arXiv subjects

Hong Xie

Publications and source records attributed to Hong Xie.

At least 37 records · Page 2Linked to original sources

arXiv2026

Cohomological Obstructions to Global Counterfactuals: A Sheaf-Theoretic Foundation for Generative Causal Models

Current continuous generative models (e.g., Diffusion Models, Flow Matching) implicitly assume that locally consistent causal mechanisms naturally yield globally coherent counterfactuals. In this paper, we prove that this assumption fails fundamentally when the causal graph exhibits non-trivial homology (e.g., structural conflicts or hidden confounders). We formalize structural causal models as cellular sheaves over Wasserstein spaces, providing a strict algebraic topological definition of cohomological obstructions in measure spaces. To ensure computational tractability and avoid deterministic singularities (which we define as manifold tearing), we introduce entropic regularization and derive the Entropic Wasserstein Causal Sheaf Laplacian, a novel system of coupled non-linear Fokker-Planck equations. Crucially, we prove an entropic pullback lemma for the first variation of pushforward measures. By integrating this with the Implicit Function Theorem (IFT) on Sinkhorn optimality conditions, we establish a direct algorithmic bridge to automatic differentiation (VJP), achieving O(1)-memory reverse-mode gradients strictly independent of the iteration horizon. Empirically, our framework successfully leverages thermodynamic noise to navigate topological barriers ("entropic tunneling") in high-dimensional scRNA-seq counterfactuals. Finally, we invert this theoretical framework to introduce the Topological Causal Score, demonstrating that our Sheaf Laplacian acts as a highly sensitive algebraic detector for topology-aware causal discovery.

cs.LG↗

arXiv2026

The Causal Uncertainty Principle: Manifold Tearing and the Topological Limits of Counterfactual Interventions

Judea Pearl's do-calculus provides a foundation for causal inference, but its translation to continuous generative models remains fraught with geometric challenges. We establish the fundamental limits of such interventions. We define the Counterfactual Event Horizon and prove the Manifold Tearing Theorem: deterministic flows inevitably develop finite-time singularities under extreme interventions. We establish the Causal Uncertainty Principle for the trade-off between intervention extremity and identity preservation. Finally, we introduce Geometry-Aware Causal Flow (GACF), a scalable algorithm that utilizes a topological radar to bypass manifold tearing, validated on high-dimensional scRNA-seq data.

cs.LG↗

arXiv2026

SmoothVLA: Aligning Vision-Language-Action Models with Physical Constraints via Intrinsic Smoothness Optimization

Vision-Language-Action (VLA) models have emerged as a powerful paradigm for robotic manipulation. However, existing post-training methods face a dilemma between stability and exploration: Supervised Fine-Tuning (SFT) is constrained by demonstration quality and lacks generalization, whereas Reinforcement Learning (RL) improves exploration but often induces erratic, jittery trajectories that violate physical constraints. To bridge this gap, we propose SmoothVLA, a novel reinforcement learning fine-tuning framework that synergistically optimizes task performance and motion smoothness. The technical core is a physics-informed hybrid reward function that integrates binary sparse task rewards with a continuous dense term derived from trajectory jerk. Crucially, this reward is intrinsic, that computing directly from policy rollouts, without requiring extrinsic environment feedback or laborious reward engineering. Leveraging the Group Relative Policy Optimization (GRPO), SmoothVLA establishes trajectory smoothness as an explicit optimization prior, guiding the model toward physically feasible and stable control. Extensive experiments on the LIBERO benchmark demonstrate that SmoothVLA outperforms standard RL by 13.8\% in smoothness and significantly surpasses SFT in generalization across diverse tasks. Our work offers a scalable approach to aligning VLA models with physical-world constraints through intrinsic reward optimization.

cs.RO↗

arXiv2026

GTM: A General Time-series Model for Enhanced Representation Learning of Time-Series Data

Despite recent progress in time-series foundation models, challenges persist in improving representation learning and adapting to diverse downstream tasks. We introduce a General Time-series Model (GTM), which advances representation learning via a novel frequency-domain attention mechanism that captures time-granularity-aware features, an aspect underexplored in prior research. We further propose a novel pre-training strategy that unifies reconstruction and autoregressive objectives through a hybrid masking mechanism. Our pre-training strategy, combined with 2D positional encoding and span shuffling, enhances the robustness and generalization of representations. GTM is established as the first generative-task-agnostic model for time-series analysis, enabling seamless adaptation to various generative tasks without any task-specific modifications. Extensive experiments demonstrate that GTM consistently outperforms SOTA models on various generative tasks and achieves strong classification results with minimal adaptation. Furthermore, GTM exhibits clear scaling behavior, with accuracy improving as model size and pre-training data increase.

cs.LG↗

arXiv2026

Fairness Begins with State: Purifying Latent Preferences for Hierarchical Reinforcement Learning in Interactive Recommendation

Interactive recommender systems (IRS) are increasingly optimized with Reinforcement Learning (RL) to capture the sequential nature of user-system dynamics. However, existing fairness-aware methods often suffer from a fundamental oversight: they assume the observed user state is a faithful representation of true preferences. In reality, implicit feedback is contaminated by popularity-driven noise and exposure bias, creating a distorted state that misleads the RL agent. We argue that the persistent conflict between accuracy and fairness is not merely a reward-shaping issue, but a state estimation failure. In this work, we propose \textbf{DSRM-HRL}, a framework that reformulates fairness-aware recommendation as a latent state purification problem followed by decoupled hierarchical decision-making. We introduce a Denoising State Representation Module (DSRM) based on diffusion models to recover the low-entropy latent preference manifold from high-entropy, noisy interaction histories. Built upon this purified state, a Hierarchical Reinforcement Learning (HRL) agent is employed to decouple conflicting objectives: a high-level policy regulates long-term fairness trajectories, while a low-level policy optimizes short-term engagement under these dynamic constraints. Extensive experiments on high-fidelity simulators (KuaiRec, KuaiRand) demonstrate that DSRM-HRL effectively breaks the "rich-get-richer" feedback loop, achieving a superior Pareto frontier between recommendation utility and exposure equity.

cs.LG↗

arXiv2026

MMH-Planner: Multi-Mode Hybrid Trajectory Planning Method for UAV Efficient Flight Based on Real-Time Spatial Awareness

Motion planning is a critical component of intelligent unmanned systems, enabling their complex autonomous operations. However, current planning algorithms still face limitations in planning efficiency due to inflexible strategies and weak adaptability. To address this, this paper proposes a multi-mode hybrid trajectory planning method for UAVs based on real-time environmental awareness, which dynamically selects the optimal planning model for high-quality trajectory generation in response to environmental changes. First, we introduce a goal-oriented spatial awareness method that rapidly assesses flight safety in the upcoming environments. Second, a multi-mode hybrid trajectory planning mechanism is proposed, which can enhance the planning efficiency by selecting the optimal planning model for trajectory generation based on prior spatial awareness. Finally, we design a lazy replanning strategy that triggers replanning only when necessary to reduce computational resource consumption while maintaining flight quality. To validate the performance of the proposed method, we conducted comprehensive comparative experiments in simulation environments. Results demonstrate that our approach outperforms existing state-of-the-art (SOTA) algorithms across multiple metrics, achieving the best performance particularly in terms of the average number of planning iterations and computational cost per iteration. Furthermore, the effectiveness of our approach is further verified through real-world flight experiments integrated with a self-developed intelligent UAV platform.

cs.RO↗

arXiv2026

Proactive Guiding Strategy for Item-side Fairness in Interactive Recommendation

Item-side fairness is crucial for ensuring the fair exposure of long-tail items in interactive recommender systems. Existing approaches promote the exposure of long-tail items by directly incorporating them into recommended results. This causes misalignment between user preferences and the recommended long-tail items, which hinders long-term user engagement and reduces the effectiveness of recommendations. We aim for a proactive fairness-guiding strategy, which actively guides user preferences toward long-tail items while preserving user satisfaction during the interactive recommendation process. To this end, we propose HRL4PFG, an interactive recommendation framework that leverages hierarchical reinforcement learning to guide user preferences toward long-tail items progressively. HRL4PFG operates through a macro-level process that generates fairness-guided targets based on multi-step feedback, and a micro-level process that fine-tunes recommendations in real time according to both these targets and evolving user preferences. Extensive experiments show that HRL4PFG improves cumulative interaction rewards and maximum user interaction length by a larger margin when compared with state-of-the-art methods in interactive recommendation environments.

