The rise of pre-trained foundation models (FMs) has popularized the trend of fine-tuning FMs to fit downstream tasks, while Federated Learning (FL) has become the de-facto approach for training distributed data with privacy-preservation. However, fine-tuning FMs in FL faces overwhelming overheads due to its bulky nature. While freezing parameters in FM have the potential to accelerate FL training, existing freezing strategies statically freeze parameters on specified or already converged layers, incur severe accuracy degradation, and resource-inefficiency in heterogeneous environments. In this paper, we propose AFedLF, an adaptive freezing framework for FM in FL, to accelerate its wall-clock time for convergence without losing its final accuracy. However, this poses great challenges, as different freezing strategies lead to different accuracy gains and time overheads, while unfreezing more layers may bring marginal accuracy gains but significant time overheads. To address this challenge, AFedLF mathematically establishes a correlation between the freezing strategy and the accuracy gain and time overhead, and allocates adaptive freezing strategies to clients, based on our insight that unfreezing more layers on devices with strong computation and communication capabilities helps improve resource efficiency. Besides, AFedLF incorporates our well-designed intermediate result caching scheme with constant approximation ratios utilizing the limited storage capacity on mobile devices to cache intermediate results to skip forward propagation, further saving wall-clock time. Finally, we implemented AFedLF using an open-source FL benchmark, and extensive trace-driven experimental results showed that AFedLF accelerates wall-clock time by up to 6.1 & times; compared to state-of-the-art solutions, without sacrificing accuracy.

Foundation model (FM) powered agent services are regarded as a promising solution to develop intelligent and personalized applications for advancing toward Artificial General Intelligence (AGI). To achieve high reliability and scalability in deploying these agent services, it is essential to collaboratively optimize computational and communication resources, thereby ensuring effective resource allocation and seamless service delivery. In pursuit of this vision, this paper proposes a unified framework aimed at providing a comprehensive survey on deploying FM-based agent services across heterogeneous devices, with the emphasis on the integration of model and resource optimization to establish a robust infrastructure for these services. Particularly, this paper begins with exploring various low-level optimization strategies during inference and studies approaches that enhance system scalability, such as parallelism techniques and resource scaling methods. The paper then discusses several prominent FMs and investigates research efforts focused on inference acceleration, including techniques such as model compression and token reduction. Moreover, the paper also investigates critical components for constructing agent services and highlights notable intelligent applications. Finally, the paper presents potential research directions for developing real-time agent services with high Quality of Service (QoS).

Visual Dialogue Navigation (VDN) aims to enable agents to reach target locations through dialogue with humans. The integration of VDN into Unmanned Aerial Vehicle (UAV) systems enhances human-machine interaction by enabling intuitive, hands-free operation, thereby unlocking vast applications. However, existing VDN models for UAVs can only perform navigation based on dialogue history, lacking proactive interaction capabilities to correct trajectories. Moreover, their sequential observation history recording mechanism struggles to accurately localize landmarks observed in the historical context, leading to ineffective utilization of referential information in new user instructions.To address these, we present AerialVLA, an end-to-end UAV navigation framework integrating dialogue comprehension, action decision-making, and navigational question generation. AerialVLA comprises three core components: i) we propose the Progress-Driven Navigation-Query Alternation mechanism to determine optimal questioning timing through navigation progress estimation autonomously. ii) To effectively model long-horizon history observation sequences, we develop the History Spatial-Temporal Fusion module that extracts discriminative spatial-temporal representations from historical observations. iii) Furthermore, to overcome data scarcity in training, we devise the Online Task-Driven Augmentation strategy that enhances learning through action-conditioned data augmentation. Experimental results demonstrate that AerialVLA achieves state-of-the-art navigation performance while exhibiting effective dialogue capabilities.Moreover, to better evaluate the agent's proactive dialogue and navigation abilities, our evaluation benchmark, named UAV Navigation with Online Dialogue (UNOD), incorporates an online dialogue interaction module. The UNOD assesses UAV agents' real-time questioning capabilities by leveraging an Air Commander Large Language Model to simulate human-UAV interactions during testing.

