Jiasen Lu

Jiasen Lu, Christopher Clark, Rowan Zellers et al. · allen-ai, uw

We propose Unified-IO, a model that performs a large variety of AI tasks spanning classical computer vision tasks, including pose estimation, object detection, depth estimation and image generation, vision-and-language tasks such as region captioning and referring expression, to natural language processing tasks such as question answering and paraphrasing. Developing a single unified model for such a large variety of tasks poses unique challenges due to the heterogeneous inputs and outputs pertaining to each task, including RGB images, per-pixel maps, binary masks, bounding boxes, and language. We achieve this unification by homogenizing every supported input and output into a sequence of discrete vocabulary tokens. This common representation across all tasks allows us to train a single transformer-based architecture, jointly on over 90 diverse datasets in the vision and language fields. Unified-IO is the first model capable of performing all 7 tasks on the GRIT benchmark and produces strong results across 16 diverse benchmarks like NYUv2-Depth, ImageNet, VQA2.0, OK-VQA, Swig, VizWizGround, BoolQ, and SciTail, with no task-specific fine-tuning. Code and demos for Unified-IO are available at: https://unified-io.allenai.org.

Matt Deitke, Christopher Clark, Sangho Lee et al. · allen-ai

Today's most advanced vision-language models (VLMs) remain proprietary. The strongest open-weight models rely heavily on synthetic data from proprietary VLMs to achieve good performance, effectively distilling these closed VLMs into open ones. As a result, the community has been missing foundational knowledge about how to build performant VLMs from scratch. We present Molmo, a new family of VLMs that are state-of-the-art in their class of openness. Our key contribution is a collection of new datasets called PixMo, including a dataset of highly detailed image captions for pre-training, a free-form image Q&A dataset for fine-tuning, and an innovative 2D pointing dataset, all collected without the use of external VLMs. The success of our approach relies on careful modeling choices, a well-tuned training pipeline, and, most critically, the quality of our newly collected datasets. Our best-in-class 72B model not only outperforms others in the class of open weight and data models, but also outperforms larger proprietary models including Claude 3.5 Sonnet, and Gemini 1.5 Pro and Flash, second only to GPT-4o based on both academic benchmarks and on a large human evaluation. Our model weights, new datasets, and source code are available at https://molmo.allenai.org/blog.

Duong H. Le, Tuan Pham, Sangho Lee et al. · allen-ai

We introduce OneDiffusion, a versatile, large-scale diffusion model that seamlessly supports bidirectional image synthesis and understanding across diverse tasks. It enables conditional generation from inputs such as text, depth, pose, layout, and semantic maps, while also handling tasks like image deblurring, upscaling, and reverse processes such as depth estimation and segmentation. Additionally, OneDiffusion allows for multi-view generation, camera pose estimation, and instant personalization using sequential image inputs. Our model takes a straightforward yet effective approach by treating all tasks as frame sequences with varying noise scales during training, allowing any frame to act as a conditioning image at inference time. Our unified training framework removes the need for specialized architectures, supports scalable multi-task training, and adapts smoothly to any resolution, enhancing both generalization and scalability. Experimental results demonstrate competitive performance across tasks in both generation and prediction such as text-to-image, multiview generation, ID preservation, depth estimation and camera pose estimation despite relatively small training dataset. Our code and checkpoint are freely available at https://github.com/lehduong/OneDiffusion

Yue Bai, Zichen Zhang, Jiasen Lu et al.

Training large language models (LLMs) and multimodal LLMs necessitates significant computing resources, and existing publicly available LLMs are typically pre-trained on diverse, privately curated datasets spanning various tasks. For instance, LLaMA, Vicuna, and LLaVA are three LLM variants trained with LLaMA base models using very different training recipes, tasks, and data modalities. The training cost and complexity for such LLM variants grow rapidly. In this study, we propose to use a soup strategy to assemble these LLM variants into a single well-generalized multimodal LLM (SoupLM) in a cost-efficient manner. Assembling these LLM variants efficiently brings knowledge and specialities trained from different domains and data modalities into an integrated one (e.g., chatbot speciality from user-shared conversations for Vicuna, and visual capacity from vision-language data for LLaVA), therefore, to avoid computing costs of repetitive training on several different domains. We propose series of soup strategies to systematically benchmark performance gains across various configurations, and probe the soup behavior across base models in the interpolation space.

Albert J. Zhai, Kuo-Hao Zeng, Jiasen Lu et al.

