Yicong Hong

Zheyuan Liu, Weixuan Sun, Yicong Hong et al.

Composed image retrieval searches for a target image based on a multi-modal user query comprised of a reference image and modification text describing the desired changes. Existing approaches to solving this challenging task learn a mapping from the (reference image, modification text)-pair to an image embedding that is then matched against a large image corpus. One area that has not yet been explored is the reverse direction, which asks the question, what reference image when modified as described by the text would produce the given target image? In this work we propose a bi-directional training scheme that leverages such reversed queries and can be applied to existing composed image retrieval architectures with minimum changes, which improves the performance of the model. To encode the bi-directional query we prepend a learnable token to the modification text that designates the direction of the query and then finetune the parameters of the text embedding module. We make no other changes to the network architecture. Experiments on two standard datasets show that our novel approach achieves improved performance over a baseline BLIP-based model that itself already achieves competitive performance. Our code is released at https://github.com/Cuberick-Orion/Bi-Blip4CIR.

Zun Wang, Jialu Li, Yicong Hong et al.

Recent research in language-guided visual navigation has demonstrated a significant demand for the diversity of traversable environments and the quantity of supervision for training generalizable agents. To tackle the common data scarcity issue in existing vision-and-language navigation datasets, we propose an effective paradigm for generating large-scale data for learning, which applies 1200+ photo-realistic environments from HM3D and Gibson datasets and synthesizes 4.9 million instruction trajectory pairs using fully-accessible resources on the web. Importantly, we investigate the influence of each component in this paradigm on the agent's performance and study how to adequately apply the augmented data to pre-train and fine-tune an agent. Thanks to our large-scale dataset, the performance of an existing agent can be pushed up (+11% absolute with regard to previous SoTA) to a significantly new best of 80% single-run success rate on the R2R test split by simple imitation learning. The long-lasting generalization gap between navigating in seen and unseen environments is also reduced to less than 1% (versus 8% in the previous best method). Moreover, our paradigm also facilitates different models to achieve new state-of-the-art navigation results on CVDN, REVERIE, and R2R in continuous environments.

Jiahao Li, Hao Tan, Kai Zhang et al.

Text-to-3D with diffusion models has achieved remarkable progress in recent years. However, existing methods either rely on score distillation-based optimization which suffer from slow inference, low diversity and Janus problems, or are feed-forward methods that generate low-quality results due to the scarcity of 3D training data. In this paper, we propose Instant3D, a novel method that generates high-quality and diverse 3D assets from text prompts in a feed-forward manner. We adopt a two-stage paradigm, which first generates a sparse set of four structured and consistent views from text in one shot with a fine-tuned 2D text-to-image diffusion model, and then directly regresses the NeRF from the generated images with a novel transformer-based sparse-view reconstructor. Through extensive experiments, we demonstrate that our method can generate diverse 3D assets of high visual quality within 20 seconds, which is two orders of magnitude faster than previous optimization-based methods that can take 1 to 10 hours. Our project webpage: https://jiahao.ai/instant3d/.

Yicong Hong, Yang Zhou, Ruiyi Zhang et al.

Being able to perceive the semantics and the spatial structure of the environment is essential for visual navigation of a household robot. However, most existing works only employ visual backbones pre-trained either with independent images for classification or with self-supervised learning methods to adapt to the indoor navigation domain, neglecting the spatial relationships that are essential to the learning of navigation. Inspired by the behavior that humans naturally build semantically and spatially meaningful cognitive maps in their brains during navigation, in this paper, we propose a novel navigational-specific visual representation learning method by contrasting the agent's egocentric views and semantic maps (Ego$^2$-Map). We apply the visual transformer as the backbone encoder and train the model with data collected from the large-scale Habitat-Matterport3D environments. Ego$^2$-Map learning transfers the compact and rich information from a map, such as objects, structure and transition, to the agent's egocentric representations for navigation. Experiments show that agents using our learned representations on object-goal navigation outperform recent visual pre-training methods. Moreover, our representations significantly improve vision-and-language navigation in continuous environments for both high-level and low-level action spaces, achieving new state-of-the-art results of 47% SR and 41% SPL on the test server.

