Related papers: Large Language Models are Universal Reasoners for …
Large Language Models (LLMs) have transformed natural language processing and hold growing promise for advancing science, healthcare, and decision-making. Yet their training paradigms remain dominated by affirmation-based inference, akin to…
Real-world multimodal applications often require any-to-any capabilities, enabling both understanding and generation across modalities including text, image, audio, and video. However, integrating the strengths of autoregressive language…
Pretrained large Language Models (LLMs) are able to answer questions that are unlikely to have been encountered during training. However a diversity of potential applications exist in the broad domain of reasoning systems and considerations…
Large vision-language models exhibit inherent capabilities to handle diverse visual perception tasks. In this paper, we introduce VisionReasoner, a unified framework capable of reasoning and solving multiple visual perception tasks within a…
Unified multimodal large language models (U-MLLMs) have demonstrated impressive performance in visual understanding and generation in an end-to-end pipeline. Compared with generation-only models (e.g., Stable Diffusion), U-MLLMs may raise…
Recent advances in multimodal large language models (MLLMs) have enabled image-based question-answering capabilities. However, a key limitation is the use of CLIP as the visual encoder; while it can capture coarse global information, it…
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…
Building upon large language models (LLMs), recent large multimodal models (LMMs) unify cross-model understanding and generation into a single framework. However, LMMs still struggle to achieve accurate vision-language alignment, prone to…
Unified multimodal models (UMMs) have emerged as a powerful paradigm for seamlessly unifying text and image understanding and generation. However, prevailing evaluations treat these abilities in isolation, such that tasks with multimodal…
The burgeoning field of generative artificial intelligence has fundamentally reshaped our approach to content creation, with Large Vision-Language Models (LVLMs) standing at its forefront. While current LVLMs have demonstrated impressive…
Unifying diverse image generation tasks within a single framework remains a fundamental challenge in visual generation. While large language models (LLMs) achieve unification through task-agnostic data and generation, existing visual…
Existing Large Vision-Language Models (LVLMs) excel at matching concepts across multi-modal inputs but struggle with compositional concepts and high-level relationships between entities. This paper introduces Progressive multi-granular…
In this paper, we introduce ILLUME, a unified multimodal large language model (MLLM) that seamlessly integrates multimodal understanding and generation capabilities within a single large language model through a unified next-token…
Diffusion models have achieved success in high-fidelity data synthesis, yet their capacity for more complex, structured reasoning like text following tasks remains constrained. While advances in language models have leveraged strategies…
How humans can effectively and efficiently acquire images has always been a perennial question. A classic solution is text-to-image retrieval from an existing database; however, the limited database typically lacks creativity. By contrast,…
The field of controllable image generation has seen significant advancements, with various architectures improving generation layout consistency with control signals. However, contemporary methods still face challenges in bridging the…
Language-guided image generation has achieved great success nowadays by using diffusion models. However, texts can be less detailed to describe highly-specific subjects such as a particular dog or a certain car, which makes pure…
Diffusion language models (dLLMs) recently emerged as a promising alternative to auto-regressive LLMs. The latest works further extended it to multimodal understanding and generation tasks. In this work, we propose LaViDa-R1, a multimodal,…
We present UniFluid, a unified autoregressive framework for joint visual generation and understanding leveraging continuous visual tokens. Our unified autoregressive architecture processes multimodal image and text inputs, generating…
Current unified multimodal models typically rely on discrete visual tokenizers to bridge the modality gap. However, discretization inevitably discards fine-grained semantic information, leading to suboptimal performance in visual…