The ability to learn manipulation skills by watching videos of humans has the potential to unlock a new source of highly scalable data for robot learning. Here, we tackle prehensile manipulation, in which tasks involve grasping an object before performing various post-grasp motions. Human videos offer strong signals for learning the post-grasp motions, but they are less useful for learning the prerequisite grasping behaviors, especially for robots without human-like hands. A promising way forward is to use a modular policy design, leveraging a dedicated grasp generator to produce stable grasps. However, arbitrary stable grasps are often not task-compatible, hindering the robot's ability to perform the desired downstream motion. To address this challenge, we present Perceive-Simulate-Imitate (PSI), a framework for training a modular manipulation policy using human video motion data processed by paired grasp-trajectory filtering in simulation. This simulation step extends the trajectory data with grasp suitability labels, which allows for supervised learning of task-oriented grasping capabilities. We show through real-world experiments that our framework can be used to learn precise manipulation skills efficiently without any robot data, resulting in significantly more robust performance than using a grasp generator naively.

Rui Tian, Mingfei Gao, Mingze Xu et al.

We introduce UniGen, a unified multimodal large language model (MLLM) capable of image understanding and generation. We study the full training pipeline of UniGen from a data-centric perspective, including multi-stage pre-training, supervised fine-tuning, and direct preference optimization. More importantly, we propose a new Chain-of-Thought Verification (CoT-V) strategy for test-time scaling, which significantly boosts UniGen's image generation quality using a simple Best-of-N test-time strategy. Specifically, CoT-V enables UniGen to act as both image generator and verifier at test time, assessing the semantic alignment between a text prompt and its generated image in a step-by-step CoT manner. Trained entirely on open-source datasets across all stages, UniGen achieves state-of-the-art performance on a range of image understanding and generation benchmarks, with a final score of 0.78 on GenEval and 85.19 on DPG-Bench. Through extensive ablation studies, our work provides actionable insights and addresses key challenges in the full life cycle of building unified MLLMs, contributing meaningful directions to the future research.

Jiasen Lu, Christopher Clark, Sangho Lee et al. · allen-ai

We present Unified-IO 2, the first autoregressive multimodal model that is capable of understanding and generating image, text, audio, and action. To unify different modalities, we tokenize inputs and outputs -- images, text, audio, action, bounding boxes, etc., into a shared semantic space and then process them with a single encoder-decoder transformer model. Since training with such diverse modalities is challenging, we propose various architectural improvements to stabilize model training. We train our model from scratch on a large multimodal pre-training corpus from diverse sources with a multimodal mixture of denoisers objective. To learn an expansive set of skills, such as following multimodal instructions, we construct and finetune on an ensemble of 120 datasets with prompts and augmentations. With a single unified model, Unified-IO 2 achieves state-of-the-art performance on the GRIT benchmark and strong results in more than 35 benchmarks, including image generation and understanding, natural language understanding, video and audio understanding, and robotic manipulation. We release all our models to the research community.

Teli Ma, Shijie Geng, Mengmeng Wang et al.

The visual world naturally exhibits a long-tailed distribution of open classes, which poses great challenges to modern visual systems. Existing approaches either perform class re-balancing strategies or directly improve network modules to address the problem. However, they still train models with a finite set of predefined labels, limiting their supervision information and restricting their transferability to novel instances. Recent advances in large-scale contrastive visual-language pretraining shed light on a new pathway for visual recognition. With open-vocabulary supervisions, pretrained contrastive vision-language models learn powerful multimodal representations that are promising to handle data deficiency and unseen concepts. By calculating the semantic similarity between visual and text inputs, visual recognition is converted to a vision-language matching problem. Inspired by this, we propose BALLAD to leverage contrastive vision-language models for long-tailed recognition. We first continue pretraining the vision-language backbone through contrastive learning on a specific long-tailed target dataset. Afterward, we freeze the backbone and further employ an additional adapter layer to enhance the representations of tail classes on balanced training samples built with re-sampling strategies. Extensive experiments have been conducted on three popular long-tailed recognition benchmarks. As a result, our simple and effective approach sets the new state-of-the-art performances and outperforms competitive baselines with a large margin. Code is released at https://github.com/gaopengcuhk/BALLAD.

Peng Gao, Jiasen Lu, Hongsheng Li et al.

Convolutional neural networks (CNNs) are ubiquitous in computer vision, with a myriad of effective and efficient variations. Recently, Transformers -- originally introduced in natural language processing -- have been increasingly adopted in computer vision. While early adopters continue to employ CNN backbones, the latest networks are end-to-end CNN-free Transformer solutions. A recent surprising finding shows that a simple MLP based solution without any traditional convolutional or Transformer components can produce effective visual representations. While CNNs, Transformers and MLP-Mixers may be considered as completely disparate architectures, we provide a unified view showing that they are in fact special cases of a more general method to aggregate spatial context in a neural network stack. We present the \model (CONText AggregatIon NEtwoRk), a general-purpose building block for multi-head context aggregation that can exploit long-range interactions \emph{a la} Transformers while still exploiting the inductive bias of the local convolution operation leading to faster convergence speeds, often seen in CNNs. In contrast to Transformer-based methods that do not scale well to downstream tasks that rely on larger input image resolutions, our efficient network, named \modellight, can be employed in object detection and instance segmentation networks such as DETR, RetinaNet and Mask-RCNN to obtain an impressive detection mAP of 38.9, 43.8, 45.1 and mask mAP of 41.3, providing large improvements of 6.6, 7.3, 6.9 and 6.6 pts respectively, compared to a ResNet-50 backbone with a comparable compute and parameter size. Our method also achieves promising results on self-supervised learning compared to DeiT on the DINO framework. Code is released at \url{https://github.com/allenai/container}.

