相关论文: Diffusion LLMs can think EoS-by-EoS

Multimodal learning has rapidly advanced visual understanding, largely via multimodal large language models (MLLMs) that use powerful LLMs as cognitive cores. In visual generation, however, these powerful core models are typically reduced…

Diffusion language models, especially masked discrete diffusion models, have achieved great success recently. While there are some theoretical and primary empirical results showing the advantages of latent reasoning with looped transformers…

Latent diffusion models (LDMs) power state-of-the-art high-resolution generative image models. LDMs learn the data distribution in the latent space of an autoencoder (AE) and produce images by mapping the generated latents into RGB image…

Current speech language models generate responses directly without explicit reasoning, leading to errors that cannot be corrected once audio is produced. We introduce \textbf{``Silent Thought, Spoken Answer''} -- a paradigm where speech…

To augment language models with the ability to reason, researchers usually prompt or finetune them to produce chain of thought reasoning steps before producing the final answer. However, although people use natural language to reason…

Unlike autoregressive models, which generate tokens sequentially and benefit from reasoning-before-answering strategies such as Chain-of-Thought, Masked Diffusion Language Models (MDLMs) refine all sequence positions simultaneously, raising…

Diffusion-based large language models (dLLMs) refine token generations through iterative denoising, but answers often stabilize before all steps complete. We propose EDIT (Early Diffusion Inference Termination), an inference-time criterion…

This work addresses the challenge of democratizing advanced Large Language Models (LLMs) by compressing their mathematical reasoning capabilities into sub-billion parameter Small Language Models (SLMs) without compromising performance. We…

Offline reinforcement learning (RL) holds promise as a means to learn high-reward policies from a static dataset, without the need for further environment interactions. However, a key challenge in offline RL lies in effectively stitching…

Chain-of-Thought (CoT) reasoning improves multi-step mathematical problem solving in large language models but remains vulnerable to exposure bias and error accumulation, as early mistakes propagate irreversibly through autoregressive…

Large Language Models (LLMs) have demonstrated remarkable performance in many applications, including challenging reasoning problems via chain-of-thoughts (CoTs) techniques that generate ``thinking tokens'' before answering the questions.…

Diffusion large language models (dLLMs) have emerged as a promising alternative to autoregressive models, offering flexible generation orders and strong performance on complex reasoning tasks. However, instruction-tuned dLLMs exhibit a…

The use of continuous instead of discrete tokens during the Chain-of-Thought (CoT) phase of reasoning LLMs has garnered attention recently, based on the intuition that a continuous mixture of discrete tokens could simulate a superposition…

Recent large language models (LLMs) have demonstrated strong reasoning capabilities that benefits from online reinforcement learning (RL). These capabilities have primarily been demonstrated within the left-to-right autoregressive (AR)…

Large Multimodal Models (LMMs) often suffer from multimodal hallucinations, wherein they may create content that is not present in the visual inputs. In this paper, we explore a new angle of this issue: overly detailed training data hinders…

Theory of Mind (ToM) assesses whether models can infer hidden mental states such as beliefs, desires, and intentions, which is essential for natural social interaction. Although recent progress in Large Reasoning Models (LRMs) has boosted…

Chain-of-thought (CoT) reasoning has become a central mechanism for eliciting multi-step reasoning in Large Language Models (LLMs). Yet recent evidence presents a tension: hidden states appear to already encode future reasoning before CoT…

Most efforts to improve the reasoning capabilities of large language models (LLMs) involve either scaling the number of parameters and the size of training data, or scaling inference computation by letting models generate complex chains of…

Diffusion-based large language models (dLLMs) have shown promising performance across various reasoning tasks, establishing themselves as an alternative to autoregressive large language models (LLMs). Unlike autoregressive LLMs that…

Entropy-based confidence signals are increasingly leveraged to improve reasoning in large language models (LLMs), yet existing approaches treat confidence as a static quantity -- typically aggregated over tokens. We show that the…