Related papers: CRAFT: Continuous Reasoning and Agentic Feedback T…

Effective prompting of generative AI is challenging for many users, particularly in expressing context for comprehension tasks such as explaining spreadsheet formulas, Python code, and text passages. Prompt middleware aims to address this…

Multimodal reasoning is a challenging task that requires models to reason across multiple modalities to answer questions. Existing approaches have made progress by incorporating language and visual modalities into a two-stage reasoning…

Text-to-image generation has witnessed great progress, especially with the recent advancements in diffusion models. Since texts cannot provide detailed conditions like object appearance, reference images are usually leveraged for the…

Empathetic response generation endows agents with the capability to comprehend dialogue contexts and react to expressed emotions. Previous works predominantly focus on leveraging the speaker's emotional labels, but ignore the importance of…

The integration of extensive, dynamic knowledge into Large Language Models (LLMs) remains a significant challenge due to the inherent entanglement of factual data and reasoning patterns. Existing solutions, ranging from non-parametric…

Graph Retrieval-Augmented Generation (Graph-RAG) enhances multihop question answering by organizing corpora into knowledge graphs and routing evidence through relational structure. However, practical deployments face two persistent…

Despite significant advancements in natural language generation, controlling language models to produce texts with desired attributes remains a formidable challenge. In this work, we introduce RSA-Control, a training-free controllable text…

Recent breakthroughs in generative simulation have harnessed Large Language Models (LLMs) to generate diverse robotic task curricula, yet these open-loop paradigms frequently produce linguistically coherent but physically infeasible goals,…

Chain-of-Thought (CoT) reasoning has been extensively explored in large models to tackle complex understanding tasks. However, it still remains an open question whether such strategies can be applied to verifying and reinforcing image…

Large language models have achieved remarkable progress on complex reasoning tasks. However, they often implicitly fabricate information when inputs are incomplete, producing confident but unreliable conclusions -- a failure mode we term…

Despite recent advances in text-to-image (T2I) models, they often fail to faithfully render all elements of complex prompts, frequently omitting or misrepresenting specific objects and attributes. Test-time optimization has emerged as a…

Recent unified models integrate multimodal understanding and generation within a single framework. However, an "understanding-generation gap" persists, where models can capture user intent but often fail to translate this semantic knowledge…

Large language models (LLMs) have become the cornerstone of modern AI. However, the existing paradigm of next-token prediction fundamentally limits their ability to form coherent, high-level concepts, making it a critical barrier to…

Generative modelling paradigms based on denoising diffusion processes have emerged as a leading candidate for conditional sampling in inverse problems. In many real-world applications, we often have access to large, expensively trained…

We propose a novel Auto-Regressive (AR) image generation approach that models images as hierarchical compositions of interpretable visual layers. While AR models have achieved transformative success in language modeling, replicating this…

Human reasoning is shaped by resource rationality -- optimizing performance under constraints. Recently, inference-time scaling has emerged as a powerful paradigm to improve the reasoning performance of Large Language Models by expanding…

Large reasoning models (LRMs) are proficient at generating explicit, step-by-step reasoning sequences before producing final answers. However, such detailed reasoning can introduce substantial computational overhead and latency,…

Text-to-video diffusion models generate realistic videos, but often fail on prompts requiring fine-grained compositional understanding, such as relations between entities, attributes, actions, and motion directions. We hypothesize that…

In this paper, we design and train a Generative Image-to-text Transformer, GIT, to unify vision-language tasks such as image/video captioning and question answering. While generative models provide a consistent network architecture between…

Associative thinking--the ability to connect seemingly unrelated ideas--is a foundational element of human creativity and problem-solving. This paper explores whether reinforcement learning (RL) guided by associative thinking principles can…