Jialin Wu, Jiasen Lu, Ashish Sabharwal et al.

The problem of knowledge-based visual question answering involves answering questions that require external knowledge in addition to the content of the image. Such knowledge typically comes in various forms, including visual, textual, and commonsense knowledge. Using more knowledge sources increases the chance of retrieving more irrelevant or noisy facts, making it challenging to comprehend the facts and find the answer. To address this challenge, we propose Multi-modal Answer Validation using External knowledge (MAVEx), where the idea is to validate a set of promising answer candidates based on answer-specific knowledge retrieval. Instead of searching for the answer in a vast collection of often irrelevant facts as most existing approaches do, MAVEx aims to learn how to extract relevant knowledge from noisy sources, which knowledge source to trust for each answer candidate, and how to validate the candidate using that source. Our multi-modal setting is the first to leverage external visual knowledge (images searched using Google), in addition to textual knowledge in the form of Wikipedia sentences and ConceptNet concepts. Our experiments with OK-VQA, a challenging knowledge-based VQA dataset, demonstrate that MAVEx achieves new state-of-the-art results. Our code is available at https://github.com/jialinwu17/MAVEX

Michael Cogswell, Jiasen Lu, Rishabh Jain et al.

Can we develop visually grounded dialog agents that can efficiently adapt to new tasks without forgetting how to talk to people? Such agents could leverage a larger variety of existing data to generalize to new tasks, minimizing expensive data collection and annotation. In this work, we study a setting we call "Dialog without Dialog", which requires agents to develop visually grounded dialog models that can adapt to new tasks without language level supervision. By factorizing intention and language, our model minimizes linguistic drift after fine-tuning for new tasks. We present qualitative results, automated metrics, and human studies that all show our model can adapt to new tasks and maintain language quality. Baselines either fail to perform well at new tasks or experience language drift, becoming unintelligible to humans. Code has been made available at https://github.com/mcogswell/dialog_without_dialog

Chih-Yao Ma, Jiasen Lu, Zuxuan Wu et al.

The Vision-and-Language Navigation (VLN) task entails an agent following navigational instruction in photo-realistic unknown environments. This challenging task demands that the agent be aware of which instruction was completed, which instruction is needed next, which way to go, and its navigation progress towards the goal. In this paper, we introduce a self-monitoring agent with two complementary components: (1) visual-textual co-grounding module to locate the instruction completed in the past, the instruction required for the next action, and the next moving direction from surrounding images and (2) progress monitor to ensure the grounded instruction correctly reflects the navigation progress. We test our self-monitoring agent on a standard benchmark and analyze our proposed approach through a series of ablation studies that elucidate the contributions of the primary components. Using our proposed method, we set the new state of the art by a significant margin (8% absolute increase in success rate on the unseen test set). Code is available at https://github.com/chihyaoma/selfmonitoring-agent .

Jiasen Lu, Jianwei Yang, Dhruv Batra et al.

We introduce a novel framework for image captioning that can produce natural language explicitly grounded in entities that object detectors find in the image. Our approach reconciles classical slot filling approaches (that are generally better grounded in images) with modern neural captioning approaches (that are generally more natural sounding and accurate). Our approach first generates a sentence `template' with slot locations explicitly tied to specific image regions. These slots are then filled in by visual concepts identified in the regions by object detectors. The entire architecture (sentence template generation and slot filling with object detectors) is end-to-end differentiable. We verify the effectiveness of our proposed model on different image captioning tasks. On standard image captioning and novel object captioning, our model reaches state-of-the-art on both COCO and Flickr30k datasets. We also demonstrate that our model has unique advantages when the train and test distributions of scene compositions -- and hence language priors of associated captions -- are different. Code has been made available at: https://github.com/jiasenlu/NeuralBabyTalk

Jiasen Lu, Anitha Kannan, Jianwei Yang et al.

