The effectiveness of Multimodal Large Language Models (MLLMs) demonstrates a profound capability in multimodal understanding. However, the simultaneous generation of images with coherent texts is still underdeveloped. Addressing this, we introduce a novel interleaved vision-and-language generation method, centered around the concept of "generative vokens". These vokens serve as pivotal elements contributing to coherent image-text outputs. Our method is marked by a unique two-stage training strategy for description-free multimodal generation, which does not necessitate extensive descriptions of images. We integrate classifier-free guidance to enhance the alignment of generated images and texts, ensuring more seamless and contextually relevant multimodal interactions. Our model, MiniGPT-5, exhibits substantial improvement over the baseline models on multimodal generation datasets, including MMDialog and VIST. The human evaluation shows MiniGPT-5 is better than the baseline model on more than 56% cases for multimodal generation, highlighting its efficacy across diverse benchmarks. Project page: https://eric-ai-lab.github.io/minigpt-5.github.io/.

The current state-of-the-art video generative models can produce commercial-grade videos with highly realistic details. However, they still struggle to coherently present multiple sequential events in the stories specified by the prompts, which is foreseeable an essential capability for future long video generation scenarios. For example, top T2V generative models still fail to generate a video of the short simple story "how to put an elephant into a refrigerator." While existing detail-oriented benchmarks primarily focus on fine-grained metrics like aesthetic quality and spatial-temporal consistency, they fall short of evaluating models’ abilities to handle event-level story presentation. To address this gap, we introduce StoryEval, a story-oriented benchmark specifically designed to assess text-to-video (T2V) models’ story-completion capabilities. StoryEval features 423 prompts spanning 7 classes, each representing short stories composed of 2–4 consecutive events. We employ Vision-Language Models, such as GPT-4o and LLaVA-OV-Chat-72B, to verify the completion of each event in the generated videos, applying a unanimous voting method to enhance reliability. Our methods ensure high alignment with human evaluations, and the evaluation of 11 models reveals its challenge, with none exceeding an average story-completion rate of 50%. StoryEval provides a new benchmark for advancing T2V models and highlights the challenges and opportunities in developing next-generation solutions for coherent story-driven video generation. Project website is available at https://ypwang61.github.io/project/StoryEval."The universe is made of stories, not of atoms."— Muriel Rukeyser

Vision language models (VLMs) have shown remarkable capabilities in integrating linguistic and visual reasoning but remain fundamentally limited in understanding dynamic spatiotemporal interactions. Humans effortlessly track and reason about object movements, rotations, and perspective shifts-abilities essential for robust dynamic real-world understanding yet notably lacking in current VLMs. In this paper, we introduce VLM4D, the first benchmark specifically designed to evaluate the spatiotemporal reasoning capabilities of VLMs. Our benchmark comprises diverse real-world and synthetic videos accompanied by carefully curated question-answer pairs emphasizing translational and rotational motions, perspective awareness, and motion continuity. Through comprehensive evaluations of state-of-the-art open and closed-source VLMs, we identify significant performance gaps compared to human baselines, highlighting fundamental deficiencies in existing models. Extensive analysis reveals that VLMs struggle particularly with integrating multiple visual cues and maintaining temporal coherence. We further explore promising directions, such as leveraging 4D feature field reconstruction and targeted spatiotemporal supervised fine-tuning, demonstrating their effectiveness in enhancing spatiotemporal comprehension. Our work aims to encourage deeper exploration into improving VLMs' spatial and temporal grounding, paving the way towards more capable and reliable visual intelligence for dynamic environments.