Yicong Hong, Kai Zhang, Jiuxiang Gu et al.

We propose the first Large Reconstruction Model (LRM) that predicts the 3D model of an object from a single input image within just 5 seconds. In contrast to many previous methods that are trained on small-scale datasets such as ShapeNet in a category-specific fashion, LRM adopts a highly scalable transformer-based architecture with 500 million learnable parameters to directly predict a neural radiance field (NeRF) from the input image. We train our model in an end-to-end manner on massive multi-view data containing around 1 million objects, including both synthetic renderings from Objaverse and real captures from MVImgNet. This combination of a high-capacity model and large-scale training data empowers our model to be highly generalizable and produce high-quality 3D reconstructions from various testing inputs, including real-world in-the-wild captures and images created by generative models. Video demos and interactable 3D meshes can be found on our LRM project webpage: https://yiconghong.me/LRM.

Yanyuan Qiao, Yuankai Qi, Yicong Hong et al.

Pre-training has been adopted in a few of recent works for Vision-and-Language Navigation (VLN). However, previous pre-training methods for VLN either lack the ability to predict future actions or ignore the trajectory contexts, which are essential for a greedy navigation process. In this work, to promote the learning of spatio-temporal visual-textual correspondence as well as the agent's capability of decision making, we propose a novel history-and-order aware pre-training paradigm (HOP) with VLN-specific objectives that exploit the past observations and support future action prediction. Specifically, in addition to the commonly used Masked Language Modeling (MLM) and Trajectory-Instruction Matching (TIM), we design two proxy tasks to model temporal order information: Trajectory Order Modeling (TOM) and Group Order Modeling (GOM). Moreover, our navigation action prediction is also enhanced by introducing the task of Action Prediction with History (APH), which takes into account the history visual perceptions. Extensive experimental results on four downstream VLN tasks (R2R, REVERIE, NDH, RxR) demonstrate the effectiveness of our proposed method compared against several state-of-the-art agents.

Dong An, Zun Wang, Yangguang Li et al.

This report presents the methods of the winning entry of the RxR-Habitat Competition in CVPR 2022. The competition addresses the problem of Vision-and-Language Navigation in Continuous Environments (VLN-CE), which requires an agent to follow step-by-step natural language instructions to reach a target. We present a modular plan-and-control approach for the task. Our model consists of three modules: the candidate waypoints predictor (CWP), the history enhanced planner and the tryout controller. In each decision loop, CWP first predicts a set of candidate waypoints based on depth observations from multiple views. It can reduce the complexity of the action space and facilitate planning. Then, a history-enhanced planner is adopted to select one of the candidate waypoints as the subgoal. The planner additionally encodes historical memory to track the navigation progress, which is especially effective for long-horizon navigation. Finally, we propose a non-parametric heuristic controller named tryout to execute low-level actions to reach the planned subgoal. It is based on the trial-and-error mechanism which can help the agent to avoid obstacles and escape from getting stuck. All three modules work hierarchically until the agent stops. We further take several recent advances of Vision-and-Language Navigation (VLN) to improve the performance such as pretraining based on large-scale synthetic in-domain dataset, environment-level data augmentation and snapshot model ensemble. Our model won the RxR-Habitat Competition 2022, with 48% and 90% relative improvements over existing methods on NDTW and SR metrics respectively.

Yicong Hong, Zun Wang, Qi Wu et al.

