week
- Source code for our paper: "ARIA: Training Language Agents with Intention-Driven Reward Aggregation".☆22Updated last month
- The official code repository for the paper "Mirage or Method? How Model–Task Alignment Induces Divergent RL Conclusions".☆12Updated 2 weeks ago
- EMPO, A Fully Unsupervised RLVR Method☆65Updated last week
- Official implementation of "MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model". Our co…☆21Updated 9 months ago
- RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment☆16Updated 9 months ago