LARA: Steering Language Models Without Repeated Weight Updates
Lagrangian Reward Augmentation (LARA) proposes a novel way to steer frozen language models using safety constraints during inference. This approach could reshape how AI models handle complex tasks…
Read the full articleYou might also wanna read
SPIRAL: A Reinforcement Learning Framework for Multi-Primitive Language Model Reasoning
Language model reasoning can be substantially improved at test time via scaffolds that scale inference compute across different primitives -
arxiv.org·14d ago
Study Finds Single Transformer Layer Can Match Full-Parameter RL Training in LLMs
Reinforcement learning (RL) has become a central component of post-training large language models (LLMs), yet little is understood about how
arxiv.org·8d agoStudy Finds Single Transformer Layer Can Match Full-Parameter RL Training in LLMs
Reinforcement learning (RL) has become a central component of post-training large language models (LLMs), yet little is understood about how
arxiv.org·8d ago
LLM-Based Framework Translates Natural Language into Spacecraft Trajectory Optimization Code
Trajectory optimization is a critical component for enabling safe and reliable autonomous operations in space exploration. As space missions
arxiv.org·1mo ago
ConSPO: A Contrastive Approach to Improving Reinforcement Learning with Verifiable Rewards for LLMs
Group Relative Policy Optimization (GRPO) is one of the most widely adopted RLVR algorithms for post-training large language models on reaso
arxiv.org·1mo ago
Ouro: Looped Language Models That Build Reasoning into Pre-Training Through Latent Space Iteration
Modern LLMs are trained to "think" primarily via explicit text generation, such as chain-of-thought (CoT), which defers reasoning to post-tr
arxiv.org·6mo agoReinforcement Learning to Train Large Language Models to Explain Human Decisions
Article URL: Comments URL: Points: 6 # Comments: 0
Comments
Sign in to join the conversation.
No comments yet. Be the first.