相关论文: Fast-Slow Thinking RM: Efficient Integration of Sc…

Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning large language models with human preferences. While recent research has focused on algorithmic improvements, the importance of prompt-data construction has been…

We introduce Reward-Guided Speculative Decoding (RSD), a novel framework aimed at improving the efficiency of inference in large language models (LLMs). RSD synergistically combines a lightweight draft model with a more powerful target…

Continuously learning new tasks using high-level ideas or knowledge is a key capability of humans. In this paper, we propose Lifelong reinforcement learning with Sequential linear temporal logic formulas and Reward Machines (LSRM), which…

Reward models (RMs) play a critical role in aligning language models through the process of reinforcement learning from human feedback. RMs are trained to predict a score reflecting human preference, which requires significant time and cost…

The emergence of LM-based judging reward modeling, represented by generative reward models, has successfully made reinforcement learning from AI feedback (RLAIF) efficient and scalable. To further advance this paradigm, we propose a core…

Effective decision-making in Large Language Models (LLMs) is essential for handling intricate tasks. However, existing approaches prioritize performance but often overlook the balance between effectiveness and computational cost. To address…

Automatic evaluation is crucial yet challenging for open-ended natural language generation, especially when rule-based metrics are infeasible. Compared with traditional methods, the recent LLM-as-a-Judge paradigms enable better and more…

Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities but often struggle with complex, multi-step mathematical reasoning, where minor errors in visual perception or logical deduction can lead to complete failure.…

Process Reward Models (PRMs) have emerged as a powerful tool for providing step-level feedback when evaluating the reasoning of Large Language Models (LLMs), which frequently produce chains of thought (CoTs) containing errors even when the…

Reinforcement Learning from Human Feedback (RLHF) remains indispensable for aligning large language models (LLMs) in subjective domains. To enhance robustness, recent work shifts toward Generative Reward Models (GenRMs) that generate…

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…

Reward Models (RMs) are critical for improving generation models via Reinforcement Learning (RL), yet the RM scaling paradigm in visual generation remains largely unexplored. It primarily due to fundamental limitations in existing…

While Large Language Models (LLMs) have demonstrated strong math reasoning abilities through Reinforcement Learning with *Verifiable Rewards* (RLVR), many advanced mathematical problems are proof-based, with no guaranteed way to determine…

Human cognition is theorized to operate in two modes: fast, intuitive System 1 thinking and slow, deliberate System 2 thinking. While current Large Reasoning Models (LRMs) excel at System 2 thinking, their inability to perform fast thinking…

Large language models (LLMs) have demonstrated strong reasoning abilities in mathematical tasks, often enhanced through reinforcement learning (RL). However, RL-trained models frequently produce unnecessarily long reasoning traces -- even…

Process Reward Model (PRM) is widely used in the post-training of Large Language Model (LLM) because it can perform fine-grained evaluation of the reasoning steps of generated content. However, most PRMs lack long-term reasoning and deep…

The reward model has become increasingly important in alignment, assessment, and data construction for large language models (LLMs). Most existing researchers focus on enhancing reward models through data improvements, following the…

Recent years have seen considerable advancements in multi-step reasoning with Large Language Models (LLMs). The previous studies have elucidated the merits of integrating feedback or search mechanisms during model inference to improve the…

Large language models excel at complex reasoning, yet evaluating their intermediate steps remains challenging. Although process reward models provide step-wise supervision, they often suffer from a risk compensation effect, where incorrect…

Recent advances in speech language models, such as GPT-4o Voice Mode and Gemini Live, have demonstrated promising speech generation capabilities. Nevertheless, the aesthetic naturalness of the synthesized audio still lags behind that of…