Related papers: Multi-Task GRPO: Reliable LLM Reasoning Across Tas…
We present a method for efficient learning of control policies for multiple related robotic motor skills. Our approach consists of two stages, joint training and specialization training. During the joint training stage, a neural network…
Multi-Task Learning (MTL) combined with Low-Rank Adaptation (LoRA) has emerged as a promising direction for parameter-efficient deployment of Large Language Models (LLMs). By sharing a single adapter across multiple tasks, one can…
Multimodal Large Language Models (MLLMs) perform well in single-image visual grounding but struggle with real-world tasks that demand cross-image reasoning and multi-modal instructions. To address this, we adopt a reinforcement learning…
We propose FlowRL: matching the full reward distribution via flow balancing instead of maximizing rewards in large language model (LLM) reinforcement learning (RL). Recent advanced reasoning models adopt reward-maximizing methods (\eg, PPO…
Multi-task learning (MTL) aims at solving multiple related tasks simultaneously and has experienced rapid growth in recent years. However, MTL models often suffer from performance degeneration with negative transfer due to learning several…
Vision--language models (VLMs) are increasingly aligned via Group Relative Policy Optimization (GRPO)-style training. However, relying solely on terminal outcome rewards yields sparse credit assignment in multi-step reasoning, weakening the…
Recent advances in large language models (LLMs) have shown that reasoning ability can be significantly enhanced through Reinforcement Learning with Verifiable Rewards (RLVR). Group Relative Policy Optimization (GRPO) has emerged as the de…
Since DeepSeek-R1 popularized, Group Relative Policy Optimization (GRPO) has become the core part of training Reasoning LLMs. However, we find some deficiency that influences RL stability and inference efficiency, like zero-variance in…
Improving the multi-step reasoning ability of large language models (LLMs) with offline reinforcement learning (RL) is essential for quickly adapting them to complex tasks. While Direct Preference Optimization (DPO) has shown promise in…
Recently, Group Relative Policy Optimization (GRPO) has shown promising potential for aligning text-to-image (T2I) models, yet existing GRPO-based methods suffer from two critical limitations. (1) \textit{Shared credit assignment}:…
Meta-learning algorithms enable rapid adaptation to new tasks with minimal data, a critical capability for real-world robotic systems. This paper evaluates Model-Agnostic Meta-Learning (MAML) combined with Trust Region Policy Optimization…
Policy optimization for large language models often suffers from sparse reward signals in multi-step reasoning tasks. Critic-free methods like GRPO assign a single normalized outcome reward to all tokens, providing limited guidance for…
A major challenge of reinforcement learning (RL) in real-world applications is the variation between environments, tasks or clients. Meta-RL (MRL) addresses this issue by learning a meta-policy that adapts to new tasks. Standard MRL methods…
Group Relative Policy Optimization (GRPO) was introduced and used recently for promoting reasoning in LLMs under verifiable (binary) rewards. We show that the mean + variance calibration of these rewards induces a weighted contrastive loss…
The role of reinforcement learning (RL) in enhancing the reasoning of large language models (LLMs) is becoming increasingly significant. Despite the success of RL in many scenarios, there are still many challenges in improving the reasoning…
Group-relative RL training (GRPO) samples a small group of parallel rollouts for every training prompt and uses their within-group reward spread to compute per-trajectory advantages. In agentic environments each rollout is a long multi-turn…
Reinforcement Learning (RL) can directly enhance the reasoning capabilities of large language models without extensive reliance on Supervised Fine-Tuning (SFT). In this work, we revisit the traditional Policy Gradient (PG) mechanism and…
A key challenge in applying reinforcement learning (RL) to diffusion large language models (dLLMs) lies in the intractability of their likelihood functions, which are essential for the RL objective, necessitating corresponding approximation…
Recent research has proposed a series of specialized optimization algorithms for deep multi-task models. It is often claimed that these multi-task optimization (MTO) methods yield solutions that are superior to the ones found by simply…
Evolution Strategies (ES) have emerged as a scalable gradient-free alternative to reinforcement learning based LLM fine-tuning, but it remains unclear whether comparable task performance implies comparable solutions in parameter space. We…