Most existing works in vision-and-language navigation (VLN) focus on either discrete or continuous environments, training agents that cannot generalize across the two. The fundamental difference between the two setups is that discrete navigation assumes prior knowledge of the connectivity graph of the environment, so that the agent can effectively transfer the problem of navigation with low-level controls to jumping from node to node with high-level actions by grounding to an image of a navigable direction. To bridge the discrete-to-continuous gap, we propose a predictor to generate a set of candidate waypoints during navigation, so that agents designed with high-level actions can be transferred to and trained in continuous environments. We refine the connectivity graph of Matterport3D to fit the continuous Habitat-Matterport3D, and train the waypoints predictor with the refined graphs to produce accessible waypoints at each time step. Moreover, we demonstrate that the predicted waypoints can be augmented during training to diversify the views and paths, and therefore enhance agent's generalization ability. Through extensive experiments we show that agents navigating in continuous environments with predicted waypoints perform significantly better than agents using low-level actions, which reduces the absolute discrete-to-continuous gap by 11.76% Success Weighted by Path Length (SPL) for the Cross-Modal Matching Agent and 18.24% SPL for the Recurrent VLN-BERT. Our agents, trained with a simple imitation learning objective, outperform previous methods by a large margin, achieving new state-of-the-art results on the testing environments of the R2R-CE and the RxR-CE datasets.

Gengze Zhou, Yicong Hong, Zun Wang et al.

Capitalizing on the remarkable advancements in Large Language Models (LLMs), there is a burgeoning initiative to harness LLMs for instruction following robotic navigation. Such a trend underscores the potential of LLMs to generalize navigational reasoning and diverse language understanding. However, a significant discrepancy in agent performance is observed when integrating LLMs in the Vision-and-Language navigation (VLN) tasks compared to previous downstream specialist models. Furthermore, the inherent capacity of language to interpret and facilitate communication in agent interactions is often underutilized in these integrations. In this work, we strive to bridge the divide between VLN-specialized models and LLM-based navigation paradigms, while maintaining the interpretative prowess of LLMs in generating linguistic navigational reasoning. By aligning visual content in a frozen LLM, we encompass visual observation comprehension for LLMs and exploit a way to incorporate LLMs and navigation policy networks for effective action predictions and navigational reasoning. We demonstrate the data efficiency of the proposed methods and eliminate the gap between LM-based agents and state-of-the-art VLN specialists.

Yicong Hong, Yiqun Mei, Chongjian Ge et al.

A truly interactive world model requires three key ingredients: real-time long-horizon streaming, consistent spatial memory, and precise user control. However, most existing approaches address only one of these aspects in isolation, as achieving all three simultaneously is highly challenging-for example, long-term memory mechanisms often degrade real-time performance. In this work, we present RELIC, a unified framework that tackles these three challenges altogether. Given a single image and a text description, RELIC enables memory-aware, long-duration exploration of arbitrary scenes in real time. Built upon recent autoregressive video-diffusion distillation techniques, our model represents long-horizon memory using highly compressed historical latent tokens encoded with both relative actions and absolute camera poses within the KV cache. This compact, camera-aware memory structure supports implicit 3D-consistent content retrieval and enforces long-term coherence with minimal computational overhead. In parallel, we fine-tune a bidirectional teacher video model to generate sequences beyond its original 5-second training horizon, and transform it into a causal student generator using a new memory-efficient self-forcing paradigm that enables full-context distillation over long-duration teacher as well as long student self-rollouts. Implemented as a 14B-parameter model and trained on a curated Unreal Engine-rendered dataset, RELIC achieves real-time generation at 16 FPS while demonstrating more accurate action following, more stable long-horizon streaming, and more robust spatial-memory retrieval compared with prior work. These capabilities establish RELIC as a strong foundation for the next generation of interactive world modeling.

Jisu Nam, Yicong Hong, Chun-Hao Paul Huang et al.

Recent advances in video diffusion transformers have enabled interactive gaming world models that allow users to explore generated environments over extended horizons. However, existing approaches struggle with precise action control and long-horizon 3D consistency. Most prior works treat user actions as abstract conditioning signals, overlooking the fundamental geometric coupling between actions and the 3D world, whereby actions induce relative camera motions that accumulate into a global camera pose within a 3D world. In this paper, we establish camera pose as a unifying geometric representation to jointly ground immediate action control and long-term 3D consistency. First, we define a physics-based continuous action space and represent user inputs in the Lie algebra to derive precise 6-DoF camera poses, which are injected into the generative model via a camera embedder to ensure accurate action alignment. Second, we use global camera poses as spatial indices to retrieve relevant past observations, enabling geometrically consistent revisiting of locations during long-horizon navigation. To support this research, we introduce a large-scale dataset comprising 3,000 minutes of authentic human gameplay annotated with camera trajectories and textual descriptions. Extensive experiments show that our approach substantially outperforms state-of-the-art interactive gaming world models in action controllability, long-horizon visual quality, and 3D spatial consistency.

