Q. Wu

Yanyuan Qiao, Wenqi Lyu, Hui Wang et al.

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 closed-source 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 real-world 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.

Qi Chen, Dileepa Pitawela, Chongyang Zhao et al.

Vision-and-Language Navigation (VLN) task aims to enable AI agents to accurately understand and follow natural language instructions to navigate through real-world environments, ultimately reaching specific target locations. We recognise a promising opportunity to extend VLN to a comparable navigation task that holds substantial significance in our daily lives, albeit within the virtual realm: navigating websites on the Internet. This paper proposes a new task named Vision-and-Language Navigation on Websites (WebVLN), where we use question-based instructions to train an agent, emulating how users naturally browse websites. Unlike the existing VLN task that only pays attention to vision and instruction (language), the WebVLN agent further considers underlying web-specific content like HTML, which could not be seen on the rendered web pages yet contains rich visual and textual information. Toward this goal, we contribute a dataset, WebVLN-v1, and introduce a novel approach called Website-aware VLN Network (WebVLN-Net), which is built upon the foundation of state-of-the-art VLN techniques. Experimental results show that WebVLN-Net outperforms current VLN and web-related navigation methods. We believe that the introduction of the new WebVLN task and its dataset will establish a new dimension within the VLN domain and contribute to the broader vision-and-language research community. The code is available at: https://github.com/WebVLN/WebVLN.

Feng Chen, Yefei He, Shaoxuan He et al.

Existing sparse attention methods primarily target inference-time acceleration by selecting critical tokens under predefined sparsity patterns. However, they often fail to bridge the training-inference gap and lack the capacity for fine-grained token selection across multiple dimensions such as queries, key-values (KV), and heads, leading to suboptimal performance and limited acceleration gains. In this paper, we introduce OmniSparse, a training-aware fine-grained sparse attention framework for long-video MLLMs, which operates in both training and inference with dynamic token budget allocation. Specifically, OmniSparse contains three adaptive and complementary mechanisms: (1) query selection via lazy-active classification, retaining active queries that capture broad semantic similarity while discarding most lazy ones that focus on limited local context and exhibit high functional redundancy; (2) KV selection with head-level dynamic budget allocation, where a shared budget is determined based on the flattest head and applied uniformly across all heads to ensure attention recall; and (3) KV cache slimming to reduce head-level redundancy by selectively fetching visual KV cache according to the head-level decoding query pattern. Experimental results show that OmniSparse matches the performance of full attention while achieving up to 2.7x speedup during prefill and 2.4x memory reduction during decoding.

Yanyuan Qiao, Zheng Yu, Longteng Guo et al.

Multimodal large language models (MLLMs) have attracted widespread interest and have rich applications. However, the inherent attention mechanism in its Transformer structure requires quadratic complexity and results in expensive computational overhead. Therefore, in this work, we propose VL-Mamba, a multimodal large language model based on state space models, which have been shown to have great potential for long-sequence modeling with fast inference and linear scaling in sequence length. Specifically, we first replace the transformer-based backbone language model such as LLama or Vicuna with the pre-trained Mamba language model. Then, we empirically explore how to effectively apply the 2D vision selective scan mechanism for multimodal learning and the combinations of different vision encoders and variants of pretrained Mamba language models. The extensive experiments on diverse multimodal benchmarks with competitive performance show the effectiveness of our proposed VL-Mamba and demonstrate the great potential of applying state space models for multimodal learning tasks.

Yingguang Yang, Qi Wu, Buyun He et al.

Recent advancements in social bot detection have been driven by the adoption of Graph Neural Networks. The social graph, constructed from social network interactions, contains benign and bot accounts that influence each other. However, previous graph-based detection methods that follow the transductive message-passing paradigm may not fully utilize hidden graph information and are vulnerable to adversarial bot behavior. The indiscriminate message passing between nodes from different categories and communities results in excessively homogeneous node representations, ultimately reducing the effectiveness of social bot detectors. In this paper, we propose SEBot, a novel multi-view graph-based contrastive learning-enabled social bot detector. In particular, we use structural entropy as an uncertainty metric to optimize the entire graph's structure and subgraph-level granularity, revealing the implicitly existing hierarchical community structure. And we design an encoder to enable message passing beyond the homophily assumption, enhancing robustness to adversarial behaviors of social bots. Finally, we employ multi-view contrastive learning to maximize mutual information between different views and enhance the detection performance through multi-task learning. Experimental results demonstrate that our approach significantly improves the performance of social bot detection compared with SOTA methods.

Keke Gai, Mohan Wang, Jing Yu et al.

Multimodal Federated Learning (MFL) with mixed modalities enables unimodal and multimodal clients to collaboratively train models while ensuring clients' privacy. As a representative sample of local data, prototypes offer an approach with low resource consumption and no reliance on prior knowledge for MFL with mixed modalities. However, existing prototype-based MFL methods assume unified labels across clients and identical tasks per client, which is impractical in MFL with mixed modalities. In this work, we propose an Adaptive prototype-based Multimodal Federated Learning (AproMFL) framework for mixed modalities to address the aforementioned issues. Our AproMFL transfers knowledge through adaptively-constructed prototypes without unified labels. Clients adaptively select prototype construction methods in line with labels; server converts client prototypes into unified multimodal prototypes and cluster them to form global prototypes. To address model aggregation issues in task heterogeneity, we develop a client relationship graph-based scheme to dynamically adjust aggregation weights. Furthermore, we propose a global prototype knowledge transfer loss and a global model knowledge transfer loss to enable the transfer of global knowledge to local knowledge. Experimental results show that AproMFL outperforms four baselines on three highly heterogeneous datasets ($α=0.1$) and two heterogeneous tasks, with the optimal results in accuracy and recall being 0.42%~6.09% and 1.6%~3.89% higher than those of FedIoT (FedAvg-based MFL), respectively.

Zipeng Fu, Qingqing Zhao, Qi Wu et al.

One of the key arguments for building robots that have similar form factors to human beings is that we can leverage the massive human data for training. Yet, doing so has remained challenging in practice due to the complexities in humanoid perception and control, lingering physical gaps between humanoids and humans in morphologies and actuation, and lack of a data pipeline for humanoids to learn autonomous skills from egocentric vision. In this paper, we introduce a full-stack system for humanoids to learn motion and autonomous skills from human data. We first train a low-level policy in simulation via reinforcement learning using existing 40-hour human motion datasets. This policy transfers to the real world and allows humanoid robots to follow human body and hand motion in real time using only a RGB camera, i.e. shadowing. Through shadowing, human operators can teleoperate humanoids to collect whole-body data for learning different tasks in the real world. Using the data collected, we then perform supervised behavior cloning to train skill policies using egocentric vision, allowing humanoids to complete different tasks autonomously by imitating human skills. We demonstrate the system on our customized 33-DoF 180cm humanoid, autonomously completing tasks such as wearing a shoe to stand up and walk, unloading objects from warehouse racks, folding a sweatshirt, rearranging objects, typing, and greeting another robot with 60-100% success rates using up to 40 demonstrations. Project website: https://humanoid-ai.github.io/