The deployment of large language models' (LLMs) inference at the edge can facilitate prompt service responsiveness while protecting user privacy. However, it is critically challenged by the resource constraints of a single edge node. Distributed inference has emerged to aggregate and leverage computational resources across multiple devices. Yet, existing methods typically require strict synchronization, which is often infeasible due to the unreliable network conditions. In this paper, we propose HALO, a novel framework that can boost the distributed LLM inference in lossy edge network. The core idea is to enable a relaxed yet effective synchronization by strategically allocating less critical neuron groups to unstable devices, thus avoiding the excessive waiting time incurred by delayed packets. HALO introduces three key mechanisms: (1) a semantic-aware predictor to assess the significance of neuron groups prior to activation. (2) a parallel execution scheme of neuron group loading during the model inference. (3) a load-balancing scheduler that efficiently orchestrates multiple devices with heterogeneous resources. Experimental results from a Raspberry Pi cluster demonstrate that HALO achieves a 3.41x end-to-end speedup for LLaMA-series LLMs under unreliable network conditions. It maintains performance comparable to optimal conditions and significantly outperforms the state-of-the-art in various scenarios.

Humans possess an innate ability to infer others’ intentions from ambiguous utterances based on the observation of contextual cues and past actions. Conversely, machines typically necessitate explicit instructions, thereby increasing the temporal cost of human-AI interaction. To mitigate this, we propose the Intuition Estimation and Knowledge-Based Planning (IEKP) method, which augments human-AI collaboration under ambiguous directives. IEKP encompasses three principal components: 1) Associative Reasoning based Goal Recognition (ARGoal) utilizes large language model to form an initial estimation of human goals and refines this estimation through associative mechanisms; 2) Finite State Machine Guided Decision Pruning (FDPrune) constructs state machines based on task types, pruning illegitimate action outputs to enhance the robustness of language models in long-term decision processes; 3) Knowledge-Enhanced Searching System (K-Search) leverages co-occurrence relationships between objects and environments to improve the agent’s efficiency in environmental searches. Our approach markedly enhances performance on the HandMeThat task, increasing the success rate by 65.42

Aerial Vision-and-Language Navigation (VLN) is an emerging task that enables Unmanned Aerial Vehicles (UAVs) to navigate outdoor environments using natural language instructions and visual cues. However, due to the extended trajectories and complex maneuverability of UAVs, achieving reliable UAV-VLN performance is challenging and often requires human intervention or overly detailed instructions. To harness the advantages of UAVs' high mobility, which could provide multi-grained perspectives, while maintaining a manageable motion space for learning, we introduce a novel task called Dual-Altitude UAV Collaborative VLN (DuAl-VLN). In this task, two UAVs operate at distinct altitudes: a high-altitude UAV responsible for broad environmental reasoning, and a low-altitude UAV tasked with precise navigation. To support the training and evaluation of the DuAl-VLN, we construct the HaL-13k, a dataset comprising 13, 838 collaborative high-low UAV demonstration trajectories, each paired with target-oriented language instructions. This dataset includes both unseen maps and an unseen object validation set to systematically evaluate the model's generalization capabilities across novel environments and unfamiliar targets. To consolidate their complementary strengths, we propose a dual-UAV collaborative VLN framework, AeroDuo, where the high-altitude UAV integrates a multimodal large language model (Pilot-LLM) for target reasoning, while the low-altitude UAV employs a lightweight multi-stage policy for navigation and target grounding. The two UAVs work collaboratively and only exchange minimal coordinate information to ensure efficiency. Experimental results indicate that AeroDuo achieves an evident 9.71% improvement in success rates compared to existing single-UAV methods, demonstrating the effectiveness of dual-altitude collaboration in balancing environmental coverage, precision, and operational autonomy.

Unmanned Aerial Vehicles, operating in environments with relatively few obstacles, offer high maneuverability and full three-dimensional mobility. This allows them to rapidly approach objects and perform a wide range of tasks often challenging for ground robots, making them ideal for exploration, inspection, aerial imaging, and everyday assistance. In this paper, we introduce AirStar, a UAV-centric embodied platform that turns a UAV into an intelligent aerial assistant: a large language model acts as the cognitive core for environmental understanding, contextual reasoning, and task planning. AirStar accepts natural interaction through voice commands and gestures, removing the need for a remote controller and significantly broadening its user base. It combines geospatial knowledge-driven long-distance navigation with contextual reasoning for fine-grained short-range control, resulting in an efficient and accurate vision-and-language navigation (VLN) capability. Furthermore, the system also offers built-in capabilities such as cross-modal question answering, intelligent filming, and target tracking. With a highly extensible framework, it supports seamless integration of new functionalities, paving the way toward a general-purpose, instruction-driven intelligent UAV agent. The supplementary PPT is available at https://buaa-colalab.github.io/airstar.github.io.

Inferring user status at the edge is essential for delivering personalized services, such as detecting emotional states. However, deploying large-scale models directly on user devices is impractical due to substantial computational overhead and the scarcity of labeled data. Conversely, uploading raw data to the cloud for processing raises significant privacy concerns and incurs prohibitive communication costs. To address this challenge, we propose a privacy-preserving multimodal inference framework that leverages large-scale public data while safeguarding sensitive information and optimizing computational efficiency. Specifically, we first train a teacher model in the cloud using publicly available data. Through a feature distillation process, the knowledge from this teacher model is transferred to a lightweight encoder deployed at the user end. This transfer is tailored to the user's data, ensuring that only relevant knowledge is distilled. To accommodate varying communication constraints, we introduce a feature compression mechanism that significantly reduces communication overhead without compromising inference accuracy. Extensive experiments on emotion recognition tasks demonstrate that the proposed framework effectively balances privacy preservation, resource efficiency, and inference accuracy, facilitating seamless collaboration between cloud and edge devices.

The inference of large language models (LLMs) on distributed edge devices is crucial for privacy-preserving applications. However, its performance is severely degraded in a practically lossy edge network due to frequent synchronization. In this paper, we propose Coda, a novel context-aware distributed acceleration framework tailored for packet loss scenarios. We observe the consistency of sparse patterns of neuron group activations in the same context. By identifying sparsity patterns during the prefill phase and updating neuron groups mapping strategically, we enable a relaxed synchronization for decoding, without slowing down, while preserving accuracy. Our approach offers up to 5.62x speedup, significantly outperforming the state-of-the-art in various scenarios.

Collaborative perception shares information among different agents and helps solving problems that individual agents may face, e.g., occlusions and small sensing range. Prior methods usually separate the multi-agent fusion and multi-time fusion into two consecutive steps. In contrast, this paper proposes an efficient collaborative perception that aggregates the observations from different agents (space) and different times into a unified spatio-temporal space simultanesouly. The unified spatio-temporal space brings two benefits, i.e., efficient feature transmission and superior feature fusion. 1) Efficient feature transmission: each static object yields a single observation in the spatial temporal space, and thus only requires transmission only once (whereas prior methods re-transmit all the object features multiple times). 2) superior feature fusion: merging the multi-agent and multi-time fusion into a unified spatial-temporal aggregation enables a more holistic perspective, thereby enhancing perception performance in challenging scenarios. Consequently, our Collaborative perception with Spatio-temporal Transformer (CoST) gains improvement in both efficiency and accuracy. Notably, CoST is not tied to any specific method and is compatible with a majority of previous methods, enhancing their accuracy while reducing the transmission bandwidth.

Developing agents capable of navigating to a target location based on language instructions and visual information, known as vision-language navigation (VLN), has attracted widespread interest. Most research has focused on ground-based agents, while UAV-based VLN remains relatively underexplored. Recent efforts in UAV vision-language navigation predominantly adopt ground-based VLN settings, relying on predefined discrete action spaces and neglecting the inherent disparities in agent movement dynamics and the complexity of navigation tasks between ground and aerial environments. To address these disparities and challenges, we propose solutions from three perspectives: platform, benchmark, and methodology. To enable realistic UAV trajectory simulation in VLN tasks, we propose the OpenUAV platform, which features diverse environments, realistic flight control, and extensive algorithmic support. We further construct a target-oriented VLN dataset consisting of approximately 12k trajectories on this platform, serving as the first dataset specifically designed for realistic UAV VLN tasks. To tackle the challenges posed by complex aerial environments, we propose an assistant-guided UAV object search benchmark called UAV-Need-Help, which provides varying levels of guidance information to help UAVs better accomplish realistic VLN tasks. We also propose a UAV navigation LLM that, given multi-view images, task descriptions, and assistant instructions, leverages the multimodal understanding capabilities of the MLLM to jointly process visual and textual information, and performs hierarchical trajectory generation. The evaluation results of our method significantly outperform the baseline models, while there remains a considerable gap between our results and those achieved by human operators, underscoring the challenge presented by the UAV-Need-Help task.

Recent advancements in multimodal large language models (MLLMs) have shown promising results, yet existing approaches struggle to effectively handle both temporal and spatial localization simultaneously. This challenge stems from two key issues: first, incorporating spatial-temporal localization introduces a vast number of coordinate combinations, complicating the alignment of linguistic and visual coordinate representations; second, encoding fine-grained temporal and spatial information during video feature compression is inherently difficult. To address these issues, we propose LLaVA-ST, a MLLM for fine-grained spatial-temporal multimodal understanding. In LLaVA-ST, we propose Language-Aligned Positional Embedding, which embeds the textual coordinate special token into the visual space, simplifying the alignment of fine-grained spatial-temporal correspondences. Additionally, we design the Spatial-Temporal Packer, which decouples the feature compression of temporal and spatial resolutions into two distinct point-to-region attention processing streams. Furthermore, we propose ST-Align dataset with 4.3M training samples for fine-grained spatial-temporal multimodal understanding. With ST-align, we present a progressive training pipeline that aligns the visual and textual feature through sequential coarse-to-fine stages. Additionally, we introduce an ST-Align benchmark to evaluate spatial-temporal interleaved fine-grained understanding tasks, which include Spatial-Temporal Video Grounding (STVG) , Event Localization and Captioning (ELC) and Spatial Video Grounding (SVG). LLaVA-ST achieves outstanding performance on 11 benchmarks requiring fine-grained temporal, spatial, or spatial-temporal interleaving multimodal understanding. Our code, data and benchmark will be released at https://github.com/appletea233/LLaVA-ST.

A typical human strategy for giving navigation guidance is to sketch route maps based on the environmental layout. Inspired by this, we introduce Sketch map-based visual Navigation (SkeNa), an embodied navigation task in which an agent must reach a goal in an unseen environment using only a hand-drawn sketch map as guidance. To support research for SkeNa, we present a large-scale dataset named SoR, comprising 54k trajectory and sketch map pairs across 71 indoor scenes. In SoR, we introduce two navigation validation sets with varying levels of abstraction in hand-drawn sketches, categorized based on their preservation of spatial scales in the environment, to facilitate future research. To construct SoR, we develop an automated sketch-generation pipeline that efficiently converts floor plans into hand-drawn representations. To solve SkeNa, we propose SkeNavigator, a navigation framework that aligns visual observations with hand-drawn maps to estimate navigation targets. It employs a Ray-based Map Descriptor (RMD) to enhance sketch map valid feature representation using equidistant sampling points and boundary distances. To improve alignment with visual observations, a Dual-Map Aligned Goal Predictor (DAGP) leverages the correspondence between sketch map features and on-site constructed exploration map features to predict goal position and guide navigation. SkeNavigator outperforms prior floor plan navigation methods by a large margin, improving SPL on the high-abstract validation set by 105

