Diversified Scaling Inference in Time Series Foundation Models

The advancement of Time Series Foundation Models (TSFMs) has been driven primarily by large-scale pre-training, but inference-time compute potential remains largely untapped. This work systematically investigates two questions: how do TSFMs behave under standard sampling-based inference scaling, and can controlled sampling diversity enhance performance? We first examine the properties of TSFMs under standard sampling often fail to adhere to scaling laws due to insufficient exploration of the solution space. Building on this, we then delve into diversified inference scaling via tailored time series perturbations to expand the generative distribution's support. We theoretically analyze the diversity-fidelity trade-off and derive a critical sample threshold for diversified sampling to outperform standard sampling. Extensive experiments across various TSFMs and datasets show proper diversified inference scaling yields substantial performance gains without parameter updates, establishing inference design as a critical, compute-efficient dimension of TSFM optimization. As an application, we propose RobustMSE, a rigorous metric to quantify the headroom performance of TSFM under a fixed budget. Overall, our findings clarify these factor interactions, enabling reliable performance via diverse large-scale inference time series in parallel environments without re-training TSFMs.

Unified Video Editing with Temporal Reasoner

Existing video editing methods face a critical trade-off: expert models offer precision but rely on task-specific priors like masks, hindering unification; conversely, unified temporal in-context learning models are mask-free but lack explicit spatial cues, leading to weak instruction-to-region mapping and imprecise localization. To resolve this conflict, we propose VideoCoF, a novel Chain-of-Frames approach inspired by Chain-of-Thought reasoning. VideoCoF enforces a ``see, reason, then edit" procedure by compelling the video diffusion model to first predict reasoning tokens (edit-region latents) before generating the target video tokens. This explicit reasoning step removes the need for user-provided masks while achieving precise instruction-to-region alignment and fine-grained video editing. Furthermore, we introduce a RoPE alignment strategy that leverages these reasoning tokens to ensure motion alignment and enable length extrapolation beyond the training duration. We demonstrate that with a minimal data cost of only 50k video pairs, VideoCoF achieves state-of-the-art performance on VideoCoF-Bench, validating the efficiency and effectiveness of our approach. Our code, weight, data are available at https://github.com/knightyxp/VideoCoF.

Bi-level Personalization for Federated Foundation Models: A Task-vector Aggregation Approach

Federated foundation models represent a new paradigm to jointly fine-tune pre-trained foundation models across clients. It is still a challenge to fine-tune foundation models for a small group of new users or specialized scenarios, which typically involve limited data compared to the large-scale data used in pre-training. In this context, the trade-off between personalization and federation becomes more sensitive. To tackle these, we proposed a bi-level personalization framework for federated fine-tuning on foundation models. Specifically, we conduct personalized fine-tuning on the client-level using its private data, and then conduct a personalized aggregation on the server-level using similar users measured by client-specific task vectors. Given the personalization information gained from client-level fine-tuning, the server-level personalized aggregation can gain group-wise personalization information while mitigating the disturbance of irrelevant or interest-conflict clients with non-IID data. The effectiveness of the proposed algorithm has been demonstrated by extensive experimental analysis in benchmark datasets.

Efficient and Microphone-Fault-Tolerant 3D Sound Source Localization

Sound source localization (SSL) is a critical technology for determining the position of sound sources in complex environments. However, existing methods face challenges such as high computational costs and precise calibration requirements, limiting their deployment in dynamic or resource-constrained environments. This paper introduces a novel 3D SSL framework, which uses sparse cross-attention, pretraining, and adaptive signal coherence metrics, to achieve accurate and computationally efficient localization with fewer input microphones. The framework is also fault-tolerant to unreliable or even unknown microphone position inputs, ensuring its applicability in real-world scenarios. Preliminary experiments demonstrate its scalability for multi-source localization without requiring additional hardware. This work advances SSL by balancing the model's performance and efficiency and improving its robustness for real-world scenarios.

RoHyDR: Robust Hybrid Diffusion Recovery for Incomplete Multimodal Emotion Recognition

Multimodal emotion recognition analyzes emotions by combining data from multiple sources. However, real-world noise or sensor failures often cause missing or corrupted data, creating the Incomplete Multimodal Emotion Recognition (IMER) challenge. In this paper, we propose Robust Hybrid Diffusion Recovery (RoHyDR), a novel framework that performs missing-modality recovery at unimodal, multimodal, feature, and semantic levels. For unimodal representation recovery of missing modalities, RoHyDR exploits a diffusion-based generator to generate distribution-consistent and semantically aligned representations from Gaussian noise, using available modalities as conditioning. For multimodal fusion recovery, we introduce adversarial learning to produce a realistic fused multimodal representation and recover missing semantic content. We further propose a multi-stage optimization strategy that enhances training stability and efficiency. In contrast to previous work, the hybrid diffusion and adversarial learning-based recovery mechanism in RoHyDR allows recovery of missing information in both unimodal representation and multimodal fusion, at both feature and semantic levels, effectively mitigating performance degradation caused by suboptimal optimization. Comprehensive experiments conducted on two widely used multimodal emotion recognition benchmarks demonstrate that our proposed method outperforms state-of-the-art IMER methods, achieving robust recognition performance under various missing-modality scenarios. Our code will be made publicly available upon acceptance.

Federated Adapter on Foundation Models: An Out-Of-Distribution Approach

As foundation models gain prominence, Federated Foundation Models (FedFM) have emerged as a privacy-preserving approach to collaboratively fine-tune models in federated learning (FL) frameworks using distributed datasets across clients. A key challenge for FedFM, given the versatile nature of foundation models, is addressing out-of-distribution (OOD) generalization, where unseen tasks or clients may exhibit distribution shifts leading to suboptimal performance. Although numerous studies have explored OOD generalization in conventional FL, these methods are inadequate for FedFM due to the challenges posed by large parameter scales and increased data heterogeneity. To address these, we propose FedOA, which employs adapter-based parameter-efficient fine-tuning methods for efficacy and introduces personalized adapters with feature distance-based regularization to align distributions and guarantee OOD generalization for each client. Theoretically, we demonstrate that the conventional aggregated global model in FedFM inherently retains OOD generalization capabilities, and our proposed method enhances the personalized model's OOD generalization through regularization informed by the global model, with proven convergence under general non-convex settings. Empirically, the effectiveness of the proposed method is validated on benchmark datasets across various NLP tasks.

Target Speaker Extraction through Comparing Noisy Positive and Negative Audio Enrollments

Target speaker extraction focuses on isolating a specific speaker's voice from an audio mixture containing multiple speakers. To provide information about the target speaker's identity, prior works have utilized clean audio examples as conditioning inputs. However, such clean audio examples are not always readily available (e.g. It is impractical to obtain a clean audio example of a stranger's voice at a cocktail party without stepping away from the noisy environment). Limited prior research has explored extracting the target speaker's characteristics from noisy audio examples, which may include overlapping speech from disturbing speakers. In this work, we focus on target speaker extraction when multiple speakers are present during the enrollment stage, through leveraging differences between audio segments where the target speakers are speaking (Positive Enrollments) and segments where they are not (Negative Enrollments). Experiments show the effectiveness of our model architecture and the dedicated pretraining method for the proposed task. Our method achieves state-of-the-art performance in the proposed application settings and demonstrates strong generalizability across challenging and realistic scenarios.

Position: Empowering Time Series Reasoning with Multimodal LLMs

Understanding time series data is crucial for multiple real-world applications. While large language models (LLMs) show promise in time series tasks, current approaches often rely on numerical data alone, overlooking the multimodal nature of time-dependent information, such as textual descriptions, visual data, and audio signals. Moreover, these methods underutilize LLMs' reasoning capabilities, limiting the analysis to surface-level interpretations instead of deeper temporal and multimodal reasoning. In this position paper, we argue that multimodal LLMs (MLLMs) can enable more powerful and flexible reasoning for time series analysis, enhancing decision-making and real-world applications. We call on researchers and practitioners to leverage this potential by developing strategies that prioritize trust, interpretability, and robust reasoning in MLLMs. Lastly, we highlight key research directions, including novel reasoning paradigms, architectural innovations, and domain-specific applications, to advance time series reasoning with MLLMs.

USV-AUV Collaboration Framework for Underwater Tasks under Extreme Sea Conditions

Autonomous underwater vehicles (AUVs) are valuable for ocean exploration due to their flexibility and ability to carry communication and detection units. Nevertheless, AUVs alone often face challenges in harsh and extreme sea conditions. This study introduces a unmanned surface vehicle (USV)-AUV collaboration framework, which includes high-precision multi-AUV positioning using USV path planning via Fisher information matrix optimization and reinforcement learning for multi-AUV cooperative tasks. Applied to a multi-AUV underwater data collection task scenario, extensive simulations validate the framework's feasibility and superior performance, highlighting exceptional coordination and robustness under extreme sea conditions. The simulation code will be made available as open-source to foster future research in this area.

Large Language Models as Efficient Reward Function Searchers for Custom-Environment Multi-Objective Reinforcement Learning

Leveraging large language models (LLMs) for designing reward functions demonstrates significant potential. However, achieving effective design and improvement of reward functions in reinforcement learning (RL) tasks with complex custom environments and multiple requirements presents considerable challenges. In this paper, we enable LLMs to be effective white-box searchers, highlighting their advanced semantic understanding capabilities. Specifically, we generate reward components for each explicit user requirement and employ the reward critic to identify the correct code form. Then, LLMs assign weights to the reward components to balance their values and iteratively search and optimize these weights based on the context provided by the training log analyzer, while adaptively determining the search step size. We applied the framework to an underwater information collection RL task without direct human feedback or reward examples (zero-shot). The reward critic successfully correct the reward code with only one feedback for each requirement, effectively preventing irreparable errors that can occur when reward function feedback is provided in aggregate. The effective initialization of weights enables the acquisition of different reward functions within the Pareto solution set without weight search. Even in the case where a weight is 100 times off, fewer than four iterations are needed to obtain solutions that meet user requirements. The framework also works well with most prompts utilizing GPT-3.5 Turbo, since it does not require advanced numerical understanding or calculation.