Changwen Zheng

Offline goal-conditioned reinforcement learning (GCRL) provides a practical framework for learning policies from fixed offline datasets to accomplish diverse goals. Existing methods commonly construct goal-conditioned learning signals through goal relabeling, reusing achieved states in offline trajectories as training goals. However, conventional relabeling methods typically treat these states uniformly, failing to prioritize informative, task-advancing goals. In this work, we propose Key-State Relabeling (KSR), a plug-and-play goal relabeling strategy that prioritizes task-relevant key states as relabeled goals. To efficiently identify key states in complex long-horizon offline trajectories, we leverage the reasoning capabilities of large language models (LLMs) to generate executable discriminators from task specifications. For trustworthy and controllable relabeling, we further introduce a two-stage Self-Check mechanism to mitigate hallucinations in LLM-generated discriminators: compile-time code validation and TD-error-guided relabel-time refinement. Theoretically, we show that KSR yields a tighter sample-complexity bound by reducing the covering complexity of the relabeled goal set and lowering the effective GOAL-BE dimension. Empirically, we show that KSR, as a plug-and-play goal relabeling strategy, consistently improves multiple offline GCRL baselines across diverse OGBench navigation and manipulation tasks, while remaining effective on noisy datasets and introducing only moderate computational overhead. Overall, key-state relabeling provides an effective way to construct more informative training transitions for goal-conditioned policy learning.

The World Wide Web needs reliable predictive capabilities to respond to changes in user behavior and usage patterns. Time series forecasting (TSF) is a key means to achieve this goal. In recent years, the large language models (LLMs) for TSF (LLM4TSF) have achieved good performance. However, there is a significant difference between pretraining corpora and time series data, making it hard to guarantee forecasting quality when directly applying LLMs to TSF; fine-tuning LLMs can mitigate this issue, but often incurs substantial computational overhead. Thus, LLM4TSF faces a dual challenge of prediction performance and compute overhead. To address this, we aim to explore a method for improving the forecasting performance of LLM4TSF while freezing all LLM parameters to reduce computational overhead. Inspired by in-context learning (ICL), we propose LVICL. LVICL uses our vector-injected ICL to inject example information into a frozen LLM, eliciting its in-context learning ability and thereby enhancing its performance on the example-related task (i.e., TSF). Specifically, we first use the LLM together with a learnable context vector adapter to extract a context vector from multiple examples adaptively. This vector contains compressed, example-related information. Subsequently, during the forward pass, we inject this vector into every layer of the LLM to improve forecasting performance. Compared with conventional ICL that adds examples into the prompt, our vector-injected ICL does not increase prompt length; moreover, adaptively deriving a context vector from examples suppresses components harmful to forecasting, thereby improving model performance. Extensive experiments demonstrate the effectiveness of our approach.

Discrete Global Grid Systems (DGGS), as a next-generation framework for the digital Earth, inevitably suffer from geometric non-uniformity, which impacts the accuracy of data representation and analysis. Existing quality assessments, predominantly based on Goodchild's criteria, are inadequate for diamond-based grids, particularly in evaluating angular and distance uniformity. This paper addresses this gap by proposing a comprehensive evaluation framework for spherical diamond grids. We extend the Goodchild criteria by incorporating metrics for angular and distance uniformity, creating an integrated five-dimensional system (shape, topology, size, distance, and angle). Using this framework, we systematically compare three typical diamond DGGS derived from the cube, octahedron, and icosahedron. Our results demonstrate that the icosahedron-based grid exhibits optimal uniformity across all five dimensions. Critically, we reveal that the octahedron-based grid, despite having more initial faces, suffers from severe angular distortion in the across-face boundary regions, rendering its uniformity inferior to that of the cube-based grid. We further validate our framework by constructing a Spherical Residual Network for Diamond Grids (SResNet-DG) for a classification task. Our experimental results demonstrate a strong positive correlation between grid uniformity and the SResNet-DG's performance, substantiating the effectiveness and practical relevance of our proposed geometric evaluation system.

Large Language Models (LLMs) have recently shown exceptional potential in time series forecasting, leveraging their inherent sequential reasoning capabilities to model complex temporal dynamics. However, existing approaches typically employ a naive autoregressive generation strategy. We identify a critical theoretical flaw in this paradigm: during inference, the model operates in an open-loop manner, consuming its own generated outputs recursively. This leads to inevitable error accumulation (exposure bias), where minor early deviations cascade into significant trajectory drift over long horizons. In this paper, we reformulate autoregressive forecasting through the lens of control theory, proposing \textbf{F-LLM} (Feedback-driven LLM), a novel closed-loop framework. Unlike standard methods that passively propagate errors, F-LLM actively stabilizes the trajectory via a learnable residual estimator (Observer) and a feedback controller. Furthermore, we provide a theoretical guarantee that our closed-loop mechanism ensures uniformly bounded error, provided the base model satisfies a local Lipschitz constraint. Extensive experiments demonstrate that F-LLM significantly mitigates error propagation, achieving good performance on time series benchmarks.

In this paper, we addressed the limitation of relying solely on distribution alignment and source-domain empirical risk minimization in Unsupervised Domain Adaptation (UDA). Our information-theoretic analysis showed that this standard adversarial-based framework neglects the discriminability of target-domain features, leading to suboptimal performance. To bridge this theoretical–practical gap, we defined “good representation learning” as guaranteeing both transferability and discriminability, and proved that an additional loss term targeting target-domain discriminability is necessary. Building on these insights, we proposed a novel adversarial-based UDA framework that explicitly integrates a domain alignment objective with a discriminability-enhancing constraint. Instantiated as Domain-Invariant Representation Learning with Global and Local Consistency (RLGLC), our method leverages Asymmetrically-Relaxed Wasserstein of Wasserstein Distance (AR-WWD) to address class imbalance and semantic dimension weighting, and employs a local consistency mechanism to preserve fine-grained target-domain discriminative information. Extensive experiments across multiple benchmark datasets demonstrate that RLGLC consistently surpasses state-of-the-art methods, confirming the value of our theoretical perspective and underscoring the necessity of enforcing both transferability and discriminability in adversarial-based UDA.

Graph contrastive learning (GCL) aims to learn discriminative semantic invariance by contrasting different views of the same graph that share critical topological patterns. However, existing GCL approaches with structural augmentations often struggle to identify task-relevant topological structures, let alone adapt to the varying coarse-to-fine topological granularities required across different downstream tasks. To remedy this issue, we introduce Hierarchical Topological Granularity Graph Contrastive Learning (HTG-GCL), a novel framework that leverages transformations of the same graph to generate multi-scale ring-based cellular complexes, embodying the concept of topological granularity, thereby generating diverse topological views. Recognizing that a certain granularity may contain misleading semantics, we propose a multi-granularity decoupled contrast and apply a granularity-specific weighting mechanism based on uncertainty estimation. Comprehensive experiments on various benchmarks demonstrate the effectiveness of HTG-GCL, highlighting its superior performance in capturing meaningful graph representations through hierarchical topological information.