Entities · Models
GRPO
33 articles tagged with this entity.
-
Agon: Competitive Cross-Model RL with Implicit Rival Grading of Reasoning
-
DRIFTLENS: Measuring Memory-Induced Reasoning Drift in Personalized Language Models
-
Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL
-
Paved with True Intents: Intent-Aware Training Improves LLM Safety Classification Across Training Regimes
-
MetaResearcher: Scaling Deep Research via Self-Reflective Reinforcement Learning in Adversarial Virtual Environments
-
EnvRL: Learn from Environment Dynamics in Agentic Reinforcement Learning
-
StarOR: Synergizing Tree Search and Test-Time Reinforcement Learning for Optimization Modeling
-
DEEPRUBRIC: Evidence-Tree Rubric Supervision for Efficient Reinforcement Learning of Deep Research Agents
-
It Takes One to Bias Them All: Breaking Bad with One-Shot GRPO
-
INFUSER: Influence-Guided Self-Evolution Improves Reasoning
-
CATPO: Critique-Augmented Tree Policy Optimization
-
Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO
-
TAPO: Tool-Aware Policy Optimization via Credit Transfer for Multimodal Search Agents
-
GLASS: GRPO-Trained LoRA for Acoustic Style Steering in Zero-Shot Text-to-Speech
-
ReSkill: Reconciling Skill Creation with Policy Optimization in Agentic RL
-
Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective
-
VeriGate: Verifier-Gated Step-Level Supervision for GRPO
-
Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models
-
IRPO: Boosting Image Restoration via Post-training GRPO
-
UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models
-
Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization
-
Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards
-
BPPO: Binary Prefix Policy Optimization for Efficient GRPO-Style Reasoning RL with Concise Responses
-
TAGRPO: Boosting GRPO on Image-to-Video Generation with Direct Trajectory Alignment
-
ECHO: Terminal Agents Learn World Models for Free
-
LC-ERD: Mining Latent Logic for Self-Evolving Reasoning via Consistency-Regulated Reward Decomposition
-
Quantifying Empirical Compute-Supervision Tradeoffs in RLVR
-
Better, Faster: Harnessing Self-Improvement in Large Reasoning Models
-
XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation
-
DeepSeekMath Meets Order Book: Group-Aware Policy Optimization for High-Frequency Directional Trading
-
DRM: Diffusion-based Reward Model With Step-wise Guidance
-
Co-ReAct: Rubrics as Step-Level Collaborators for ReAct Agents
-
Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning