HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models
cs.LG, cs.AI
Submitted: 2026-07-29
Updated: 2026-11-09
Code: https://github.com/global-computing-consortium/HiFloat4
Terminology
Sources
- Training Verifiers to Solve Math Word Problems
- Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
- PACT: Parameterized Clipping Activation for Quantized Neural Networks
- GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
- HiFloat4 Format for Language Model Inference
- ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs
- Accelerating Sparse Deep Neural Networks
- Qwen2.5 Technical Report
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- HybridFlow: A Flexible and Efficient RLHF Framework
- FastCuRL: Curriculum Reinforcement Learning with Stage-wise Context Scaling for Efficient Training R1-like Reasoning Models
- HiFloat4 Format for Language Model Pre-training on Ascend NPUs
- Training LLMs with MXFP4
- Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow
- Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning
- Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
- Accurate INT8 Training Through Dynamic Block-Level Fallback
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis