Medical decision-making often involves integrating knowledge from multiple clinical specialties, typically achieved through multidisciplinary teams.Inspired by this collaborative process, recent work has leveraged large language models (LLMs) in multi-agent collaboration frameworks to emulate expert teamwork.While these approaches improve reasoning through agent interaction, they are limited by static, pre-assigned roles, which hinder adaptability and dynamic knowledge integration.To address these limitations, we propose KAMAC, a Knowledge-driven Adaptive Multi-Agent Collaboration framework that enables LLM agents to dynamically form and expand expert teams based on the evolving diagnostic context.KAMAC begins with one or more expert agents and then conducts a knowledge-driven discussion to identify and fill knowledge gaps by recruiting additional specialists as needed.This supports flexible, scalable collaboration in complex clinical scenarios, with decisions finalized through reviewing updated agent comments.Experiments on two real-world medical benchmarks demonstrate that KAMAC significantly outperforms both single-agent and advanced multi-agent methods, particularly in complex clinical scenarios (i.e., cancer prognosis) requiring dynamic, cross-specialty expertise.

Integrating large language models (LLMs) into embodied AI models is becoming increasingly prevalent.However, existing zero-shot LLMbased Vision-and-Language Navigation (VLN) agents either encode images as textual scene descriptions, potentially oversimplifying visual details, or process raw image inputs, which can fail to capture abstract semantics required for high-level reasoning.In this paper, we improve the navigation agent's contextual understanding by incorporating textual descriptions from multiple perspectives that facilitate analogical reasoning across images.By leveraging textbased analogical reasoning, the agent enhances its global scene understanding and spatial reasoning, leading to more accurate action decisions.We evaluate our approach on the R2R dataset, where our experiments demonstrate significant improvements in navigation performance.

Vision-and-Language Navigation (VLN) tasks have gained prominence within artificial intelligence research due to their potential application in fields like home assistants. Many contemporary VLN approaches, while based on transformer architectures, have increasingly incorporated additional components such as external knowledge bases or map information to enhance performance. These additions, while boosting performance, also lead to larger models and increased computational costs. In this paper, to achieve both high performance and low computational costs, we propose a novel architecture with the COmbination of Selective MemOrization (COSMO). Specifically, COSMO integrates state-space modules and transformer modules, and incorporates two VLN-customized selective state space modules: the Round Selective Scan (RSS) and the Cross-modal Selective State Space Module (CS3). RSS facilitates comprehensive inter-modal interactions within a single scan, while the CS3 module adapts the selective state space module into a dual-stream architecture, thereby enhancing the acquisition of cross-modal interactions. Experimental validations on three mainstream VLN benchmarks, REVERIE, R2R, and R2R-CE, not only demonstrate competitive navigation performance of our model but also show a significant reduction in computational costs.

Vision-and-Language Navigation (VLN) tasks mainly evaluate agents based on one-time execution of individual instructions across multiple environments, aiming to develop agents capable of functioning in any environment in a zero-shot manner. However, real-world navigation robots often operate in persistent environments with relatively consistent physical layouts, visual observations, and language styles from instructors. Such a gap in the task setting presents an opportunity to improve VLN agents by incorporating continuous adaptation to specific environments. To better reflect these real-world conditions, we introduce GSA-VLN (General Scene Adaptation for VLN), a novel task requiring agents to execute navigation instructions within a specific scene and simultaneously adapt to it for improved performance over time. To evaluate the proposed task, one has to address two challenges in existing VLN datasets: the lack of out-of-distribution (OOD) data, and the limited number and style diversity of instructions for each scene. Therefore, we propose a new dataset, GSA-R2R, which significantly expands the diversity and quantity of environments and instructions for the Room-to-Room (R2R) dataset to evaluate agent adaptability in both ID and OOD contexts. Furthermore, we design a three-stage instruction orchestration pipeline that leverages large language models (LLMs) to refine speaker-generated instructions and apply role-playing techniques to rephrase instructions into different speaking styles. This is motivated by the observation that each individual user often has consistent signatures or preferences in their instructions, taking the use case of home robotic assistants as an example. We conducted extensive experiments on GSA-R2R to thoroughly evaluate our dataset and benchmark various methods, revealing key factors enabling agents to adapt to specific environments. Based on our findings, we propose a novel method, Graph-Retained DUET (GR-DUET), which incorporates memory-based navigation graphs with an environment-specific training strategy, achieving state-of-the-art results on all GSA-R2R splits.