cs.IR↗

arXiv2026

Unusual Circumstances of the 2024 June 8 GLE

Ground Level Enhancement (GLE) in large solar energetic particle (SEP) events is indicative of protons accelerated to GeV energies. Almost all GLE events are associated with sustained gamma-ray emission (SGRE) from the Sun because the latter require >300 MeV protons that are readily present during GLEs. Here we report on the 2024 June 8 GLE event, which has the distinction of not being associated with an SGRE event. All the associated phenomena typical of SGRE events were present: a fast and wide CME, a major solar flare, and an intense type II radio bursts that extend from the metric to kilometric wavelength domains. There was a data gap of ~51 min, but the SGRE is expected to last for hours. We suggest the east-west asymmetry in the flow of energetic particles from the shock is likely to be the reason for the lack of SGRE emission.

astro-ph.SR↗

arXiv2026

AgentCAT: An LLM Agent for Extracting and Analyzing Catalytic Reaction Data from Chemical Engineering Literature

This paper presents a large language model (LLM) agent named AgentCAT, which extracts and analyzes catalytic reaction data from chemical engineering papers, %and supports natural language based interactive analysis of the extracted data. AgentCAT serves as an alternative to overcome the long-standing data bottleneck in chemical engineering field, and its natural language based interactive data analysis functionality is friendly to the community. AgentCAT also presents a formal abstraction and challenge analysis of the catalytic reaction data extraction task in an artificial intelligence-friendly manner. This abstraction would help the artificial intelligence community understand this problem and in turn would attract more attention to address it. Technically, the complex catalytic process leads to complicated dependency structure in catalytic reaction data with respect to elementary reaction steps, molecular behaviors, measurement evidence, etc. This dependency structure makes it challenging to guarantee the correctness and completeness of data extraction, as well as representing them for analysis. AgentCAT addresses this challenge and it makes four folds of technical contributions: (1) a schema-governed extraction pipeline with progressive schema evolution, enabling robust data extraction from chemical engineering papers; (2) a dependency-aware reaction-network knowledge graph that links catalysts/active sites, synthesis-derived descriptors, mechanistic claims with evidence, and macroscopic outcomes, preserving process coupling and traceability; (3) a general querying module that supports natural-language exploration and visualization over the constructed graph for cross-paper analysis; (4) an evaluation on $\sim$800 peer-reviewed chemical engineering publications demonstrating the effectiveness of AgentCAT.

physics.chem-ph↗

arXiv2026

Demystifying Design Choices of Reinforcement Fine-tuning: A Batched Contextual Bandit Learning Perspective

The reinforcement fine-tuning area is undergoing an explosion papers largely on optimizing design choices. Though performance gains are often claimed, inconsistent conclusions also arise from time to time, making the progress illusive. Reflecting on this illusion, we still lack principled answers to two fundamental questions: 1) what is the role of each design choice? 2) which ones are critical? This paper aims to shed light on them. The underlying challenge is that design choices are entangled together, making their contribution to learning and generalization difficult to attribute. To address this challenge, we first construct a minimalist baseline for disentangling factors: one rollout per query in each round, the outcome reward serving as the training signal without any advantage trick, and a batch size of thirty-two. This baseline connects to batched contextual bandit learning, which facilitates experimental analysis. Centering around this baseline, we design an experiment pipeline, examining the marginal gains of factors like advantage, number of rollouts, etc. Experiments on three base models and two datasets, not only reveal new understanding on the role of various design choices on learning and generalization dynamics, but also identify critical ones that deserve more effort.

cs.LG↗

arXiv2026

Rethinking Reinforcement fine-tuning of LLMs: A Multi-armed Bandit Learning Perspective

A large number of heuristics have been proposed to optimize the reinforcement fine-tuning of LLMs. However, inconsistent claims are made from time to time, making this area elusive. Reflecting on this situation, two fundamental questions still lack a clear understanding: 1) what is the role of each optimizing choice? 2) which ones are the bottlenecks? This paper aims to shed light on them, and it faces the challenge of several entangled confounding factors in the fine-tuning process. To tackle this challenge, we propose a bottom-up experiment pipeline. The bottom layer is composed of a minimalist configuration: one training data, one rollout per round and the reward directly serve as the learning signal without advantage function design. This minimalist configuration connects to multi-armed bandit learning with extremely large discrete action space, which offers theories to corroborate the experiment findings. The up procedure of the experiment pipeline expanding the minimalist configuration layer by layer, examining the role of each design choice. Experimental results on three LLMs and two reasoning datasets not only reveal new understanding of the design choice but also yield essential insights to shape the area.

