Related papers: SEGA: A Stepwise Evolution Paradigm for Content-Aw…

Deep learning, a rebranding of deep neural network research works, has achieved a remarkable success in recent years. With multiple hidden layers, deep learning models aim at computing the hierarchical feature representations of the…

In recent years, advancements in AIGC (Artificial Intelligence Generated Content) technology have significantly enhanced the capabilities of large text-to-image models. Despite these improvements, controllable image generation remains a…

Large, text-conditioned generative diffusion models have recently gained a lot of attention for their impressive performance in generating high-fidelity images from text alone. However, achieving high-quality results is almost unfeasible in…

Generating controllable and physically plausible indoor scenes is a pivotal prerequisite for constructing high-fidelity simulation environments for embodied AI. However, existing deeplearning-based methods usually treat all objects as…

In this paper, we propose a self-supervised visual representation learning approach which involves both generative and discriminative proxies, where we focus on the former part by requiring the target network to recover the original image…

Modern generative models are usually designed to match target distributions directly in the data space, where the intrinsic dimension of data can be much lower than the ambient dimension. We argue that this discrepancy may contribute to the…

It is common in graphic design humans visually arrange various elements according to their design intent and semantics. For example, a title text almost always appears on top of other elements in a document. In this work, we generate…

Controlled table-to-text generation seeks to generate natural language descriptions for highlighted subparts of a table. Previous SOTA systems still employ a sequence-to-sequence generation method, which merely captures the table as a…

While thinking-aware generation aims to improve performance on complex tasks, we identify a critical failure mode where existing sequential, autoregressive approaches can paradoxically degrade performance due to error propagation. To…

The evolution of Large Language Model (LLM) reasoning is bottlenecked by the scarcity of high-quality process data. While self-alignment via endogenous rewards offers a solution, mining valid supervision faces three challenges: (1) Label…

Recently there is an increasing interest in scene generation within the research community. However, models used for generating scene layouts from textual description largely ignore plausible visual variations within the structure dictated…

We introduce a novel, training-free approach for enhancing alignment in Transformer-based Text-Guided Diffusion Models (TGDMs). Existing TGDMs often struggle to generate semantically aligned images, particularly when dealing with complex…

In this work, we consider the problem of procedural content generation for video game levels. Prior approaches have relied on evolutionary search (ES) methods capable of generating diverse levels, but this generation procedure is slow,…

Unified Multimodal Models (UMMs) exhibit strong understanding, yet this capability often fails to effectively guide generation. We identify this as a Cognitive Gap: the model lacks the understanding of how to enhance its own generation…

Video Large Language Models (Video-LLMs) have recently shown strong performance in basic video understanding tasks, such as captioning and coarse-grained question answering, but struggle with compositional reasoning that requires multi-step…

In this work, we investigate automatic design composition from multimodal graphic elements. Although recent studies have developed various generative models for graphic design, they usually face the following limitations: they only focus on…

Data sparsity is a well-known problem for grammatical error correction (GEC). Generating synthetic training data is one widely proposed solution to this problem, and has allowed models to achieve state-of-the-art (SOTA) performance in…

Large Language Models have significantly advanced the field of code generation, demonstrating the ability to produce functionally correct code snippets. However, advancements in generative AI for code overlook foundational Software…

Current evaluation practices in speech-driven gesture generation lack standardisation and focus on aspects that are easy to measure over aspects that actually matter. This leads to a situation where it is impossible to know what is the…

Long-term memory is becoming a central bottleneck for language agents. Exsting RAG and GraphRAG systems largely treat memory graphs as static retrieval middleware, which limits their ability to recover complete evidence chains from partial…