arXiv subjects

Haotian Liu

Publications and source records attributed to Haotian Liu.

At least 19 recordsLinked to original sources

arXiv2026

Toward Generalized LEO Channel Prediction: A Rapid Adaptation Time-Frequency Mamba Framework

Accurate channel state information (CSI) prediction is pivotal for enhancing system capacity in low Earth orbit (LEO) satellite-terrestrial communications within the sixth-generation vision of global ubiquitous connectivity. However, the extreme mobility of LEO satellites, coupled with significant propagation delays, induces severe channel aging. Existing deep learning (DL) methods often struggle with non-stationary dynamics or generalize poorly across diverse global geographies. To address these challenges, we design the Evo-TFMamba, which is an evolutionary framework integrating time-frequency selective Mamba blocks with meta-learning for generalized CSI prediction. Experimental results demonstrate that the proposed Evo-TFMamba performs adaptive prediction according to the geographic coverage of LEO satellites. Meanwhile, it significantly enhances the model's generalization ability, particularly when faced with unseen channel environments in LEO satellite communication.

eess.SP↗

arXiv2026

ORCA: Onboard Reflective Collaborative Agents for Reliable Task Offloading in LEO Satellite Networks

Low Earth orbit (LEO) satellites increasingly perform time-critical onboard processing, yet heterogeneous computing capabilities, rapidly changing inter-satellite links (ISLs) and uncertain neighbor behavior make decentralized task offloading difficult under partial observations. This paper presents ORCA, an architecture of Onboard Reflective Collaborative Agents for autonomous onboard task offloading. ORCA organizes offloading decisions into a four-Agent \emph{Perceive}$\rightarrow$\emph{Reason}$\rightarrow$ \emph{Act}$\rightarrow$\emph{Learn} loop. It aims to improve efficiency and reliability in dynamic, heterogeneous, and unreliable LEO satellite networks. The simulation results of a heterogeneous 60-satellite Walker-delta constellation demonstrates that ORCA delivers competitive system efficiency in cooperative settings while achieving superior task-success robustness and offloading reliability under previously unseen malicious node behavior, indicating that outcome-grounded reflection can improve the reliability of decentralized onboard offloading without centralized runtime coordination.

eess.SP↗

arXiv2026

PhyPro-FM: A Physics and Prompt-Guided Graph Foundation Model for Contingency Analysis

The continuous evolution of next-generation power systems, characterized by the high penetration of renewable energy resources and dynamic topology variations, poses formidable challenges to traditional N-1/N-2 contingency analysis in terms of computational efficiency and scalability. While deep learning-based methods offer accelerated inference, existing studies predominantly treat contingency analysis as a pure regression problem, often overlooking the physical essence of grid operation and engineering requirements of real-world scenarios. To bridge this gap, this paper proposes a physics and prompt-guided graph foundation model (PhyPro-FM) for generalizable and engineering-viable contingency analysis. The proposed architecture integrates graph neural networks with a learnable global query mechanism and, notably, introduces a prompt-guided learning paradigm. By leveraging historical snapshots as few-shot prompts, the model dynamically captures correlations between target and historical operating conditions, significantly enhancing generalization capabilities under unseen topologies. Furthermore, we design a physics-informed training mechanism that prioritizes branch power flow errors over nodal voltage errors, aligning the optimization objective with critical grid security constraints. To ensure engineering applicability, a physics-informed inference mechanism is also developed, incorporating a residual-based correction module and a specialized post-processing strategy for singular branches to circumvent numerical instability. Comprehensive experiments demonstrate that PhyPro-FM outperforms state-of-the-art methods in accuracy and generalization, validating its superior physical consistency and robustness for practical engineering applications.

eess.SY↗

arXiv2026

Beyond Answer Voting: Fine-Grained Correction of LLM Reasoning through Graph Alignment across Sampled Traces

Large language models increasingly tackle tasks that require multi-step reasoning, where errors in intermediate claims can affect the final answer. Self-consistency (SC) improves reasoning by voting over sampled final answers, but its vote leaves intermediate disagreements unresolved. To address this problem, we introduce DDRG (Disagreement-Driven Verification Guided by Reasoning Graphs), a framework for selective correction from a frozen bank of reasoning traces. Our insight is that graph alignment can expose claim-level disagreements and provide correction evidence without expanding the sampled trace bank. DDRG builds source-grounded claim graphs and sends localized conflicts to an answer-blind verifier. A verifier-supported refutation that reaches the majority answer's supporting path triggers one focused repair; otherwise, DDRG returns the exact SC vote. Experimental results across five benchmarks show that native zero-shot DDRG improves macro-average accuracy over direct answering by 8.65 and 15.83 percentage points for Qwen2.5-7B and Llama3.1-8B. It also exceeds CoT, the evaluated GoT and GoV question-answering adaptations, and SC on this macro metric. DDRG links local verification to selective correction without enlarging the initial candidate bank.