cs.LG↗

arXiv2025

Multiple-play Stochastic Bandits with Prioritized Arm Capacity Sharing

This paper proposes a variant of multiple-play stochastic bandits tailored to resource allocation problems arising from LLM applications, edge intelligence, etc. The model is composed of $M$ arms and $K$ plays. Each arm has a stochastic number of capacities, and each unit of capacity is associated with a reward function. Each play is associated with a priority weight. When multiple plays compete for the arm capacity, the arm capacity is allocated in a larger priority weight first manner. Instance independent and instance dependent regret lower bounds of $Ω( α_1 σ\sqrt{KM T} )$ and $Ω(α_1 σ^2 \frac{M}Δ \ln T)$ are proved, where $α_1$ is the largest priority weight and $σ$ characterizes the reward tail. When model parameters are given, we design an algorithm named \texttt{MSB-PRS-OffOpt} to locate the optimal play allocation policy with a computational complexity of $O(MK^3)$. Utilizing \texttt{MSB-PRS-OffOpt} as a subroutine, an approximate upper confidence bound (UCB) based algorithm is designed, which has instance independent and instance dependent regret upper bounds matching the corresponding lower bound up to factors of $ \sqrt{K \ln KT }$ and $α_1 K^2$ respectively. To this end, we address nontrivial technical challenges arising from optimizing and learning under a special nonlinear combinatorial utility function induced by the prioritized resource sharing mechanism.

cs.AI↗

arXiv2025

Revisiting Fairness-aware Interactive Recommendation: Item Lifecycle as a Control Knob

This paper revisits fairness-aware interactive recommendation (e.g., TikTok, KuaiShou) by introducing a novel control knob, i.e., the lifecycle of items. We make threefold contributions. First, we conduct a comprehensive empirical analysis and uncover that item lifecycles in short-video platforms follow a compressed three-phase pattern, i.e., rapid growth, transient stability, and sharp decay, which significantly deviates from the classical four-stage model (introduction, growth, maturity, decline). Second, we introduce LHRL, a lifecycle-aware hierarchical reinforcement learning framework that dynamically harmonizes fairness and accuracy by leveraging phase-specific exposure dynamics. LHRL consists of two key components: (1) PhaseFormer, a lightweight encoder combining STL decomposition and attention mechanisms for robust phase detection; (2) a two-level HRL agent, where the high-level policy imposes phase-aware fairness constraints, and the low-level policy optimizes immediate user engagement. This decoupled optimization allows for effective reconciliation between long-term equity and short-term utility. Third, experiments on multiple real-world interactive recommendation datasets demonstrate that LHRL significantly improves both fairness and user engagement. Furthermore, the integration of lifecycle-aware rewards into existing RL-based models consistently yields performance gains, highlighting the generalizability and practical value of our approach.

cs.AI↗

arXiv2025

A Unified Frequency Domain Decomposition Framework for Interpretable and Robust Time Series Forecasting

Current approaches for time series forecasting, whether in the time or frequency domain, predominantly use deep learning models based on linear layers or transformers. They often encode time series data in a black-box manner and rely on trial-and-error optimization solely based on forecasting performance, leading to limited interpretability and theoretical understanding. Furthermore, the dynamics in data distribution over time and frequency domains pose a critical challenge to accurate forecasting. We propose FIRE, a unified frequency domain decomposition framework that provides a mathematical abstraction for diverse types of time series, so as to achieve interpretable and robust time series forecasting. FIRE introduces several key innovations: (i) independent modeling of amplitude and phase components, (ii) adaptive learning of weights of frequency basis components, (iii) a targeted loss function, and (iv) a novel training paradigm for sparse data. Extensive experiments demonstrate that FIRE consistently outperforms state-of-the-art models on long-term forecasting benchmarks, achieving superior predictive performance and significantly enhancing interpretability of time series

cs.LG↗

arXiv2025

LLM Cache Bandit Revisited: Addressing Query Heterogeneity for Cost-Effective LLM Inference

This paper revisits the LLM cache bandit problem, with a special focus on addressing the query heterogeneity for cost-effective LLM inference. Previous works often assume uniform query sizes. Heterogeneous query sizes introduce a combinatorial structure for cache selection, making the cache replacement process more computationally and statistically challenging. We treat optimal cache selection as a knapsack problem and employ an accumulation-based strategy to effectively balance computational overhead and cache updates. In theoretical analysis, we prove that the regret of our algorithm achieves an $O(\sqrt{MNT})$ bound, improving the coefficient of $\sqrt{MN}$ compared to the $O(MN\sqrt{T})$ result in Berkeley, where $N$ is the total number of queries and $M$ is the cache size. Additionally, we also provide a problem-dependent bound, which was absent in previous works. The experiment rely on real-world data show that our algorithm reduces the total cost by approximately 12\%.