Multimodal Language Language Models (MLLMs) demonstrate the emerging abilities of "world models"---interpreting and reasoning about complex real-world dynamics. To assess these abilities, we posit videos are the ideal medium, as they encapsulate rich representations of real-world dynamics and causalities. To this end, we introduce MMWorld, a new benchmark for multi-discipline, multi-faceted multimodal video understanding. MMWorld distinguishes itself from previous video understanding benchmarks with two unique advantages: (1) multi-discipline, covering various disciplines that often require domain expertise for comprehensive understanding; (2) multi-faceted reasoning, including explanation, counterfactual thinking, future prediction, etc. MMWorld consists of a human-annotated dataset to evaluate MLLMs with questions about the whole videos and a synthetic dataset to analyze MLLMs within a single modality of perception. Together, MMWorld encompasses 1,910 videos across seven broad disciplines and 69 subdisciplines, complete with 6,627 question-answer pairs and associated captions. The evaluation includes 4 proprietary and 11 open-source MLLMs, which struggle on MMWorld (e.g., GPT-4o performs the best with only 62.5% accuracy), showing large room for improvement. Further ablation studies reveal other interesting findings such as models' different skill sets from humans. We hope MMWorld can serve as an essential step towards world model evaluation in videos.

Given the steep learning curve of professional 3D software and the time- consuming process of managing large 3D assets, language-guided 3D scene editing has significant potential in fields such as virtual reality, augmented reality, and gaming. However, recent approaches to language-guided 3D scene editing either require manual interventions or focus only on appearance modifications without supporting comprehensive scene layout changes. In response, we propose EditRoom, a unified framework capable of executing a variety of layout edits through natural language commands, without requiring manual intervention. Specifically, EditRoom leverages Large Language Models (LLMs) for command planning and generates target scenes using a diffusion-based method, enabling six types of edits: rotate, translate, scale, replace, add, and remove. To address the lack of data for language-guided 3D scene editing, we have developed an automatic pipeline to augment existing 3D scene synthesis datasets and introduced EditRoom-DB, a large-scale dataset with 83k editing pairs, for training and evaluation. Our experiments demonstrate that our approach consistently outperforms other baselines across all metrics, indicating higher accuracy and coherence in language-guided scene layout editing.

Building a conversational embodied agent to execute real-life tasks has been a long-standing yet quite challenging research goal, as it requires effective human-agent communication, multi-modal understanding, long-range sequential decision making, etc. Traditional symbolic methods have scaling and generalization issues, while end-to-end deep learning models suffer from data scarcity and high task complexity, and are often hard to explain. To benefit from both worlds, we propose JARVIS, a neuro-symbolic commonsense reasoning framework for modular, generalizable, and interpretable conversational embodied agents. First, it acquires symbolic representations by prompting large language models (LLMs) for language understanding and sub-goal planning, and by constructing semantic maps from visual observations. Then the symbolic module reasons for sub-goal planning and action generation based on task- and action-level common sense. Extensive experiments on the TEACh dataset validate the efficacy and efficiency of our JARVIS framework, which achieves state-of-the-art (SOTA) results on all three dialog-based embodied tasks, including Execution from Dialog History (EDH), Trajectory from Dialog (TfD), and Two-Agent Task Completion (TATC) (e.g., our method boosts the unseen Success Rate on EDH from 6.1% to 15.8%). Moreover, we systematically analyze the essential factors that affect the task performance and also demonstrate the superiority of our method in few-shot settings.

Recent studies have demonstrated the efficacy of using Reinforcement Learning (RL) in building reasoning models that articulate chains of thoughts prior to producing final answers. However, despite ongoing advances that aim at enabling reasoning for vision-language tasks, existing open-source visual reasoning models typically generate reasoning content with pure natural language, lacking explicit integration of visual information. This limits their ability to produce clearly articulated and visually grounded reasoning chains. To this end, we propose Grounded Reasoning with Images and Texts (GRIT), a novel method for training MLLMs to think with images. GRIT introduces a grounded reasoning paradigm, in which models generate reasoning chains that interleave natural language and explicit bounding box coordinates. These coordinates point to regions of the input image that the model consults during its reasoning process. Additionally, GRIT is equipped with a reinforcement learning approach, GRPO-GR, built upon the GRPO algorithm. GRPO-GR employs robust rewards focused on the final answer accuracy and format of the grounded reasoning output, which eliminates the need for data with reasoning chain annotations or explicit bounding box labels. As a result, GRIT achieves exceptional data efficiency, requiring as few as 20 image-question-answer triplets from existing datasets. Comprehensive evaluations demonstrate that GRIT effectively trains MLLMs to produce coherent and visually grounded reasoning chains, showing a successful unification of reasoning and grounding abilities. All code, data, and checkpoints will be released.