We present a novel training framework for neural sequence models, particularly for grounded dialog generation. The standard training paradigm for these models is maximum likelihood estimation (MLE), or minimizing the cross-entropy of the human responses. Across a variety of domains, a recurring problem with MLE trained generative neural dialog models (G) is that they tend to produce 'safe' and generic responses ("I don't know", "I can't tell"). In contrast, discriminative dialog models (D) that are trained to rank a list of candidate human responses outperform their generative counterparts; in terms of automatic metrics, diversity, and informativeness of the responses. However, D is not useful in practice since it cannot be deployed to have real conversations with users. Our work aims to achieve the best of both worlds -- the practical usefulness of G and the strong performance of D -- via knowledge transfer from D to G. Our primary contribution is an end-to-end trainable generative visual dialog model, where G receives gradients from D as a perceptual (not adversarial) loss of the sequence sampled from G. We leverage the recently proposed Gumbel-Softmax (GS) approximation to the discrete distribution -- specifically, an RNN augmented with a sequence of GS samplers, coupled with the straight-through gradient estimator to enable end-to-end differentiability. We also introduce a stronger encoder for visual dialog, and employ a self-attention mechanism for answer encoding along with a metric learning loss to aid D in better capturing semantic similarities in answer responses. Overall, our proposed model outperforms state-of-the-art on the VisDial dataset by a significant margin (2.67% on recall@10). The source code can be downloaded from https://github.com/jiasenlu/visDial.pytorch.

Alexander H. Miller, Will Feng, Adam Fisch et al.

We introduce ParlAI (pronounced "par-lay"), an open-source software platform for dialog research implemented in Python, available at http://parl.ai. Its goal is to provide a unified framework for sharing, training and testing of dialog models, integration of Amazon Mechanical Turk for data collection, human evaluation, and online/reinforcement learning; and a repository of machine learning models for comparing with others' models, and improving upon existing architectures. Over 20 tasks are supported in the first release, including popular datasets such as SQuAD, bAbI tasks, MCTest, WikiQA, QACNN, QADailyMail, CBT, bAbI Dialog, Ubuntu, OpenSubtitles and VQA. Several models are integrated, including neural models such as memory networks, seq2seq and attentive LSTMs.

Sucheng Ren, Chen Chen, Zhenbang Wang et al.

Text-to-image generation has advanced rapidly with diffusion models, progressing from CLIP and T5 conditioning to unified systems where a single LLM backbone handles both visual understanding and generation. Despite the architectural unification, these systems frequently fail to faithfully align complex prompts during synthesis, even though they remain highly accurate at verifying whether an image satisfies those same prompts. We formalize this as the \emph{understanding-generation gap} and propose UniReasoner, a framework that leverages the LLM as a universal reasoner to convert its understanding strength into direct generation guidance. Given a prompt, the LLM first produces a coarse visual draft composed of discrete vision tokens. It then performs a self-critique by evaluating the draft for prompt consistency, producing a grounded textual evaluation that pinpoints what needs to be corrected. Finally, a diffusion model is conditioned jointly on the prompt, the visual draft, and the evaluation, ensuring that generation is guided by explicit corrective signals. Each signal addresses a limitation of the other: the draft provides a concrete, scene-level anchor that reduces under-specification in text-only conditioning, while the evaluation turns verification into grounded, actionable constraints that correct omissions, hallucinations, and relational errors. Experiments show that UniReasoner improves compositional alignment and semantic faithfulness under the same diffusion backbone while maintaining image quality, demonstrating a practical way to exploit LLM reasoning to close the understanding-generation gap.

Zhaofeng Wu, Xinyan Velocity Yu, Dani Yogatama et al. · mit

Modern language models can process inputs across diverse languages and modalities. We hypothesize that models acquire this capability through learning a shared representation space across heterogeneous data types (e.g., different languages and modalities), which places semantically similar inputs near one another, even if they are from different modalities/languages. We term this the semantic hub hypothesis, following the hub-and-spoke model from neuroscience (Patterson et al., 2007) which posits that semantic knowledge in the human brain is organized through a transmodal semantic "hub" which integrates information from various modality-specific "spokes" regions. We first show that model representations for semantically equivalent inputs in different languages are similar in the intermediate layers, and that this space can be interpreted using the model's dominant pretraining language via the logit lens. This tendency extends to other data types, including arithmetic expressions, code, and visual/audio inputs. Interventions in the shared representation space in one data type also predictably affect model outputs in other data types, suggesting that this shared representations space is not simply a vestigial byproduct of large-scale training on broad data, but something that is actively utilized by the model during input processing.

Zongyu Lin, Wei Liu, Chen Chen et al.

The field of video generation has made remarkable advancements, yet there remains a pressing need for a clear, systematic recipe that can guide the development of robust and scalable models. In this work, we present a comprehensive study that systematically explores the interplay of model architectures, training recipes, and data curation strategies, culminating in a simple and scalable text-image-conditioned video generation method, named STIV. Our framework integrates image condition into a Diffusion Transformer (DiT) through frame replacement, while incorporating text conditioning via a joint image-text conditional classifier-free guidance. This design enables STIV to perform both text-to-video (T2V) and text-image-to-video (TI2V) tasks simultaneously. Additionally, STIV can be easily extended to various applications, such as video prediction, frame interpolation, multi-view generation, and long video generation, etc. With comprehensive ablation studies on T2I, T2V, and TI2V, STIV demonstrate strong performance, despite its simple design. An 8.7B model with 512 resolution achieves 83.1 on VBench T2V, surpassing both leading open and closed-source models like CogVideoX-5B, Pika, Kling, and Gen-3. The same-sized model also achieves a state-of-the-art result of 90.1 on VBench I2V task at 512 resolution. By providing a transparent and extensible recipe for building cutting-edge video generation models, we aim to empower future research and accelerate progress toward more versatile and reliable video generation solutions.

