Related papers: Incentivizing Multimodal Reasoning in Large Models…

With the continuous expansion of Large Language Models (LLMs) and advances in reinforcement learning, LLMs have demonstrated exceptional reasoning capabilities, enabling them to address a wide range of complex problems. Inspired by these…

Reasoning is an essential component of human intelligence as it plays a fundamental role in our ability to think critically, support responsible decisions, and solve challenging problems. Traditionally, AI has addressed reasoning in the…

Reasoning is an essential component of human intelligence in that it plays a fundamental role in our ability to think critically, support responsible decisions, and solve challenging problems. Traditionally, AI has addressed reasoning in…

Recent advances in Large Reasoning Models (LRMs), particularly those leveraging Chain-of-Thought reasoning (CoT), have opened brand new possibility for Machine Translation (MT). This position paper argues that LRMs substantially transformed…

Reasoning is essential for large language models (LLMs), especially in complex tasks such as mathematical problem solving. However, multimodal reasoning still faces challenges in modality alignment and training scalability, as many existing…

We present a large language model (LLM) based system to empower quadrupedal robots with problem-solving abilities for long-horizon tasks beyond short-term motions. Long-horizon tasks for quadrupeds are challenging since they require both a…

With the rapid evolution of multimodal large language models, the capacity to deeply understand and interpret human intentions has emerged as a critical capability, which demands detailed and thoughtful reasoning. In recent studies,…

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…

The fusion of Large Language Models (LLMs) and robotic systems has led to a transformative paradigm in the robotic field, offering unparalleled capabilities not only in the communication domain but also in skills like multimodal input…

Large Language Models (LLMs) are highly proficient in language-based tasks. Their language capabilities have positioned them at the forefront of the future AGI (Artificial General Intelligence) race. However, on closer inspection, Valmeekam…

Vision-Language Models (VLMs) have revolutionized artificial intelligence and robotics due to their commonsense reasoning capabilities. In robotic manipulation, VLMs are used primarily as high-level planners, but recent work has also…

Recent advances in vision-language models (VLMs) have enabled instruction-conditioned robotic systems with improved generalization. However, most existing work focuses on reactive System 1 policies, underutilizing VLMs' strengths in…

We propose integration of reasoning into speech large language models (speechLLMs) for the end-to-end slot-filling task. Inspired by the recent development of reasoning LLMs, we use a chain-of-thought framework to decompose the slot-filling…

Vision-Language Models in Continual Learning (VLM-CL) aim to continuously adapt to new multimodal tasks while retaining prior knowledge. The emerging paradigm that couples Multimodal Large Language Models (MLLMs) with Reinforcement Learning…

The remarkable reasoning capability of large language models (LLMs) stems from cognitive behaviors that emerge through reinforcement with verifiable rewards. This work investigates how to transfer this principle to Multimodal LLMs (MLLMs)…

Although Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across diverse tasks, they encounter challenges in terms of reasoning efficiency, large model size and overthinking. However, existing lightweight…

We present MiMo-7B, a large language model born for reasoning tasks, with optimization across both pre-training and post-training stages. During pre-training, we enhance the data preprocessing pipeline and employ a three-stage data mixing…

We present a controlled study of multi-hop contextual reasoning in large language models, providing a clean demonstration of the task-method dissociation: rule-based pattern matching achieves 100% success on structured information retrieval…

Multimodal embeddings are widely used in downstream tasks such as multimodal retrieval, enabling alignment of interleaved modalities in a shared representation space. While recent studies show that Multimodal Large Language Models (MLLMs)…

Large Language Models (LLMs) pre-trained on internet-scale datasets have shown impressive capabilities in code understanding, synthesis, and general purpose question-and-answering. Key to their performance is the substantial prior knowledge…