Vision-and-Language Navigation (VLN) empowers agents to associate time-sequenced visual observations with corresponding instructions to make sequential decisions. However, dealing with visually diverse scenes or transitioning from simulated environments to real-world deployment is still challenging. In this paper, we address the mismatch between human-centric instructions and quadruped robots with a lowheight field of view, proposing a Ground-level Viewpoint Navigation (GVNav) approach to mitigate this issue. This work represents the first attempt to highlight the generalization gap in VLN across varying heights of visual observation in realistic robot deployments. Our approach leverages weighted historical observations as enriched spatiotemporal contexts for instruction following, effectively managing feature collisions within cells by assigning appropriate weights to identical features across different viewpoints. This enables low-height robots to overcome challenges such as visual obstructions and perceptual mismatches. Additionally, we transfer the connectivity graph from the HM3D and Gibson datasets as an extra resource to enhance spatial priors and a more comprehensive representation of real-world scenarios, leading to improved performance and generalizability of the waypoint predictor in real-world environments. Extensive experiments demonstrate that our Groundlevel Viewpoint Navigation (GVnav) approach significantly improves performance in both simulated environments and real-world deployments with quadruped robots.

Vision-and-Language Navigation (VLN) tasks require an agent to follow textual instructions to navigate through 3D environments. Traditional approaches use supervised learning methods, relying heavily on domain-specific datasets to train VLN models. Recent methods try to utilize closedsource large language models (LLMs) like GPT-4 to solve VLN tasks in zero-shot manners, but face challenges related to expensive token costs and potential data breaches in realworld applications. In this work, we introduce Open-Nav, a novel study that explores open-source LLMs for zero-shot VLN in the continuous environment. Open-Nav employs a spatial-temporal chain-of-thought (CoT) reasoning approach to break down tasks into instruction comprehension, progress estimation, and decision-making. It enhances scene perceptions with fine-grained object and spatial knowledge to improve LLM's reasoning in navigation. Our extensive experiments in both simulated and real-world environments demonstrate that Open-Nav achieves competitive performance compared to using closed-source LLMs.

Generalist robot manipulation policies (GMPs) have the potential to generalize across a wide range of tasks, devices, and environments. However, existing policies continue to struggle with out-of-distribution scenarios due to the inherent difficulty of collecting sufficient action data to cover extensively diverse domains. While fine-tuning offers a practical way to quickly adapt a GMPs to novel domains and tasks with limited samples, we observe that the performance of the resulting GMPs differs significantly with respect to the design choices of fine-tuning strategies. In this work, we first conduct an indepth empirical study to investigate the effect of key factors in GMPs fine-tuning strategies, covering the action space, policy head, supervision signal and the choice of tunable parameters, where 2,500 rollouts are evaluated for a single configuration. We systematically discuss and summarize our findings and identify the key design choices, which we believe give a practical guideline for GMPs fine-tuning. We observe that in a lowdata regime, with carefully chosen fine-tuning strategies, a GMPs significantly outperforms the state-of-the-art imitation learning algorithms. The results presented in this work establish a new baseline for future studies on fine-tuned GMPs.

In recent years, Embodied Artificial Intelligence (Embodied AI) has advanced rapidly, yet the increasing size of models conflicts with the limited computational capabilities of Embodied AI platforms. To address this challenge, we aim to achieve both high model performance and practical deployability. Specifically, we focus on Vision-and-Language Navigation (VLN), a core task in Embodied AI. This paper introduces a two-stage knowledge distillation framework, producing a student model, MiniVLN, and showcasing the significant potential of distillation techniques in developing lightweight models. The proposed method aims to capture fine-grained knowledge during the pretraining phase and navigation-specific knowledge during the fine-tuning phase. Our findings indicate that the two-stage distillation approach is more effective in narrowing the performance gap between the teacher model and the student model compared to single-stage distillation. On the public R2R and REVERIE benchmarks, MiniVLN achieves performance on par with the teacher model while having only about 12 % of the teacher model's parameter count.

Vision-and-Language Navigation (VLN) in continuous environments requires agents to interpret natural language instructions while navigating unconstrained 3D spaces. Existing VLN-CE frameworks rely on a two-stage approach: a waypoint predictor to generate waypoints and a navigator to execute movements. However, current waypoint predictors struggle with spatial awareness, while navigators lack historical reasoning and backtracking capabilities, limiting adaptability. We propose a zero-shot VLN-CE framework integrating an enhanced waypoint predictor with a Multi-modal Large Language Model (MLLM)-based navigator. Our predictor employs a stronger vision encoder, masked cross-attention fusion, and an occupancy-aware loss for better waypoint quality. The navigator incorporates history-aware reasoning and adaptive path planning with backtracking, improving robustness. Experiments on R2R-CE and MP3D benchmarks show our method achieves state-of-the-art (SOTA) performance in zero-shot settings, demonstrating competitive results compared to fully supervised methods. Real-world validation on Turtlebot 4 further highlights its adaptability.

