Reasoning with Autoregressive-Diffusion Collaborative Thoughts
Autoregressive and diffusion models represent two complementary generative paradigms. Autoregressive models excel at sequential planning and constraint composition, yet struggle with tasks that require explicit spatial or physical grounding. Diffusion models, in contrast, capture rich spatial structure through high-dimensional generation, but lack the stepwise logical control needed to satisfy complex, multi-stage constraints or to reliably identify and correct errors. We introduce Collaborative Thoughts, a unified collaborative framework that enables autoregressive and diffusion models to reason and generate jointly through a closed-loop interaction. In Collaborative Thoughts, autoregressive models perform structured planning and constraint management, diffusion models instantiate these constraints as intermediate visual thoughts, and a vision-based critic module evaluates whether the visual thoughts satisfy the intended structural and physical requirements. This feedback is then used to iteratively refine subsequent planning and generation steps, mitigating error propagation across modalities. Importantly, Collaborative Thoughts uses the same collaborative loop regardless of whether the task is autoregressive question answering or diffusion-based visual generation. Through representative examples, we illustrate how Collaborative Thoughts can improve the reliability of spatial reasoning and the controllability of generation.
Code (0)
등록된 구현이 없습니다.
Tasks
Question AnsweringSpatial ReasoningSimilar Papers 제목 키워드 기반
Diffuse Thinking: Exploring Diffusion Language Models as Efficient Thought Proposers for Reasoning
In recent years, large language models (LLMs) have witnessed remarkable advancements, with the test-time scaling law consistently enhancing the reasoning capabilities. Through systematic evaluation and exploration of a d…
Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models
Recently, diffusion models have garnered significant interest in the field of text processing due to their many potential advantages compared to conventional autoregressive models. In this work, we propose Diffusion-of-T…
Language ModelingLanguage ModellingMathSwimBird: Eliciting Switchable Reasoning Mode in Hybrid Autoregressive MLLMs
Multimodal Large Language Models (MLLMs) have made remarkable progress in multimodal perception and reasoning by bridging vision and language. However, most existing MLLMs perform reasoning primarily with textual CoT, wh…
Multimodal ReasoningLogical ReasoningHybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model
Recent advancements in vision-language models (VLMs) for common-sense reasoning have led to the development of vision-language-action (VLA) models, enabling robots to perform generalized manipulation. Although existing a…
Common Sense ReasoningDenoisingLarge Language ModelVision-Language-ActionUnlocking the Working Memory of Large Language Models for Latent Reasoning
To improve the reasoning capabilities of large language models, test-time compute is typically scaled by generating intermediate tokens before the final answer. However, this couples reasoning to autoregressive generatio…