Gonzalo Gomez-Nogales, Yicong Hong, Chongjian Ge et al.

Traditional rendering pipelines rely on complex assets, accurate materials and lighting, and substantial computational resources to produce realistic imagery, yet they still face challenges in scalability and realism for populated dynamic scenes. We present C2R (Coarse-to-Real), a generative rendering framework that synthesizes real-style urban crowd videos from coarse 3D simulations. Our approach uses coarse 3D renderings to explicitly control scene layout, camera motion, and human trajectories, while a learned neural renderer generates realistic appearance, lighting, and fine-scale dynamics guided by text prompts. To overcome the lack of paired training data between coarse simulations and real videos, we adopt a two-phase mixed CG-real training strategy that learns a strong generative prior from large-scale real footage and introduces controllability through shared implicit spatio-temporal features across domains. The resulting system supports coarse-to-fine control, generalizes across diverse CG and game inputs, and produces temporally consistent, controllable, and realistic urban scene videos from minimal 3D input. We will release the model and project webpage at https://gonzalognogales.github.io/coarse2real/.

Jiazhao Zhang, Kunyu Wang, Rongtao Xu et al.

Vision-and-language navigation (VLN) stands as a key research problem of Embodied AI, aiming at enabling agents to navigate in unseen environments following linguistic instructions. In this field, generalization is a long-standing challenge, either to out-of-distribution scenes or from Sim to Real. In this paper, we propose NaVid, a video-based large vision language model (VLM), to mitigate such a generalization gap. NaVid makes the first endeavor to showcase the capability of VLMs to achieve state-of-the-art level navigation performance without any maps, odometers, or depth inputs. Following human instruction, NaVid only requires an on-the-fly video stream from a monocular RGB camera equipped on the robot to output the next-step action. Our formulation mimics how humans navigate and naturally gets rid of the problems introduced by odometer noises, and the Sim2Real gaps from map or depth inputs. Moreover, our video-based approach can effectively encode the historical observations of robots as spatio-temporal contexts for decision making and instruction following. We train NaVid with 510k navigation samples collected from continuous environments, including action-planning and instruction-reasoning samples, along with 763k large-scale web data. Extensive experiments show that NaVid achieves state-of-the-art performance in simulation environments and the real world, demonstrating superior cross-dataset and Sim2Real transfer. We thus believe our proposed VLM approach plans the next step for not only the navigation agents but also this research field.

Yuankai Qi, Zizheng Pan, Yicong Hong et al.

Vision-and-Language Navigation (VLN) requires an agent to find a path to a remote location on the basis of natural-language instructions and a set of photo-realistic panoramas. Most existing methods take the words in the instructions and the discrete views of each panorama as the minimal unit of encoding. However, this requires a model to match different nouns (e.g., TV, table) against the same input view feature. In this work, we propose an object-informed sequential BERT to encode visual perceptions and linguistic instructions at the same fine-grained level, namely objects and words. Our sequential BERT also enables the visual-textual clues to be interpreted in light of the temporal context, which is crucial to multi-round VLN tasks. Additionally, we enable the model to identify the relative direction (e.g., left/right/front/back) of each navigable location and the room type (e.g., bedroom, kitchen) of its current and final navigation goal, as such information is widely mentioned in instructions implying the desired next and final locations. We thus enable the model to know-where the objects lie in the images, and to know-where they stand in the scene. Extensive experiments demonstrate the effectiveness compared against several state-of-the-art methods on three indoor VLN tasks: REVERIE, NDH, and R2R. Project repository: https://github.com/YuankaiQi/ORIST

Yicong Hong, Cristian Rodriguez-Opazo, Yuankai Qi et al.