Mobile robots rely on object detectors for perception and object localization in indoor environments. However, standard closed-set methods struggle to handle the diverse objects and dynamic conditions encountered in real homes and labs. Open-vocabulary object detection (OVOD), driven by Vision Language Models (VLMs), extends beyond fixed labels but still struggles with domain shifts in indoor environments. We introduce a Source-Free Domain Adaptation (SFDA) approach that adapts a pre-trained model without accessing source data. We refine pseudo labels via temporal clustering, employ multi-scale threshold fusion, and apply a Mean Teacher framework with contrastive learning. Our Embodied Domain Adaptation for Object Detection (EDAOD) benchmark evaluates adaptation under sequential changes in lighting, layout, and object diversity. Our experiments show significant gains in zero-shot detection performance and flexible adaptation to dynamic indoor conditions.

Multimodal Large Language Models (MLLMs) have demonstrated strong generalization in vision-language tasks, yet their ability to understand and act within embodied environments remains underexplored. We present NavBench, a benchmark to evaluate the embodied navigation capabilities of MLLMs under zero-shot settings. NavBench consists of two components: (1) navigation comprehension, assessed through three cognitively grounded tasks including global instruction alignment, temporal progress estimation, and local observation-action reasoning, covering 3,200 question-answer pairs; and (2) step-by-step execution in 432 episodes across 72 indoor scenes, stratified by spatial, cognitive, and execution complexity. To support real-world deployment, we introduce a pipeline that converts MLLMs' outputs into robotic actions. We evaluate both proprietary and open-source models, finding that GPT-4o performs well across tasks, while lighter open-source models succeed in simpler cases. Results also show that models with higher comprehension scores tend to achieve better execution performance. Providing map-based context improves decision accuracy, especially in medium-difficulty scenarios. However, most models struggle with temporal understanding, particularly in estimating progress during navigation, which may pose a key challenge.

We present Chain-of-Action (CoA), a novel visuomotor policy paradigm built upon Trajectory Autoregressive Modeling. Unlike conventional approaches that predict next step action(s) forward, CoA generates an entire trajectory by explicit backward reasoning with task-specific goals through an action-level Chain-of-Thought (CoT) process. This process is unified within a single autoregressive structure: (1) the first token corresponds to a stable keyframe action that encodes the task-specific goals; and (2) subsequent action tokens are generated autoregressively, conditioned on the initial keyframe and previously predicted actions. This backward action reasoning enforces a global-to-local structure, allowing each local action to be tightly constrained by the final goal. To further realize the action reasoning structure, CoA incorporates four complementary designs: continuous action token representation; dynamic stopping for variable-length trajectory generation; reverse temporal ensemble; and multi-token prediction to balance action chunk modeling with global structure. As a result, CoA gives strong spatial generalization capabilities while preserving the flexibility and simplicity of a visuomotor policy. Empirically, we observe that CoA outperforms representative imitation learning algorithms such as ACT and Diffusion Policy across 60 RLBench tasks and 8 real-world tasks.

Goal-Oriented Vision-and-Language Navigation (VLN) aims to enable agents to navigate to specified locations and identify designated target objects following natural language instruction. This approach has gained popularity due to its close alignment with real-world scenarios. However, existing studies have predominantly focused on enhancing navigation performance, neglecting the ability to locate objects at the navigation endpoint. This oversight has resulted in a significant discrepancy between the success rates of navigation and object grounding. The challenge is compounded by the complex reasoning required by the instructions and the necessity to synthesize multiperspective images of objects, which overwhelms traditional object grounding methods. We leverage the Multi-Modal Large Language Model (MLLM) to bridge this gap, allowing agents to seek assistance from these models when struggling to locate the target object. The agent conducts a multi-stage evaluation to discern the cause of its confusion and promptly extracts and updates the most relevant information for MLLM to assess. Our method is plug-and-play and model-agnostic, facilitating integration with numerous existing VLN strategies without the need for retraining. Implementing our approach across four distinct methods has improved performance on the REVERIE and SOON datasets, demonstrating the effectiveness and generalizability of our technique.