Given a high-level instruction, the task of Embodied Referring Expression (REVERIE) requires an embodied agent to localise a remote referred object via navigating in the unseen environment. Previous vision-language navigation methods utilise the provided fine-grained instruction as step-by-step navigation guidance to conduct strict instruction-following, while REVERIE aims to achieve efficient goal-oriented exploration according to the high-level command. In this work, we propose a Cross-modal Knowledge Reasoning (abbreviated as CKR+) framework, which incorporates the prior knowledge as decision guidance to learn the navigation scheme comprehensively. Specifically, we design a Room-Object Aware (ROA) mechanism to explicitly decouple the room- and object-related clues from instruction and visual observations. Moreover, we propose a Knowledge-enabled Entity Relation Reasoning (KERR+) module to leverage the structured knowledge from the knowledge graph explicitly and unstructured knowledge from pre-trained model implicitly, to learn the internal-external correlations among room- and object-entities for the agent to make proper decisions. We devise an Entity Prompter (EP) that embeds in the KERR+ module, which utilises the navigation history and visual entities as prompts to transfer knowledge from the pre-trained CLIP model. In addition, we develop a Reinforced End Decider (RED) to learn the stopping scheme specifically, which is achieved by a customised reinforcement learning strategy and knowledge enhanced matching. Two techniques are also introduced to improve navigation efficiency further. Extensive experiments conducted on the REVERIE benchmark demonstrate the effectiveness and superiority of our proposed methods, which boosts the key metrics, i.e., SPL and REVERIE-success rate, to 14.46% and 13.81% respectively.

Instruction generation is a vital and multidisciplinary research area with broad applications. Existing instruction generation models are limited to generating instructions in a single style from a particular dataset, and the style and content of generated instructions cannot be controlled. Moreover, most existing instruction generation methods also disregard the spatial modeling of the navigation environment. Leveraging the capabilities of Large Language Models (LLMs), we propose C-Instructor, which utilizes the chain-of-thought-style prompt for style-controllable and content-controllable instruction generation. Firstly, we propose a Chain of Thought with Landmarks (CoTL) mechanism, which guides the LLM to identify key landmarks and then generate complete instructions. CoTL renders generated instructions more accessible to follow and offers greater controllability over the manipulation of landmark objects. Furthermore, we present a Spatial Topology Modeling Task to facilitate the understanding of the spatial structure of the environment. Finally, we introduce a Style-Mixed Training policy, harnessing the prior knowledge of LLMs to enable style control for instruction generation based on different prompts within a single model instance. Extensive experiments demonstrate that instructions generated by C-Instructor outperform those generated by previous methods in text metrics, navigation guidance evaluation, and user studies.

Audio-visual navigation is an audio-targeted wayfinding task where a robot agent is entailed to travel a never-before-seen 3D environment towards the sounding source. In this article, we present ORAN, an omnidirectional audio-visual navigator based on cross-task navigation skill transfer. In particular, ORAN sharpens its two basic abilities for a such challenging task, namely wayfinding and audio-visual information gathering. First, ORAN is trained with a confidence-aware cross-task policy distillation (CCPD) strategy. CCPD transfers the fundamental, point-to-point wayfinding skill that is well trained on the large-scale PointGoal task to ORAN, so as to help ORAN to better master audio-visual navigation with far fewer training samples. To improve the efficiency of knowledge transfer and address the domain gap, CCPD is made to be adaptive to the decision confidence of the teacher policy. Second, ORAN is equipped with an omnidirectional information gathering (OIG) mechanism, i.e., gleaning visual-acoustic observations from different directions before decision-making. As a result, ORAN yields more robust navigation behaviour. Taking CCPD and OIG together, ORAN significantly outperforms previous competitors. After the model ensemble, we got 1st in Soundspaces Challenge 2022, improving SPL and SR by 53% and 35% relatively.