Vision-and-Language Navigation (VLN) requires an agent to navigate in a real-world environment following natural language instructions. From both the textual and visual perspectives, we find that the relationships among the scene, its objects,and directional clues are essential for the agent to interpret complex instructions and correctly perceive the environment. To capture and utilize the relationships, we propose a novel Language and Visual Entity Relationship Graph for modelling the inter-modal relationships between text and vision, and the intra-modal relationships among visual entities. We propose a message passing algorithm for propagating information between language elements and visual entities in the graph, which we then combine to determine the next action to take. Experiments show that by taking advantage of the relationships we are able to improve over state-of-the-art. On the Room-to-Room (R2R) benchmark, our method achieves the new best performance on the test unseen split with success rate weighted by path length (SPL) of 52%. On the Room-for-Room (R4R) dataset, our method significantly improves the previous best from 13% to 34% on the success weighted by normalized dynamic time warping (SDTW). Code is available at: https://github.com/YicongHong/Entity-Graph-VLN.

Yicong Hong, Cristian Rodriguez-Opazo, Qi Wu et al.

Vision-and-language navigation requires an agent to navigate through a real 3D environment following natural language instructions. Despite significant advances, few previous works are able to fully utilize the strong correspondence between the visual and textual sequences. Meanwhile, due to the lack of intermediate supervision, the agent's performance at following each part of the instruction cannot be assessed during navigation. In this work, we focus on the granularity of the visual and language sequences as well as the traceability of agents through the completion of an instruction. We provide agents with fine-grained annotations during training and find that they are able to follow the instruction better and have a higher chance of reaching the target at test time. We enrich the benchmark dataset Room-to-Room (R2R) with sub-instructions and their corresponding paths. To make use of this data, we propose effective sub-instruction attention and shifting modules that select and attend to a single sub-instruction at each time-step. We implement our sub-instruction modules in four state-of-the-art agents, compare with their baseline models, and show that our proposed method improves the performance of all four agents. We release the Fine-Grained R2R dataset (FGR2R) and the code at https://github.com/YicongHong/Fine-Grained-R2R.

Chen Ziwen, Hao Tan, Kai Zhang et al.

We propose Long-LRM, a feed-forward 3D Gaussian reconstruction model for instant, high-resolution, 360° wide-coverage, scene-level reconstruction. Specifically, it takes in 32 input images at a resolution of 960x540 and produces the Gaussian reconstruction in just 1 second on a single A100 GPU. To handle the long sequence of 250K tokens brought by the large input size, Long-LRM features a mixture of the recent Mamba2 blocks and the classical transformer blocks, enhanced by a light-weight token merging module and Gaussian pruning steps that balance between quality and efficiency. We evaluate Long-LRM on the large-scale DL3DV benchmark and Tanks&Temples, demonstrating reconstruction quality comparable to the optimization-based methods while achieving an 800x speedup w.r.t. the optimization-based approaches and an input size at least 60x larger than the previous feed-forward approaches. We conduct extensive ablation studies on our model design choices for both rendering quality and computation efficiency. We also explore Long-LRM's compatibility with other Gaussian variants such as 2D GS, which enhances Long-LRM's ability in geometry reconstruction. Project page: https://arthurhero.github.io/projects/llrm

Tianyuan Zhang, Sai Bi, Yicong Hong et al.