cs.AI↗

arXiv2026

Three Stages of ISAC Signal Design: Principles, Methods and Standardization

Emerging scenarios, including low-altitude economy and intelligent transportation, require ultra-reliable communi- cation and high-precision sensing, making integrated sensing and communication (ISAC) a key enabler for sixth-generation (6G) networks. The ISAC signal serves as the carrier for both communication and sensing, and its design directly affects the overall performance of ISAC system. This article presents a progressive roadmap of ISAC signal design. First, we establish a multi-dimensional performance metric framework of ISAC signal covering communication, sensing, and radio-frequency (RF) performance. Second, we introduce a three-stage ISAC signal design paradigm, namely UNLEASH POTENTIAL, EXPAND DIMENSIONS, and DEEPEN COLLABORATION. This paradigm progresses from the exploitation of existing signals, through the design of new waveform bases and multi-dimensional signal structures, to the ISAC signal design with multi-node cooperation. Finally, we propose a corresponding standardization roadmap that evolves from compatibility with existing communication sys- tems toward native and cooperation-enabled ISAC. The resulting framework provides practical guidance for ISAC signal design and the standard evolution toward 6G.

eess.SP↗

arXiv2026

FLY-EVAL++: An Evidence-Driven Evaluation Protocol for Safety-Constrained Flight Prediction with Large Language Models

Evaluating large language models (LLMs) in safety-critical, physics-governed environments requires more than accuracy-based metrics, because predictions that are numerically close to the ground truth can still violate operational constraints, combine fields in physically inconsistent ways, or fail to produce usable structured outputs. Existing evaluation protocols do not measure these failure modes reliably. We propose FLY-EVAL++, an evidence-driven evaluation protocol that combines deterministic verification of protocol compliance, physical feasibility, and safety constraints with fixed rubric-guided aggregation into interpretable multi-dimensional scores. We instantiate FLY-EVAL++ for Flight Trajectory and Attitude Prediction (FTAP) by extending the PilotBench setting with history-conditioned and multi-step prediction tasks. Across 66 LLMs, safety compliance is the most discriminative dimension of model behavior: models with comparable predictive performance differ by more than 28 points in safety score, and we observe recurrent failures including safety violations under physically plausible predictions and instability in multi-step rollouts. These results show that evaluation in safety-critical domains should measure constraint satisfaction and structured validity explicitly rather than rely on accuracy-centric reporting alone.

cs.AI↗

arXiv2026

One Request, Multiple Experts: LLM Orchestrates Domain Specific Models via Adaptive Task Routing

With the integration of massive distributed energy resources and the widespread participation of novel market entities, the operation of active distribution networks (ADNs) is progressively evolving into a complex, multi-scenario, and multi-objective problem. Although expert engineers have developed numerous domain specific models (DSMs) to address distinct technical problems, mastering, integrating, and orchestrating these heterogeneous DSMs still entail considerable overhead for ADN operators. Therefore, an intelligent approach is urgently required to unify these DSMs and enable efficient coordination. To address this challenge, this paper proposes the ADN-Agent architecture, which leverages a general large language model (LLM) to coordinate multiple DSMs, enabling adaptive intent recognition, task decomposition, and DSM invocation. Within the ADN-Agent, we design a novel communication mechanism that provides a unified and flexible interface for diverse heterogeneous DSMs. Finally, for specific language-intensive subtasks, we propose an automated training pipeline for fine-tuning small language models, thereby effectively enhancing the overall problem-solving capability of the system. Comprehensive comparisons and ablation experiments validate the efficacy of the proposed method and demonstrate that the ADN-Agent architecture outperforms existing LLM application paradigms.

eess.SY↗

arXiv2026

LLMs are Few-Shot Decision-Makers: Generalized Context-Aware Microgrid Frequency Control through Prompt Decision Transformer

The rapid evolution of energy structures has positioned microgrids as pivotal components of next-generation power systems, offering enhanced resilience and renewable energy integration. However, the inherent low inertia, complex dynamics, and poor model conditions of microgrids necessitate advanced data-driven frequency control strategies. Although reinforcement learning (RL) has demonstrated certain potential and advantages, existing RL methods often struggle with generalization across diverse microgrid configurations and lack adaptability to unseen environments, particularly when explicit system parameters are unavailable. To address these challenges, in this paper, we introduce a novel prompt decision transformer (Prompt-DT) architecture for microgrid frequency control. Unlike traditional approaches that rely on hard-to-obtain environmental characteristic parameters, the proposed method leverages few-shot expert historical trajectories as prompts to guide autonomous perception and adaptive decision-making. In addition, we propose a context-aware training and execution mechanism utilizing self-supervised contrastive learning to enhance environment recognition and prompt utilization efficiency. In addition, a physics-informed prompt design technique that filters prompts based on cumulative reward and frequency volatility is proposed, ensuring high-quality physical guidance during online execution. Finally, to ensure generalization in unseen environments with limited data, we develop a lightweight finetuning approach that achieves performance comparable to full-parameter finetuning with minimal adjustments.