Sounding Video Generation (SVG) is an audio-video joint generation task challenged by high-dimensional signal spaces, distinct data formats, and different patterns of content information. To address these issues, we introduce a novel multi-modal latent diffusion model (MM-LDM) for the SVG task. We first unify the representation of audio and video data by converting them into a single or a couple of images. Then, we introduce a hierarchical multi-modal autoencoder that constructs a low-level perceptual latent space for each modality and a shared high-level semantic feature space. The former space is perceptually equivalent to the raw signal space of each modality but drastically reduces signal dimensions. The latter space serves to bridge the information gap between modalities and provides more insightful cross-modal guidance. Our proposed method achieves new state-of-the-art results with significant quality and efficiency gains. Specifically, our method achieves a comprehensive improvement on all evaluation metrics and a faster training and sampling speed on Landscape and AIST++ datasets. Moreover, we explore its performance on open-domain sounding video generation, long sounding video generation, audio continuation, video continuation, and conditional single-modal generation tasks for a comprehensive evaluation, where our MM-LDM demonstrates exciting adaptability and generalization ability.

Many Vision-and-Language Navigation (VLN) tasks have been proposed in recent years, from room-based to object-based and indoor to outdoor. The REVERIE (Remote Embodied Referring Expression) is interesting since it only provides high-level instructions to the agent, which are closer to human commands in practice. Nevertheless, this poses more challenges than other VLN tasks since it requires agents to infer a navigation plan only based on a short instruction. Large Language Models (LLMs) show great potential in robot action planning by providing proper prompts. Still, this strategy has not been explored under the REVERIE settings. There are several new challenges. For example, the LLM should be environment-aware so that the navigation plan can be adjusted based on the current visual observation. Moreover, the LLM planned actions should be adaptable to the much larger and more complex REVERIE environment. This paper proposes a March-in-Chat (MiC) model that can talk to the LLM on the fly and plan dynamically based on a newly proposed Room-and-Object Aware Scene Perceiver (ROASP). Our MiC model outperforms the previous state-of-the-art by large margins by SPL and RGSPL metrics on the REVERIE benchmark. The source code is available at https://github.com/YanyuanQiao/MiC

The performance of the Vision-and-Language Navigation (VLN) tasks has witnessed rapid progress recently thanks to the use of large pre-trained vision-and-language models. However, full fine-tuning the pre-trained model for every downstream VLN task is becoming costly due to the considerable model size. Recent research hotspot of Parameter-Efficient Transfer Learning (PETL) shows great potential in efficiently tuning large pre-trained models for the common CV and NLP tasks, which exploits the most of the representation knowledge implied in the pre-trained model while only tunes a minimal set of parameters. However, simply utilizing existing PETL methods for the more challenging VLN tasks may bring non-trivial degeneration to the performance. Therefore, we present the first study to explore PETL methods for VLN tasks and propose a VLN-specific PETL method named VLN-PETL. Specifically, we design two PETL modules: Historical Interaction Booster (HIB) and Cross-modal Interaction Booster (CIB). Then we combine these two modules with several existing PETL methods as the integrated VLN-PETL. Extensive experimental results on four mainstream VLN tasks (R2R, REVERIE, NDH, RxR) demonstrate the effectiveness of our proposed VLN-PETL, where VLN-PETL achieves comparable or even better performance to full fine-tuning and outperforms other PETL methods with promising margins. The source code is available at https://github.com/YanyuanQiao/VLN-PETL

Recent works attempt to employ pre-training in Vision-and-Language Navigation (VLN). However, these methods neglect the importance of historical contexts or ignore predicting future actions during pre-training, limiting the learning of visual-textual correspondence and the capability of decision-making. To address these problems, we present a history-enhanced and order-aware pre-training with the complementing fine-tuning paradigm (HOP+) for VLN. Specifically, besides the common Masked Language Modeling (MLM) and Trajectory-Instruction Matching (TIM) tasks, we design three novel VLN-specific proxy tasks: Action Prediction with History (APH) task, Trajectory Order Modeling (TOM) task and Group Order Modeling (GOM) task. APH task takes into account the visual perception trajectory to enhance the learning of historical knowledge as well as action prediction. The two temporal visual-textual alignment tasks, TOM and GOM further improve the agent's ability to order reasoning. Moreover, we design a memory network to address the representation inconsistency of history context between the pre-training and the fine-tuning stages. The memory network effectively selects and summarizes historical information for action prediction during fine-tuning, without costing huge extra computation consumption for downstream VLN tasks. HOP+ achieves new state-of-the-art performance on four downstream VLN tasks (R2R, REVERIE, RxR, and NDH), which demonstrates the effectiveness of our proposed method.