Test-Time Training (TTT) models context dependencies by adapting part of the model's weights (referred to as fast weights) during inference. This fast weight, akin to recurrent states in RNNs, stores temporary memories of past tokens in the current sequence. Existing TTT methods struggled to show effectiveness in handling long-context data, due to their inefficiency on modern GPUs. The TTT layers in many of these approaches operate with extremely low FLOPs utilization (often <5%) because they deliberately apply small online minibatch sizes (e.g., updating fast weights every 16 or 64 tokens). Moreover, a small minibatch implies fine-grained block-wise causal dependencies in the data, unsuitable for data beyond 1D ordered sequences, like sets or N-dimensional grids such as images or videos. In contrast, we pursue the opposite direction by using an extremely large chunk update, ranging from 2K to 1M tokens across tasks of varying modalities, which we refer to as Large Chunk Test-Time Training (LaCT). It improves hardware utilization by orders of magnitude, and more importantly, facilitates scaling of nonlinear state size (up to 40% of model parameters), hence substantially improving state capacity, all without requiring cumbersome and error-prone kernel implementations. It also allows easy integration of sophisticated optimizers, e.g. Muon for online updates. We validate our approach across diverse modalities and tasks, including novel view synthesis with image set, language models, and auto-regressive video diffusion. Our approach can scale up to 14B-parameter AR video diffusion model on sequences up to 56K tokens. In our longest sequence experiment, we perform novel view synthesis with 1 million context length. We hope this work will inspire and accelerate new research in the field of long-context modeling and test-time training. Website: https://tianyuanzhang.com/projects/ttt-done-right

Shoubin Yu, Difan Liu, Ziqiao Ma et al.

Recent video diffusion models have enhanced video editing, but it remains challenging to handle instructional editing and diverse tasks (e.g., adding, removing, changing) within a unified framework. In this paper, we introduce VEGGIE, a Video Editor with Grounded Generation from Instructions, a simple end-to-end framework that unifies video concept editing, grounding, and reasoning based on diverse user instructions. Specifically, given a video and text query, VEGGIE first utilizes an MLLM to interpret user intentions in instructions and ground them to the video contexts, generating frame-specific grounded task queries for pixel-space responses. A diffusion model then renders these plans and generates edited videos that align with user intent. To support diverse tasks and complex instructions, we employ a curriculum learning strategy: first aligning the MLLM and video diffusion model with large-scale instructional image editing data, followed by end-to-end fine-tuning on high-quality multitask video data. Additionally, we introduce a novel data synthesis pipeline to generate paired instructional video editing data for model training. It transforms static image data into diverse, high-quality video editing samples by leveraging Image-to-Video models to inject dynamics. VEGGIE shows strong performance in instructional video editing with different editing skills, outperforming the best instructional baseline as a versatile model, while other models struggle with multi-tasking. VEGGIE also excels in video object grounding and reasoning segmentation, where other baselines fail. We further reveal how the multiple tasks help each other and highlight promising applications like zero-shot multimodal instructional and in-context video editing.

Zun Wang, Jialu Li, Yicong Hong et al.

Creating high-quality data for training robust language-instructed agents is a long-lasting challenge in embodied AI. In this paper, we introduce a Self-Refining Data Flywheel (SRDF) that generates high-quality and large-scale navigational instruction-trajectory pairs by iteratively refining the data pool through the collaboration between two models, the instruction generator and the navigator, without any human-in-the-loop annotation. Specifically, SRDF starts with using a base generator to create an initial data pool for training a base navigator, followed by applying the trained navigator to filter the data pool. This leads to higher-fidelity data to train a better generator, which can, in turn, produce higher-quality data for training the next-round navigator. Such a flywheel establishes a data self-refining process, yielding a continuously improved and highly effective dataset for large-scale language-guided navigation learning. Our experiments demonstrate that after several flywheel rounds, the navigator elevates the performance boundary from 70% to 78% SPL on the classic R2R test set, surpassing human performance (76%) for the first time. Meanwhile, this process results in a superior generator, evidenced by a SPICE increase from 23.5 to 26.2, better than all previous VLN instruction generation methods. Finally, we demonstrate the scalability of our method through increasing environment and instruction diversity, and the generalization ability of our pre-trained navigator across various downstream navigation tasks, surpassing state-of-the-art methods by a large margin in all cases.

Gengze Zhou, Yicong Hong, Zun Wang et al.