eess.SY↗

arXiv2026

Learning Unified Video and Image Representation for Video Face Forgery Detection

Face forgery detection is crucial for preserving the security and integrity of facial data given the rapid developments in face manipulation techniques and deep generative models. Existing methods for video face forgery detection typically assume that all frames in a forged video are manipulated, while detecting partially forged videos that contain only a subset of altered frames remains challenging. To address this issue, we propose a novel framework, UVIF, that utilizes additional annotated images to provide fine-grained supervision for detecting partial forgeries in videos. UVIF employs a unified encoder and a multi-task learning paradigm to jointly model facial videos and images for boosted video face forgery detection. A 2D backbone with temporal fusion modules is employed as the unified encoder. A pseudo labeling process is designed for video frames to bridge their representations with those of static images. A video-oriented feature alignment strategy is further introduced to reduce the distribution gap between videos and images. Extensive experiments on benchmark datasets demonstrate the effectiveness of our framework, which outperforms state-of-theart methods in detecting partially forged videos while introducing no additional computational overhead. Our code is available at https://github.com/haotianll/UVIF.

cs.CV↗

arXiv2026

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills

LLM training is shifting from manual design and annotation to interaction-driven self-evolution. However, existing self-evolutionary methods face a fundamental dilemma between task diversity and verification reliability: environment-bound methods obtain precise feedback but confine learning to narrow domains, while open-ended self-generation broadens the task space but lacks reliable verification, allowing misleading rewards to pollute the training loop. We identify agent skills as a powerful middle ground to reconcile this tension: each skill ensures deep, verifiable execution in a specific scenario, while dynamic routing across skills maintains open-ended task variety. Leveraging this insight, we introduce Skill Self-Play (Skill-SP), a co-evolutionary framework comprising a proposer, a solver, and a dynamic skill controller. Orchestrated via a reinforcement learning loop, these components co-evolve in a continuous self-play loop: the proposer generates challenging tasks conditioned on dynamically sampled skills; the solver explores candidate solutions to push its capability boundaries; and the skill controller collects execution feedback to update and expand the skill library. This interactive co-evolution effectively bridges the gap between structured verification and open-ended exploration. Empirical evaluations on tool-use and reasoning benchmarks demonstrate that Skill-SP, serving as a robust evolution engine, consistently pushes the performance ceiling of competent backbones while catalyzing striking turnarounds for initially misaligned models. Our code is available at https://github.com/Qwen-Applications/skill-self-play.

cs.CL↗

arXiv2026

DMSNet: Cross-Band Learning for Multi-Target Sensing in Multi-Band ISAC

Multi-band integrated sensing and communication (ISAC) offers complementary high- and low-frequency echo information for multi-target sensing. However, existing dual-band ISAC sensing methods have a limited ability to exploit deep complementary information across heterogeneous bands and often incur high computational costs. To address these limitations, we propose a Dual-Band Multi-Target Sensing Neural Network (DMSNet) for joint target number and parameter estimation. Under representative simulation conditions, DMSNet outperforms the best baseline in target number estimation, increasing count accuracy from 89.01 % to 91.74 % and Macro-F1 from 90.80 % to 93.07 %. For parameter estimation, compared with the best baselines, DMSNet reduces the median absolute errors of range, velocity, and angle by 82.2%, 56.9%, and 73.2%, respectively. Moreover, DMSNet reduces runtime by 68.7 % relative to the fastest existing dual-band ISAC sensing method.

eess.SP↗

arXiv2026

Efficient and Effective In-place Graph-based Vector Index Updates

In the era of Large Language Models (LLMs), efficient vector updates are critical for capturing real-time information from rapidly evolving data. However, it is not trivial to process frequent vector insert and delete updates and maintain a high recall of the search results simultaneously. Specifically, the cluster-based vector indexing methods have high update throughput but low search result quality. Existing out-of-place graph-based vector indexing update approaches suffer from poor update throughput due to the need to periodically merge update batches into the underlying graph index. Building a vector data system that supports efficient and effective in-place updates is inherently challenging. In this work, we propose Yi to achieve it. In particular, Yi supports in-place graph-based vector indexing updates with consistently high update throughput and good search result quality. The key idea of Yi is decomposition facilitates consolidation. In particular, we introduce a vector-level update mechanism and architect Yi with three core components: (i) a tasklet-based execution engine, (ii) an asynchronous buffer manager, and (iii) a vector file system. Experimental results demonstrate that Yi achieves 1.75x higher update throughput and 1.8x higher concurrent search throughput than the state-of-the-art systems on the 800M dataset, while using only 73% of the peak memory and fewer CPU cores.