We show that reinforcement learning with verifiable reward using one training example (1-shot RLVR) is effective in incentivizing the math reasoning capabilities of large language models (LLMs). Applying RLVR to the base model Qwen2.5-Math-1.5B, we identify a single example that elevates model performance on MATH500 from 36.0\% to 73.6\% (8.6\% improvement beyond format correction), and improves the average performance across six common mathematical reasoning benchmarks from 17.6\% to 35.7\% (7.0\% non-format gain). This result matches the performance obtained using the 1.2k DeepScaleR subset (MATH500: 73.6\%, average: 35.9\%), which contains the aforementioned example. Furthermore, RLVR with only two examples even slightly exceeds these results (MATH500: 74.8\%, average: 36.6\%). Similar substantial improvements are observed across various models (Qwen2.5-Math-7B, Llama3.2-3B-Instruct, DeepSeek-R1-Distill-Qwen-1.5B), RL algorithms (GRPO and PPO), and different math examples. In addition, we identify some interesting phenomena during 1-shot RLVR, including cross-category generalization, increased frequency of self-reflection, and sustained test performance improvement even after the training accuracy has saturated, a phenomenon we term \textit{post-saturation generalization}. Moreover, we verify that the effectiveness of 1-shot RLVR primarily arises from the policy gradient loss, distinguishing it from the "grokking" phenomenon. We also show the critical role of promoting exploration (e.g., by incorporating entropy loss with an appropriate coefficient) in 1-shot RLVR training. We also further discuss related observations about format correction, label robustness and prompt modification. These findings can inspire future work on RLVR efficiency and encourage a re-examination of recent progress and the underlying mechanisms in RLVR. Our code, models, and data are open source at https://github.com/ypwang61/One-Shot-RLVR.

Human cognition typically involves thinking through abstract, fluid concepts rather than strictly using discrete linguistic tokens. Current Large Language Models (LLMs), however, are constrained to reasoning within the boundaries of human language, processing discrete token embeddings that represent fixed points in semantic space. This discrete constraint restricts the expressive power and upper potential of such reasoning models, often causing incomplete exploration of reasoning paths, as standard Chain-of-Thought (CoT) methods rely on sampling one token per step. In this work, we introduce Soft Thinking, a training-free method that emulates human-like ``soft'' reasoning by generating abstract concept tokens in a continuous concept space. These concept tokens are created by the probability-weighted mixture of token embeddings, which span the continuous concept space, enabling smooth transitions and richer representations that transcend traditional discrete boundaries. In essence, each generated concept token encapsulates multiple meanings from related discrete tokens, implicitly exploring various reasoning paths to converge effectively toward the correct answer. Empirical evaluations on diverse mathematical and coding benchmarks consistently demonstrate the effectiveness and efficiency of Soft Thinking, improving pass@1 accuracy by up to 2.48 points while simultaneously reducing token usage by up to 22.4\% compared to standard CoT. Qualitative analysis further reveals that Soft Thinking outputs remain highly interpretable and readable, highlighting the potential of Soft Thinking to break the inherent limits of discrete language-based reasoning.

Prompt-based learning has been demonstrated as a compelling paradigm contributing to large language models’ tremendous success (LLMs). Inspired by their success in language tasks, existing research has leveraged LLMs in embodied instruction following and task planning. In this work, we tackle the problem of training a robot to understand multimodal prompts, interleaving vision signals with text descriptions. This type of task poses a major challenge to robots’ capability to understand the interconnection and complementarity between vision and language signals. In this work, we introduce an effective framework that learns a policy to perform robot manipulation with multimodal prompts from multi-task expert trajectories. Our methods consist of a two-stage training pipeline that performs inverse dynamics pretraining and multi-task finetuning. To facilitate multimodal understanding, we design our multimodal prompt encoder by augmenting a pretrained LM with a residual connection to the visual input and model the dependencies among action dimensions. Empirically, we evaluate the efficacy of our method on the VIMA-BENCH and establish a new state-of-the-art (10% improvement in success rate). Moreover, we demonstrate that our model exhibits remarkable in-context learning ability.