Federated Learning (FL) is an emerging paradigm that enables distributed users to collaboratively and iteratively train machine learning models without sharing their private data. Motivated by the effectiveness and robustness of self-attention-based architectures, researchers are turning to using pre-trained Transformers (i.e., foundation models) instead of traditional convolutional neural networks in FL to leverage their excellent transfer learning capabilities. Despite recent progress, how pre-trained Transformer models play a role in FL remains obscure, that is, how to efficiently fine-tune these pre-trained models in FL and how FL users could benefit from this new paradigm. In this paper, we explore this issue and demonstrate that the fine-tuned Transformers achieve extraordinary performance on FL, and that the lightweight fine-tuning method facilitates a fast convergence rate and low communication costs. Concretely, we conduct a rigorous empirical study of three tuning methods (i.e., modifying the input, adding extra modules, and adjusting the backbone) using two types of pre-trained models (i.e., vision-language models and vision models) for FL. Our experiments show that 1) Fine-tuning the bias term of the backbone performs best when relying on a strong pre-trained model; 2) The vision-language model (e.g., CLIP) outperforms the pure vision model (e.g., ViT) and is more robust to the few-shot settings; 3) Compared to pure local training, FL with pre-trained models has a higher accuracy because it alleviates the problem of over-fitting. We will release our code and encourage further exploration of pre-trained Transformers and FL.

Vision-language navigation is the task of directing an embodied agent to navigate in 3D scenes with natural language instructions. For the agent, inferring the long-term navigation target from visual-linguistic clues is crucial for reliable path planning, which, however, has rarely been studied before in literature. In this article, we propose a Target-Driven Structured Transformer Planner (TD-STP) for long-horizon goal-guided and room layout-aware navigation. Specifically, we devise an Imaginary Scene Tokenization mechanism for explicit estimation of the long-term target (even located in unexplored environments). In addition, we design a Structured Transformer Planner which elegantly incorporates the explored room layout into a neural attention architecture for structured and global planning. Experimental results demonstrate that our TD-STP substantially improves previous best methods' success rate by 2% and 5% on the test set of R2R and REVERIE benchmarks, respectively. Our code is available at https://github.com/YushengZhao/TD-STP.

Vision-and-language Navigation (VLN) task requires an embodied agent to navigate to a remote location following a natural language instruction. Previous methods usually adopt a sequence model (e.g., Transformer and LSTM) as the navigator. In such a paradigm, the sequence model predicts action at each step through a maintained navigation state, which is generally represented as a one-dimensional vector. However, the crucial navigation clues (i.e., object-level environment layout) for embodied navigation task is discarded since the maintained vector is essentially unstructured. In this paper, we propose a novel Structured state-Evolution (SEvol) model to effectively maintain the environment layout clues for VLN. Specifically, we utilise the graph-based feature to represent the navigation state instead of the vector-based state. Accordingly, we devise a Reinforced Layout clues Miner (RLM) to mine and detect the most crucial layout graph for long-term navigation via a customised reinforcement learning strategy. Moreover, the Structured Evolving Module (SEM) is proposed to maintain the structured graph-based state during navigation, where the state is gradually evolved to learn the object-level spatial-temporal relationship. The experiments on the R2R and R4R datasets show that the proposed SEvol model improves VLN models' performance by large margins, e.g., +3% absolute SPL accuracy for NvEM and +8% for EnvDrop on the R2R test set.

The Remote Embodied Referring Expression (REVERIE) is a recently raised task that requires an agent to navigate to and localise a referred remote object according to a high-level language instruction. Different from related VLN tasks, the key to REVERIE is to conduct goal-oriented exploration instead of strict instruction-following, due to the lack of step-by-step navigation guidance. In this paper, we propose a novel Cross-modality Knowledge Reasoning (CKR) model to address the unique challenges of this task. The CKR, based on a transformer-architecture, learns to generate scene memory tokens and utilise these informative history clues for exploration. Particularly, a Room-and-Object Aware Attention (ROAA) mechanism is devised to explicitly perceive the room- and object-type information from both linguistic and visual observations. Moreover, through incorporating commonsense knowledge, we propose a Knowledge-enabled Entity Relationship Reasoning (KERR) module to learn the internal-external correlations among room- and object-entities for agent to make proper action at each viewpoint. Evaluation on REVERIE benchmark demonstrates the superiority of the CKR model, which significantly boosts SPL and REVERIE-success rate by 64.67% and 46.05%, respectively. Code is available at: https://github.com/alloldman/CKR.