Related papers: STITCH: Simultaneous Thinking and Talking with Chu…

The thinking-while-speaking paradigm aims to make AI communication more human. A key challenge is maintaining fluent speech while performing deep reasoning. Our method, InterRS, tackles this by inserting reasoning steps only during natural…

Chain-of-Thought (CoT) is a critical technique in enhancing the reasoning ability of Large Language Models (LLMs), and latent reasoning methods have been proposed to accelerate the inefficient token-level reasoning chain. We notice that…

Many state-of-the-art LLMs are trained to think before giving their answer. Reasoning can greatly improve language model capabilities, but it also makes them less interactive: given a new input, a model must stop thinking before it can…

Large Language Models (LLMs) solve many reasoning tasks via chain-of-thought (CoT) prompting, but smaller models (about 7 to 8B parameters) still struggle with multi-step reasoning under tight compute and token budgets. Existing test time…

We propose cognitive prompting as a novel approach to guide problem-solving in large language models (LLMs) through structured, human-like cognitive operations, such as goal clarification, decomposition, filtering, abstraction, and pattern…

Speech language models (SpeechLMs) accept speech input and produce speech output, allowing for more natural human-computer interaction compared to text-based large language models (LLMs). Traditional approaches for developing SpeechLMs are…

Large language models (LLMs) have demonstrated remarkable capabilities in tasks requiring reasoning and multi-step problem-solving through the use of chain-of-thought (CoT) prompting. However, generating the full CoT process results in…

Large language models (LLMs) are typically constrained to reason in the language space, where they express the reasoning process through a chain-of-thought (CoT) to solve complex problems. However, the language space may not always be…

Early-stage design ideation often relies on rough sketches created under time pressure, leaving much of the designer's intent implicit. In practice, designers frequently speak while sketching, verbally articulating functional goals and…

While Multimodal Large Language Models (MLLMs) excel at visual understanding tasks through text reasoning, they often fall short in scenarios requiring visual imagination. Unlike current works that take predefined external toolkits or…

We present a generative dialogue system capable of operating in a full-duplex manner, allowing for seamless interaction. It is based on a large language model (LLM) carefully aligned to be aware of a perception module, a motor function…

While explicit Chain-of-Thought (CoT) equips Large Language Models (LLMs) with strong reasoning capabilities, it requires models to verbalize every intermediate step in text tokens, constraining the model thoughts to the discrete vocabulary…

Recent advances in spoken dialogue language models (SDLMs) reflect growing interest in shifting from turn-based to full-duplex systems, where the models continuously perceive user speech streams while generating responses. This simultaneous…

Chain-of-thought (CoT) reasoning has enabled large language models (LLMs) to utilize additional computation through intermediate tokens to solve complex tasks. However, we posit that typical reasoning traces contain many redundant tokens,…

Large language models (LLMs) have recently attracted considerable interest for their ability to perform complex reasoning tasks, such as chain-of-thought (CoT) reasoning. However, most of the existing approaches to enhance this ability rely…

Reasoning large language models (RLLMs) have recently demonstrated remarkable capabilities through structured and multi-step reasoning. While prior research has primarily focused on improving their training and inference strategies, their…

Unlike human reasoning in abstract conceptual spaces, large language models (LLMs) typically reason by generating discrete tokens, which potentially limit their expressive power. The recent work Soft Thinking has shown that LLMs' latent…

Human cognition typically involves thinking through abstract, fluid concepts rather than strictly using discrete linguistic tokens. Current reasoning models, however, are constrained to reasoning within the boundaries of human language,…

Large Language Models (LLMs) have shown impressive performance on complex tasks through Chain-of-Thought (CoT) reasoning. However, conventional CoT relies on explicitly verbalized intermediate steps, which constrains its broader…

Large Language Models (LLMs) demonstrate impressive capabilities, yet interaction with these models is mostly facilitated through text. Using Text-To-Speech to synthesize LLM outputs typically results in notable latency, which is…