Mingze Xu, Mingfei Gao, Shiyu Li et al.

We introduce SlowFast-LLaVA-1.5 (abbreviated as SF-LLaVA-1.5), a family of video large language models (LLMs) offering a token-efficient solution for long-form video understanding. We incorporate the two-stream SlowFast mechanism into a streamlined training pipeline, and perform joint video-image training on a carefully curated data mixture of only publicly available datasets. Our primary focus is on highly efficient model scales (1B and 3B), demonstrating that even relatively small Video LLMs can achieve state-of-the-art performance on video understanding, meeting the demand for mobile-friendly models. Experimental results demonstrate that SF-LLaVA-1.5 achieves superior performance on a wide range of video and image tasks, with robust results at all model sizes (ranging from 1B to 7B). Notably, SF-LLaVA-1.5 achieves state-of-the-art results in long-form video understanding (e.g., LongVideoBench and MLVU) and excels at small scales across various video benchmarks.

Jiasen Lu, Liangchen Song, Mingze Xu et al.

We present AToken, the first unified visual tokenizer that achieves both high-fidelity reconstruction and semantic understanding across images, videos, and 3D assets. Unlike existing tokenizers that specialize in either reconstruction or understanding for single modalities, AToken encodes these diverse visual inputs into a shared 4D latent space, unifying both tasks and modalities in a single framework. Specifically, we introduce a pure transformer architecture with 4D rotary position embeddings to process visual inputs of arbitrary resolutions and temporal durations. To ensure stable training, we introduce an adversarial-free training objective that combines perceptual and Gram matrix losses, achieving state-of-the-art reconstruction quality. By employing a progressive training curriculum, AToken gradually expands from single images, videos, and 3D, and supports both continuous and discrete latent tokens. AToken achieves 0.21 rFID with 82.2% ImageNet accuracy for images, 3.01 rFVD with 40.2% MSRVTT retrieval for videos, and 28.28 PSNR with 90.9% classification accuracy for 3D.. In downstream applications, AToken enables both visual generation tasks (e.g., image generation with continuous and discrete tokens, text-to-video generation, image-to-3D synthesis) and understanding tasks (e.g., multimodal LLMs), achieving competitive performance across all benchmarks. These results shed light on the next-generation multimodal AI systems built upon unified visual tokenization.

Yusu Qian, Eli Bocek-Rivele, Liangchen Song et al.

Recent advances in multimodal models have demonstrated remarkable text-guided image editing capabilities, with systems like GPT-4o and Nano-Banana setting new benchmarks. However, the research community's progress remains constrained by the absence of large-scale, high-quality, and openly accessible datasets built from real images. We introduce Pico-Banana-400K, a comprehensive 400K-image dataset for instruction-based image editing. Our dataset is constructed by leveraging Nano-Banana to generate diverse edit pairs from real photographs in the OpenImages collection. What distinguishes Pico-Banana-400K from previous synthetic datasets is our systematic approach to quality and diversity. We employ a fine-grained image editing taxonomy to ensure comprehensive coverage of edit types while maintaining precise content preservation and instruction faithfulness through MLLM-based quality scoring and careful curation. Beyond single turn editing, Pico-Banana-400K enables research into complex editing scenarios. The dataset includes three specialized subsets: (1) a 72K-example multi-turn collection for studying sequential editing, reasoning, and planning across consecutive modifications; (2) a 56K-example preference subset for alignment research and reward model training; and (3) paired long-short editing instructions for developing instruction rewriting and summarization capabilities. By providing this large-scale, high-quality, and task-rich resource, Pico-Banana-400K establishes a robust foundation for training and benchmarking the next generation of text-guided image editing models.

Rui Tian, Mingfei Gao, Haiming Gang et al.

We present UniGen-1.5, a unified multimodal large language model (MLLM) for advanced image understanding, generation and editing. Building upon UniGen, we comprehensively enhance the model architecture and training pipeline to strengthen the image understanding and generation capabilities while unlocking strong image editing ability. Especially, we propose a unified Reinforcement Learning (RL) strategy that improves both image generation and image editing jointly via shared reward models. To further enhance image editing performance, we propose a light Edit Instruction Alignment stage that significantly improves the editing instruction comprehension that is essential for the success of the RL training. Experimental results show that UniGen-1.5 demonstrates competitive understanding and generation performance. Specifically, UniGen-1.5 achieves 0.89 and 4.31 overall scores on GenEval and ImgEdit that surpass the state-of-the-art models such as BAGEL and reaching performance comparable to proprietary models such as GPT-Image-1.

