Related papers: Balanced Actor Initialization: Stable RLHF Trainin…

The emergence of large language models has enabled sophisticated multi-agent systems, yet coordinating their reasoning capabilities through prompt engineering remains challenging. We present a theoretically-grounded framework for dynamic…

Diffusion models have revolutionized generative modeling in continuous domains like image, audio, and video synthesis. However, their iterative sampling process leads to slow generation and inefficient training, challenges that are further…

Distilling reasoning paths from teacher to student models via supervised fine-tuning (SFT) provides a shortcut for improving the reasoning ability of smaller Large Language Models (LLMs). However, the reasoning paths generated by teacher…

The effectiveness of reinforcement learning (RL) agents in continuous control robotics tasks is mainly dependent on the design of the underlying reward function, which is highly prone to reward hacking. A misalignment between the reward…

Reinforcement Learning from human feedback (RLHF) has been shown a promising direction for aligning generative models with human intent and has also been explored in recent works for alignment of diffusion generative models. In this work,…

Current AI systems based on probabilistic neural networks, such as large language models (LLMs), have demonstrated remarkable generative capabilities yet face critical challenges including hallucination, unpredictability, and misalignment…

Reasoning is a cognitive process of using evidence to reach a sound conclusion. The reasoning capability is essential for large language models (LLMs) to serve as the brain of the artificial general intelligence agent. Recent studies reveal…

Long chain-of-thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs). However, extensive reasoning traces lead to inefficiencies and increased time-to-first-token (TTFT). We propose a training…

Multimodal reasoning stands as a pivotal capability for large vision-language models (LVLMs). The integration with Domain-Specific Languages (DSL), offering precise visual representations, equips these models with the opportunity to execute…

Large Language Models (LLMs) have revolutionized natural language processing, yet aligning these models with human values and preferences using RLHF remains a significant challenge. This challenge is characterized by various instabilities,…

Large Multimodal Models (LMMs) excel at comprehending human instructions and demonstrate remarkable results across a broad spectrum of tasks. Reinforcement Learning from Human Feedback (RLHF) and AI Feedback (RLAIF) further refine LLMs by…

Large language models (LLMs) excel in complex reasoning tasks, and distilling their reasoning capabilities into smaller models has shown promise. However, we uncover an interesting phenomenon, which we term the Small Model Learnability Gap:…

Reinforcement Learning with Verifiable Reward (RLVR) effectively solves complex tasks but demands extremely long context lengths during training, leading to substantial computational costs. While multi-stage training can partially mitigate…

Reasoning over dynamic visual content remains a central challenge for multimodal large language models. Recent thinking models generate explicit reasoning traces for interpretability; however, their reasoning often appears convincing while…

LLM implementations are failing in highly regulated industries owing to instability issues, inconsistent reasoning, hallucinations and performance variability, especially in workflows. These reliability issues restrict safe use of LLM in…

Search-integrated reasoning enables language agents to transcend static parametric knowledge by actively querying external sources. However, training these agents via reinforcement learning is hindered by the multi-scale credit assignment…

The development of autonomous agents for complex, long-horizon tasks is a central goal in AI. However, dominant training paradigms face a critical limitation: reinforcement learning (RL) methods that optimize solely for final task success…

Recent studies have focused on leveraging large-scale artificial intelligence (LAI) models to improve semantic representation and compression capabilities. However, the substantial computational demands of LAI models pose significant…

Despite the significant improvements achieved by large language models (LLMs) in English reasoning tasks, these models continue to struggle with multilingual reasoning. Recent studies leverage a full-parameter and two-stage training…

Distilled autoregressive (AR) video models enable efficient streaming generation but frequently misalign with human visual preferences. Existing reinforcement learning (RL) frameworks are not naturally suited to these architectures,…