Pretraining has been adopted in a few of recent works for Vision-and-Language Navigation (VLN). However, pre-vious 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 intro-ducing 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.

Despite recent significant progress on generative models, context-rich text-to-image synthesis depicting multiple complex objects is still non-trivial. The main challenges lie in the ambiguous semantic of a complex description and the intricate scene of an image with various objects, different positional relationship and diverse appearances. To address these challenges, we propose R-GAN, which can generate reasonable images according to the given text in a human-like way. Specifically, just like humans will first find and settle the essential elements to create a simple sketch, we first capture a monolithic-structural text representation by building a scene graph to find the essential semantic elements. Then, based on this representation, we design a bounding box generator to estimate the layout with position and size of target objects, and a following shape generator, which draws a fine-detailed shape for each object. Different from previous work only generating coarse shapes blindly, we introduce a coarse-to-fine shape generator based on a shape knowledge base. At last, to finish the final image synthesis, we propose a multi-modal geometry-aware spatially-adaptive generator conditioned on the monolithic-structural text representation and the geometry-aware map of the shapes. Extensive experiments on the real-world dataset MSCOCO show the superiority of our method in terms of both quantitative and qualitative metrics.

Referring expression comprehension (REC) aims to localize a target object in an image described by a referring expression phrased in natural language. Different from the object detection task that queried object labels have been pre-defined, the REC problem only can observe the queries during the test. It is more challenging than a conventional computer vision problem. This task has attracted a lot of attention from both computer vision and natural language processing community, and several lines of work have been proposed, from CNN-RNN model, modular network to complex graph-based model. In this survey, we first examine the state-of-the-art by comparing modern approaches to the problem. We classify methods by their mechanism to encode the visual and textual modalities. In particular, we examine the common approach of joint embedding images and expressions to a common feature space. We also discuss modular architectures and graph-based models that interface with structured graph representation. In the second part of this survey, we review the datasets available for training and evaluating REC approaches. We then group results according to the datasets, backbone models, settings so that they can be fairly compared. Finally, we discuss promising future directions for this field, in particular the compositional referring expression comprehension that requires more reasoning steps to address.

Visual Question Answering (VQA) is a comprehensive task to answer questions about the visual contents of an image. Recently, a number of studies have pointed out that VQA models tend to be misled by the dataset biases, and rely heavily on the superficial correlations between question and answer, rather than really understanding the visual contents. To address this issue, we propose visual calibration mechanism for VQA(VC-VQA) which extends the conventional VQA model with an additional image feature reconstruction module. The proposed model reconstructs image features based on predicted answer with question and measures the similarity between reconstructed image feature and original image feature, which will guide the VQA model predict the final answer. We evaluate our model on both VQA v1 and VQA v2 datasets, showing that VC-VQA effectively reduces impacts of dataset bias and achieves competitive performance compared to other mainstream methods.

Visual Question Answering (VQA) is a comprehensive task to answer questions about the visual contents of an image. However, a number of studies have pointed out that VQA models rely heavily on superficial correlations between question and answer, and predict the answer just according to the textual statistical correlations without truly understanding the visual contents. To address this issue, we propose an answer re-ranking VQA model, called as RankVQA, in which the roles of the input image are re-examined to select the most relevant answer from a set of candidate answers generated by a typical VQA model. Specifically, we rank the candidate answers with their relevance to visual content of the input image and some question-related image captions respectively. Extensive experiments on the two datasets, i.e., VQA v2 and VQACP v2, demonstrate the effectiveness of the proposed model, and the state-of-the-art performance on both the datasets are achieved.

Using dropout in Visual Question Answering (VQA) is a common practice to prevent overfitting. However, in multi-path networks, the current way to use dropout may cause two problems: the co-adaptations of neurons and the explosion of output variance. In this paper, we propose the coherent dropout and the siamese dropouy to solve the two problems, respectively. Specifically, in coherent dropout, all relevant dropout layers in multiple paths are forced to work coherently to maximize the ability of preventing neuron co-adaptations. We show that the coherent dropout is simple in implementation but very effective to overcome overfitting. As for the explosion of output variance, we develop a siamese dropout mechanism to explicitly minimize the difference between the two output vectors produced from the same input data during training phase. Such mechanism can reduce the gap between training and inference phases and make the VQA model more robust. Extensive experiments are conducted to verify the effectiveness of coherent dropout and siamese dropout. And the results also show that our methods can bring additional improvements on the state-of-the-art VQA models.