Sucheng Ren, Chen Chen, Zhenbang Wang et al.

Autoregressive models for video generation typically operate frame-by-frame, extending next-token prediction from language to video's temporal dimension. We question that unlike word as token is universally agreed in language if frame is a appropriate prediction unit? To address this, we present VideoAR, a unified framework that supports a spectrum of prediction units including full frames, key-detail frames, multiscale refinements, and spatiotemporal cubes. Among these designs, we find model video generation using \textit{spatiotemporal} cubes as prediction units, which allows autoregressive models to operate across both spatial and temporal dimensions simultaneously. This approach eliminates the assumption that frames are the natural atomic units for video autoregression. We evaluate VideoAR across diverse prediction strategies, finding that cube-based prediction consistently delivers superior quality, speed, and temporal coherence. By removing the frame-by-frame constraint, our video generator surpasses state-of-the-art baselines on VBench while achieving faster inference and enabling seamless scaling to minute-long sequences. We hope this work will motivate rethinking sequence decomposition in video and other spatiotemporal domains.

Chen Chen, Pengsheng Guo, Liangchen Song et al.

Conditional generative modeling aims to learn a conditional data distribution from samples containing data-condition pairs. For this, diffusion and flow-based methods have attained compelling results. These methods use a learned (flow) model to transport an initial standard Gaussian noise that ignores the condition to the conditional data distribution. The model is hence required to learn both mass transport and conditional injection. To ease the demand on the model, we propose Condition-Aware Reparameterization for Flow Matching (CAR-Flow) -- a lightweight, learned shift that conditions the source, the target, or both distributions. By relocating these distributions, CAR-Flow shortens the probability path the model must learn, leading to faster training in practice. On low-dimensional synthetic data, we visualize and quantify the effects of CAR-Flow. On higher-dimensional natural image data (ImageNet-256), equipping SiT-XL/2 with CAR-Flow reduces FID from 2.07 to 1.68, while introducing less than 0.6% additional parameters.

Duong H. Le, Tuan Pham, Aniruddha Kembhavi et al.

We present Piva (Preserving Identity with Variational Score Distillation), a novel optimization-based method for editing images and 3D models based on diffusion models. Specifically, our approach is inspired by the recently proposed method for 2D image editing - Delta Denoising Score (DDS). We pinpoint the limitations in DDS for 2D and 3D editing, which causes detail loss and over-saturation. To address this, we propose an additional score distillation term that enforces identity preservation. This results in a more stable editing process, gradually optimizing NeRF models to match target prompts while retaining crucial input characteristics. We demonstrate the effectiveness of our approach in zero-shot image and neural field editing. Our method successfully alters visual attributes, adds both subtle and substantial structural elements, translates shapes, and achieves competitive results on standard 2D and 3D editing benchmarks. Additionally, our method imposes no constraints like masking or pre-training, making it compatible with a wide range of pre-trained diffusion models. This allows for versatile editing without needing neural field-to-mesh conversion, offering a more user-friendly experience.

Jiasen Lu, Jordi Salvador, Roozbeh Mottaghi et al.

Embodied AI has seen steady progress across a diverse set of independent tasks. While these varied tasks have different end goals, the basic skills required to complete them successfully overlap significantly. In this paper, our goal is to leverage these shared skills to learn to perform multiple tasks jointly. We propose Atomic Skill Completion (ASC), an approach for multi-task training for Embodied AI, where a set of atomic skills shared across multiple tasks are composed together to perform the tasks. The key to the success of this approach is a pre-training scheme that decouples learning of the skills from the high-level tasks making joint training effective. We use ASC to train agents within the AI2-THOR environment to perform four interactive tasks jointly and find it to be remarkably effective. In a multi-task setting, ASC improves success rates by a factor of 2x on Seen scenes and 4x on Unseen scenes compared to no pre-training. Importantly, ASC enables us to train a multi-task agent that has a 52% higher Success Rate than training 4 independent single task agents. Finally, our hierarchical agents are more interpretable than traditional black-box architectures.

Rowan Zellers, Jiasen Lu, Ximing Lu et al.