cs.CL↗

arXiv2025

Casual3DHDR: Deblurring High Dynamic Range 3D Gaussian Splatting from Casually Captured Videos

Photo-realistic novel view synthesis from multi-view images, such as neural radiance field (NeRF) and 3D Gaussian Splatting (3DGS), has gained significant attention for its superior performance. However, most existing methods rely on low dynamic range (LDR) images, limiting their ability to capture detailed scenes in high-contrast environments. While some prior works address high dynamic range (HDR) scene reconstruction, they typically require multi-view sharp images with varying exposure times captured at fixed camera positions, which is time-consuming and impractical. To make data acquisition more flexible, we propose \textbf{Casual3DHDR}, a robust one-stage method that reconstructs 3D HDR scenes from casually-captured auto-exposure (AE) videos, even under severe motion blur and unknown, varying exposure times. Our approach integrates a continuous-time camera trajectory into a unified physical imaging model, jointly optimizing exposure times, camera trajectory, and the camera response function (CRF). Extensive experiments on synthetic and real-world datasets demonstrate that \textbf{Casual3DHDR} outperforms existing methods in robustness and rendering quality. Our source code and dataset will be available at https://lingzhezhao.github.io/CasualHDRSplat/

cs.CV↗

arXiv2025

Multispacecraft Observations of the 2024 September 9 Backside Solar Eruption that Resulted in a Sustained Gamma Ray Emission Event

We report on the 2024 September 9 sustained gamma ray emission (SGRE) event observed by the Large Area Telescope (LAT) onboard the Fermi satellite. The event was associated with a backside solar eruption observed by multiple spacecraft such as the Solar and Heliospheric Observatory (SOHO), Solar Terrestrial Relations Observatory (STEREO), Parker Solar Probe (PSP), Solar Orbiter (SolO), Solar Dynamics Observatory (SDO), Wind, and GOES, and by ground based radio telescopes. Fermi LAT observed the SGRE after the EUV wave from the backside eruption crossed the limb to the frontside of the Sun. SolO's Spectrometer Telescope for Imaging X rays (STIX) imaged an intense (X3.3) flare, which occurred about 41 deg behind the east limb, from heliographic coordinates S13E131. Forward modeling of the CME flux rope revealed that it impulsively accelerated (3.54 km/s/s) to attain a peak speed of 2162 km/s. SolO's energetic particle detectors (EPD) observed protons up to about 1 GeV from the extended shock and electrons that produced a complex type II burst and possibly type III bursts. The durations of SGRE and type II burst are consistent with the linear relation between these quantities obtained from longer duration (>3 hours) SGRE events. All these observations are consistent with an extended shock surrounding the CME flux rope, which is the likely source of high energy protons required for the SGRE event. We compare this event with six other BTL SGRE eruptions and find that they are all consistent with energetic shock driving CMEs. We also find a significant east west asymmetry (3:1) in the BTL source locations.

astro-ph.SR↗

arXiv2025

M$^2$-MFP: A Multi-Scale and Multi-Level Memory Failure Prediction Framework for Reliable Cloud Infrastructure

As cloud services become increasingly integral to modern IT infrastructure, ensuring hardware reliability is essential to sustain high-quality service. Memory failures pose a significant threat to overall system stability, making accurate failure prediction through the analysis of memory error logs (i.e., Correctable Errors) imperative. Existing memory failure prediction approaches have notable limitations: rule-based expert models suffer from limited generalizability and low recall rates, while automated feature extraction methods exhibit suboptimal performance. To address these limitations, we propose M$^2$-MFP: a Multi-scale and hierarchical memory failure prediction framework designed to enhance the reliability and availability of cloud infrastructure. M$^2$-MFP converts Correctable Errors (CEs) into multi-level binary matrix representations and introduces a Binary Spatial Feature Extractor (BSFE) to automatically extract high-order features at both DIMM-level and bit-level. Building upon the BSFE outputs, we develop a dual-path temporal modeling architecture: 1) a time-patch module that aggregates multi-level features within observation windows, and 2) a time-point module that employs interpretable rule-generation trees trained on bit-level patterns. Experiments on both benchmark datasets and real-world deployment show the superiority of M$^2$-MFP as it outperforms existing state-of-the-art methods by significant margins. Code and data are available at this repository: https://github.com/hwcloud-RAS/M2-MFP.

cs.DC↗