Kenan Jiang, Xuehai He, Ruize Xu, Xin Wang. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Abstract In many NLP applications, to mitigate data deficiency in a target task, source data is collected to help with target model training. Existing transfer learning methods either select a subset of source examples that are close to the target domain or try to adapt all source examples into the target domain, then use selected or adapted source examples to train the target model. These methods either incur significant information loss or bear the risk that after adaptation, source examples which are originally already in the target domain may be outside the target domain. To address the limitations of these methods, we propose a four-level optimization based framework which simultaneously selects and adapts source data. Our method can automatically identify in-domain and out-of-domain source examples and apply example-specific processing methods: selection for in-domain examples and adaptation for out-of-domain examples. Experiments on various datasets demonstrate the effectiveness of our proposed method.

In computer vision, it has achieved great transfer learning performance via adapting large-scale pretrained vision models (e.g., vision transformers) to downstream tasks. Common approaches for model adaptation either update all model parameters or leverage linear probes. In this paper, we aim to study parameter-efficient model adaptation strategies for vision transformers on the image classification task. We formulate efficient model adaptation as a subspace training problem and perform a comprehensive benchmarking over different efficient adaptation methods. We conduct an empirical study on each efficient model adaptation method focusing on its performance alongside parameter cost. Furthermore, we propose a parameter-efficient model adaptation framework, which first selects submodules by measuring local intrinsic dimensions and then projects them into subspace for further decomposition via a novel Kronecker Adaptation method. We analyze and compare our method with a diverse set of baseline model adaptation methods (including state-of-the-art methods for pretrained language models). Our method performs the best in terms of the tradeoff between accuracy and parameter efficiency across 20 datasets under the few-shot setting and 7 image classification datasets under the full-shot setting.

Despite the success of Transformer models in vision and language tasks, they often learn knowledge from enormous data implicitly and cannot utilize structured input data directly.On the other hand, structured learning approaches such as graph neural networks (GNNs) that integrate prior information can barely compete with Transformer models.In this work, we aim to benefit from both worlds and propose a novel Multimodal Graph Transformer for question answering tasks that requires performing reasoning across multiple modalities.We introduce a graph-involved plug-and-play quasi-attention mechanism to incorporate multimodal graph information, acquired from text and visual data, to the vanilla self-attention as effective prior.In particular, we construct the text graph, dense region graph, and semantic graph to generate adjacency matrices, and then compose them with input vision and language features to perform downstream reasoning.Such a way of regularizing self-attention with graph information significantly improves the inferring ability and helps align features from different modalities.We validate the effectiveness of Multimodal Graph Transformer over its Transformer baselines on GQA, VQAv2, and MultiModalQA datasets.

Attaining a high degree of user controllability in visual generation often requires intricate, fine-grained inputs like layouts. However, such inputs impose a substantial burden on users when compared to simple text inputs. To address the issue, we study how Large Language Models (LLMs) can serve as visual planners by generating layouts from text conditions, and thus collaborate with visual generative models. We propose LayoutGPT, a method to compose in-context visual demonstrations in style sheet language to enhance visual planning skills of LLMs. We show that LayoutGPT can generate plausible layouts in multiple domains, ranging from 2D images to 3D indoor scenes. LayoutGPT also shows superior performance in converting challenging language concepts like numerical and spatial relations to layout arrangements for faithful text-to-image generation. When combined with a downstream image generation model, LayoutGPT outperforms text-to-image models/systems by 20-40\% and achieves comparable performance as human users in designing visual layouts for numerical and spatial correctness. Lastly, LayoutGPT achieves comparable performance to supervised methods in 3D indoor scene synthesis, demonstrating its effectiveness and potential in multiple visual domains.

Xuehai He, Diji Yang, Weixi Feng, Tsu-Jui Fu, Arjun Akula, Varun Jampani, Pradyumna Narayana, Sugato Basu, William Yang Wang, Xin Wang. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 2022.