As humans, we navigate a multimodal world, building a holistic understanding from all our senses. We introduce MERLOT Reserve, a model that represents videos jointly over time -- through a new training objective that learns from audio, subtitles, and video frames. Given a video, we replace snippets of text and audio with a MASK token; the model learns by choosing the correct masked-out snippet. Our objective learns faster than alternatives, and performs well at scale: we pretrain on 20 million YouTube videos. Empirical results show that MERLOT Reserve learns strong multimodal representations. When finetuned, it sets state-of-the-art on Visual Commonsense Reasoning (VCR), TVQA, and Kinetics-600; outperforming prior work by 5%, 7%, and 1.5% respectively. Ablations show that these tasks benefit from audio pretraining -- even VCR, a QA task centered around images (without sound). Moreover, our objective enables out-of-the-box prediction, revealing strong multimodal commonsense understanding. In a fully zero-shot setting, our model obtains competitive results on four video tasks, even outperforming supervised approaches on the recently proposed Situated Reasoning (STAR) benchmark. We analyze why audio enables better vision-language representations, suggesting significant opportunities for future research. We conclude by discussing ethical and societal implications of multimodal pretraining.

Jaemin Cho, Jiasen Lu, Dustin Schwenk et al.

Mirroring the success of masked language models, vision-and-language counterparts like ViLBERT, LXMERT and UNITER have achieved state of the art performance on a variety of multimodal discriminative tasks like visual question answering and visual grounding. Recent work has also successfully adapted such models towards the generative task of image captioning. This begs the question: Can these models go the other way and generate images from pieces of text? Our analysis of a popular representative from this model family - LXMERT - finds that it is unable to generate rich and semantically meaningful imagery with its current training setup. We introduce X-LXMERT, an extension to LXMERT with training refinements including: discretizing visual representations, using uniform masking with a large range of masking ratios and aligning the right pre-training datasets to the right objectives which enables it to paint. X-LXMERT's image generation capabilities rival state of the art generative models while its question answering and captioning abilities remains comparable to LXMERT. Finally, we demonstrate the generality of these training refinements by adding image generation capabilities into UNITER to produce X-UNITER.

Yash Kant, Dhruv Batra, Peter Anderson et al.

Textual cues are essential for everyday tasks like buying groceries and using public transport. To develop this assistive technology, we study the TextVQA task, i.e., reasoning about text in images to answer a question. Existing approaches are limited in their use of spatial relations and rely on fully-connected transformer-like architectures to implicitly learn the spatial structure of a scene. In contrast, we propose a novel spatially aware self-attention layer such that each visual entity only looks at neighboring entities defined by a spatial graph. Further, each head in our multi-head self-attention layer focuses on a different subset of relations. Our approach has two advantages: (1) each head considers local context instead of dispersing the attention amongst all visual entities; (2) we avoid learning redundant features. We show that our model improves the absolute accuracy of current state-of-the-art methods on TextVQA by 2.2% overall over an improved baseline, and 4.62% on questions that involve spatial reasoning and can be answered correctly using OCR tokens. Similarly on ST-VQA, we improve the absolute accuracy by 4.2%. We further show that spatially aware self-attention improves visual grounding.

Jiasen Lu, Vedanuj Goswami, Marcus Rohrbach et al.

Much of vision-and-language research focuses on a small but diverse set of independent tasks and supporting datasets often studied in isolation; however, the visually-grounded language understanding skills required for success at these tasks overlap significantly. In this work, we investigate these relationships between vision-and-language tasks by developing a large-scale, multi-task training regime. Our approach culminates in a single model on 12 datasets from four broad categories of task including visual question answering, caption-based image retrieval, grounding referring expressions, and multi-modal verification. Compared to independently trained single-task models, this represents a reduction from approximately 3 billion parameters to 270 million while simultaneously improving performance by 2.05 points on average across tasks. We use our multi-task framework to perform in-depth analysis of the effect of joint training diverse tasks. Further, we show that finetuning task-specific models from our single multi-task model can lead to further improvements, achieving performance at or above the state-of-the-art.

Jiasen Lu, Dhruv Batra, Devi Parikh et al.

We present ViLBERT (short for Vision-and-Language BERT), a model for learning task-agnostic joint representations of image content and natural language. We extend the popular BERT architecture to a multi-modal two-stream model, pro-cessing both visual and textual inputs in separate streams that interact through co-attentional transformer layers. We pretrain our model through two proxy tasks on the large, automatically collected Conceptual Captions dataset and then transfer it to multiple established vision-and-language tasks -- visual question answering, visual commonsense reasoning, referring expressions, and caption-based image retrieval -- by making only minor additions to the base architecture. We observe significant improvements across tasks compared to existing task-specific models -- achieving state-of-the-art on all four tasks. Our work represents a shift away from learning groundings between vision and language only as part of task training and towards treating visual grounding as a pretrainable and transferable capability.

Michael Cogswell, Jiasen Lu, Stefan Lee et al.

Recent work has studied the emergence of language among deep reinforcement learning agents that must collaborate to solve a task. Of particular interest are the factors that cause language to be compositional -- i.e., express meaning by combining words which themselves have meaning. Evolutionary linguists have found that in addition to structural priors like those already studied in deep learning, the dynamics of transmitting language from generation to generation contribute significantly to the emergence of compositionality. In this paper, we introduce these cultural evolutionary dynamics into language emergence by periodically replacing agents in a population to create a knowledge gap, implicitly inducing cultural transmission of language. We show that this implicit cultural transmission encourages the resulting languages to exhibit better compositional generalization.