The academic field of learning instruction-guided visual navigation can be generally categorized into high-level category-specific search and low-level language-guided navigation, depending on the granularity of language instruction, in which the former emphasizes the exploration process, while the latter concentrates on following detailed textual commands. Despite the differing focuses of these tasks, the underlying requirements of interpreting instructions, comprehending the surroundings, and inferring action decisions remain consistent. This paper consolidates diverse navigation tasks into a unified and generic framework -- we investigate the core difficulties of sharing general knowledge and exploiting task-specific capabilities in learning navigation and propose a novel State-Adaptive Mixture of Experts (SAME) model that effectively enables an agent to infer decisions based on different-granularity language and dynamic observations. Powered by SAME, we present a versatile agent capable of addressing seven navigation tasks simultaneously that outperforms or achieves highly comparable performance to task-specific agents.

Yuan Yao, Yicong Hong, Difan Liu et al.

The quadratic computational complexity of self-attention in diffusion transformers (DiT) introduces substantial computational costs in high-resolution image generation. While the linear-complexity Mamba model emerges as a potential alternative, direct Mamba training remains empirically challenging. To address this issue, this paper introduces diffusion transformer-to-mamba distillation (T2MD), forming an efficient training pipeline that facilitates the transition from the self-attention-based transformer to the linear complexity state-space model Mamba. We establish a diffusion self-attention and Mamba hybrid model that simultaneously achieves efficiency and global dependencies. With the proposed layer-level teacher forcing and feature-based knowledge distillation, T2MD alleviates the training difficulty and high cost of a state space model from scratch. Starting from the distilled 512$\times$512 resolution base model, we push the generation towards 2048$\times$2048 images via lightweight adaptation and high-resolution fine-tuning. Experiments demonstrate that our training path leads to low overhead but high-quality text-to-image generation. Importantly, our results also justify the feasibility of using sequential and causal Mamba models for generating non-causal visual output, suggesting the potential for future exploration.

Yitian Zhang, Long Mai, Aniruddha Mahapatra et al.

We present a novel perspective on learning video embedders for generative modeling: rather than requiring an exact reproduction of an input video, an effective embedder should focus on synthesizing visually plausible reconstructions. This relaxed criterion enables substantial improvements in compression ratios without compromising the quality of downstream generative models. Specifically, we propose replacing the conventional encoder-decoder video embedder with an encoder-generator framework that employs a diffusion transformer (DiT) to synthesize missing details from a compact latent space. Therein, we develop a dedicated latent conditioning module to condition the DiT decoder on the encoded video latent embedding. Our experiments demonstrate that our approach enables superior encoding-decoding performance compared to state-of-the-art methods, particularly as the compression ratio increases. To demonstrate the efficacy of our approach, we report results from our video embedders achieving a temporal compression ratio of up to 32x (8x higher than leading video embedders) and validate the robustness of this ultra-compact latent space for text-to-video generation, providing a significant efficiency boost in latent diffusion model training and inference.

Yicong Hong, Long Mai, Yuan Yao et al.

While Transformers have become the dominant architecture for visual generation, linear attention models, such as the state-space models (SSM), are increasingly recognized for their efficiency in processing long visual sequences. However, the essential efficiency of these models comes from formulating a limited recurrent state, enforcing causality among tokens that are prone to inconsistent modeling of N-dimensional visual data, leaving questions on their capacity to generate long non-causal sequences. In this paper, we explore the boundary of SSM on image and video generation by building the largest-scale diffusion SSM-Transformer hybrid model to date (5B parameters) based on the sub-quadratic bi-directional Hydra and self-attention, and generate up to 2K images and 360p 8 seconds (16 FPS) videos. Our results demonstrate that the model can produce faithful results aligned with complex text prompts and temporal consistent videos with high dynamics, suggesting the great potential of using SSMs for visual generation tasks.

Bahram Mohammadi, Yicong Hong, Yuankai Qi et al.

The vision-and-language navigation (VLN) task necessitates an agent to perceive the surroundings, follow natural language instructions, and act in photo-realistic unseen environments. Most of the existing methods employ the entire image or object features to represent navigable viewpoints. However, these representations are insufficient for proper action prediction, especially for the REVERIE task, which uses concise high-level instructions, such as ''Bring me the blue cushion in the master bedroom''. To address enhancing representation, we propose an augmented commonsense knowledge model (ACK) to leverage commonsense information as a spatio-temporal knowledge graph for improving agent navigation. Specifically, the proposed approach involves constructing a knowledge base by retrieving commonsense information from ConceptNet, followed by a refinement module to remove noisy and irrelevant knowledge. We further present ACK which consists of knowledge graph-aware cross-modal and concept aggregation modules to enhance visual representation and visual-textual data alignment by integrating visible objects, commonsense knowledge, and concept history, which includes object and knowledge temporal information. Moreover, we add a new pipeline for the commonsense-based decision-making process which leads to more accurate local action prediction. Experimental results demonstrate our proposed model noticeably outperforms the baseline and archives the state-of-the-art on the REVERIE benchmark.

Gengze Zhou, Yicong Hong, Qi Wu

Trained with an unprecedented scale of data, large language models (LLMs) like ChatGPT and GPT-4 exhibit the emergence of significant reasoning abilities from model scaling. Such a trend underscored the potential of training LLMs with unlimited language data, advancing the development of a universal embodied agent. In this work, we introduce the NavGPT, a purely LLM-based instruction-following navigation agent, to reveal the reasoning capability of GPT models in complex embodied scenes by performing zero-shot sequential action prediction for vision-and-language navigation (VLN). At each step, NavGPT takes the textual descriptions of visual observations, navigation history, and future explorable directions as inputs to reason the agent's current status, and makes the decision to approach the target. Through comprehensive experiments, we demonstrate NavGPT can explicitly perform high-level planning for navigation, including decomposing instruction into sub-goal, integrating commonsense knowledge relevant to navigation task resolution, identifying landmarks from observed scenes, tracking navigation progress, and adapting to exceptions with plan adjustment. Furthermore, we show that LLMs is capable of generating high-quality navigational instructions from observations and actions along a path, as well as drawing accurate top-down metric trajectory given the agent's navigation history. Despite the performance of using NavGPT to zero-shot R2R tasks still falling short of trained models, we suggest adapting multi-modality inputs for LLMs to use as visual navigation agents and applying the explicit reasoning of LLMs to benefit learning-based models.

Jiawei Liu, Jing Zhang, Yicong Hong et al.

Compared with expensive pixel-wise annotations, image-level labels make it possible to learn semantic segmentation in a weakly-supervised manner. Within this pipeline, the class activation map (CAM) is obtained and further processed to serve as a pseudo label to train the semantic segmentation model in a fully-supervised manner. In this paper, we argue that the lost structure information in CAM limits its application in downstream semantic segmentation, leading to deteriorated predictions. Furthermore, the inconsistent class activation scores inside the same object contradicts the common sense that each region of the same object should belong to the same semantic category. To produce sharp prediction with structure information, we introduce an auxiliary semantic boundary detection module, which penalizes the deteriorated predictions. Furthermore, we adopt smoothness loss to encourage prediction inside the object to be consistent. Experimental results on the PASCAL-VOC dataset illustrate the effectiveness of the proposed solution.

Yicong Hong, Qi Wu, Yuankai Qi et al.

Accuracy of many visiolinguistic tasks has benefited significantly from the application of vision-and-language(V&L) BERT. However, its application for the task of vision-and-language navigation (VLN) remains limited. One reason for this is the difficulty adapting the BERT architecture to the partially observable Markov decision process present in VLN, requiring history-dependent attention and decision making. In this paper we propose a recurrent BERT model that is time-aware for use in VLN. Specifically, we equip the BERT model with a recurrent function that maintains cross-modal state information for the agent. Through extensive experiments on R2R and REVERIE we demonstrate that our model can replace more complex encoder-decoder models to achieve state-of-the-art results. Moreover, our approach can be generalised to other transformer-based architectures, supports pre-training, and is capable of solving navigation and referring expression tasks simultaneously.