Jianwei Yang, Jiasen Lu, Stefan Lee et al.

In an open-world setting, it is inevitable that an intelligent agent (e.g., a robot) will encounter visual objects, attributes or relationships it does not recognize. In this work, we develop an agent empowered with visual curiosity, i.e. the ability to ask questions to an Oracle (e.g., human) about the contents in images (e.g., What is the object on the left side of the red cube?) and build visual recognition model based on the answers received (e.g., Cylinder). In order to do this, the agent must (1) understand what it recognizes and what it does not, (2) formulate a valid, unambiguous and informative language query (a question) to ask the Oracle, (3) derive the parameters of visual classifiers from the Oracle response and (4) leverage the updated visual classifiers to ask more clarified questions. Specifically, we propose a novel framework and formulate the learning of visual curiosity as a reinforcement learning problem. In this framework, all components of our agent, visual recognition module (to see), question generation policy (to ask), answer digestion module (to understand) and graph memory module (to memorize), are learned entirely end-to-end to maximize the reward derived from the scene graph obtained by the agent as a consequence of the dialog with the Oracle. Importantly, the question generation policy is disentangled from the visual recognition system and specifics of the environment. Consequently, we demonstrate a sort of double generalization. Our question generation policy generalizes to new environments and a new pair of eyes, i.e., new visual system. Trained on a synthetic dataset, our results show that our agent learns new visual concepts significantly faster than several heuristic baselines, even when tested on synthetic environments with novel objects, as well as in a realistic environment.

Jianwei Yang, Jiasen Lu, Stefan Lee et al.

We propose a novel scene graph generation model called Graph R-CNN, that is both effective and efficient at detecting objects and their relations in images. Our model contains a Relation Proposal Network (RePN) that efficiently deals with the quadratic number of potential relations between objects in an image. We also propose an attentional Graph Convolutional Network (aGCN) that effectively captures contextual information between objects and relations. Finally, we introduce a new evaluation metric that is more holistic and realistic than existing metrics. We report state-of-the-art performance on scene graph generation as evaluated using both existing and our proposed metrics.

Jiasen Lu, Caiming Xiong, Devi Parikh et al.

Attention-based neural encoder-decoder frameworks have been widely adopted for image captioning. Most methods force visual attention to be active for every generated word. However, the decoder likely requires little to no visual information from the image to predict non-visual words such as "the" and "of". Other words that may seem visual can often be predicted reliably just from the language model e.g., "sign" after "behind a red stop" or "phone" following "talking on a cell". In this paper, we propose a novel adaptive attention model with a visual sentinel. At each time step, our model decides whether to attend to the image (and if so, to which regions) or to the visual sentinel. The model decides whether to attend to the image and where, in order to extract meaningful information for sequential word generation. We test our method on the COCO image captioning 2015 challenge dataset and Flickr30K. Our approach sets the new state-of-the-art by a significant margin.

Jiasen Lu, Jianwei Yang, Dhruv Batra et al.

A number of recent works have proposed attention models for Visual Question Answering (VQA) that generate spatial maps highlighting image regions relevant to answering the question. In this paper, we argue that in addition to modeling "where to look" or visual attention, it is equally important to model "what words to listen to" or question attention. We present a novel co-attention model for VQA that jointly reasons about image and question attention. In addition, our model reasons about the question (and consequently the image via the co-attention mechanism) in a hierarchical fashion via a novel 1-dimensional convolution neural networks (CNN). Our model improves the state-of-the-art on the VQA dataset from 60.3% to 60.5%, and from 61.6% to 63.3% on the COCO-QA dataset. By using ResNet, the performance is further improved to 62.1% for VQA and 65.4% for COCO-QA.

Aishwarya Agrawal, Jiasen Lu, Stanislaw Antol et al.

We propose the task of free-form and open-ended Visual Question Answering (VQA). Given an image and a natural language question about the image, the task is to provide an accurate natural language answer. Mirroring real-world scenarios, such as helping the visually impaired, both the questions and answers are open-ended. Visual questions selectively target different areas of an image, including background details and underlying context. As a result, a system that succeeds at VQA typically needs a more detailed understanding of the image and complex reasoning than a system producing generic image captions. Moreover, VQA is amenable to automatic evaluation, since many open-ended answers contain only a few words or a closed set of answers that can be provided in a multiple-choice format. We provide a dataset containing ~0.25M images, ~0.76M questions, and ~10M answers (www.visualqa.org), and discuss the information it provides. Numerous baselines and methods for VQA are provided and compared with human performance. Our VQA demo is available on CloudCV (http://cloudcv.org/vqa).