cs.DB↗

arXiv2026

Pix2Act: Image-Space Manipulation Policies with Equivariant Augmentation

Representing manipulation actions as 2D trajectories in the camera plane provides a compact and interpretable basis for learning complex 3D manipulation policies. However, it also creates challenges from out-of-frame trajectories and limited precision. We propose Pix2Act, an imitation learning method that addresses these challenges by generating continuous image-space keypoint trajectories in each camera plane and losslessly recovering end-effector poses via triangulation. This reformulates high-dimensional 3D control as a simpler, more learnable 2D prediction problem. Crucially, it aligns observations and actions in the same coordinate space, enabling equivariant transformations to jointly rotate individual camera images together with their image-space actions. We analyze the symmetry properties of this augmentation and design a network architecture that can fuse multiple camera views while respecting their per-view rotations. As a result, Pix2Act implicitly enlarges the support of the data distribution and learns invariant action structures across transformations, yielding improved generalization and overall performance. Across diverse simulated and real-world manipulation tasks, Pix2Act outperforms state-of-the-art baselines and remains robust under camera perturbations.

cs.RO↗

arXiv2026

AlayaLaser: Efficient Index Layout and Search Strategy for Large-scale High-dimensional Vector Similarity Search

On-disk graph-based approximate nearest neighbor search (ANNS) is essential for large-scale, high-dimensional vector retrieval, yet its performance is widely recognized to be limited by the prohibitive I/O costs. Interestingly, we observed that the performance of on-disk graph-based index systems is compute-bound, not I/O-bound, with the rising of the vector data dimensionality (e.g., hundreds or thousands). This insight uncovers a significant optimization opportunity: existing on-disk graph-based index systems universally target I/O reduction and largely overlook computational overhead, which leaves a substantial performance improvement space. In this work, we propose AlayaLaser, an efficient on-disk graph-based index system for large-scale high-dimensional vector similarity search. In particular, we first conduct performance analysis on existing on-disk graph-based index systems via the adapted roofline model, then we devise a novel on-disk data layout in AlayaLaser to effectively alleviate the compute-bound, which is revealed by the above roofline model analysis, by exploiting SIMD instructions on modern CPUs. We next design a suite of optimization techniques (e.g., degree-based node cache, cluster-based entry point selection, and early dispatch strategy) to further improve the performance of AlayaLaser. We last conduct extensive experimental studies on a wide range of large-scale high-dimensional vector datasets to verify the superiority of AlayaLaser. Specifically, AlayaLaser not only surpasses existing on-disk graph-based index systems but also matches or even exceeds the performance of in-memory index systems.

cs.DB↗

arXiv2026

Beyond Single-Band: Analysis and Resource Allocation for Multi-band ISAC Systems

Integrated sensing and communication (ISAC) has emerged as a pivotal technology for sixth-generation wireless networks to empower high-precision sensing. The demand for superior sensing resolution and the reality of spectrum fragmentation have driven the research of multi-band ISAC. Multi-band ISAC provides frequency diversity through independent observations across disparate bands, mitigating sensing performance fluctuations caused by frequency-selective radar cross-section compared to single-band counterparts. In this paper, we propose a framework for analytical performance characterization and resource optimization in multi-band ISAC systems. Specifically, analytical closed-form detection and false alarm probabilities for multi-band OFDM signals are derived, providing a theoretical foundation for subsequent resource allocation. Then, a joint power and time-frequency resource allocation scheme is developed and solved via a proposed ADMM-based algorithm to maximize detection performance. Numerical results validate the accuracy of the closed-form derivations and demonstrate the superior robustness of multi-band signals. Notably, the proposed optimization scheme achieves an 18 dB detection gain over traditional single-band baselines at a 90\% detection probability.

eess.SP↗

arXiv2026

Toward Deeper Environmental Understanding: Event-Level Sensing for Intelligent 6G ISAC

The intelligent evolution of mission-critical networks, such as the Internet of vehicles (IoV) and the low-altitude economy (LAE), requires sixth-generation (6G) networks to move beyond discrete physical parameter estimation toward deeper environmental understanding. However, existing integrated sensing and communications (ISAC) studies mainly focus on target-level sensing, which provides fragmented snapshots of the physical world and lacks the behavioral semantic capability to interpret intent. This limitation hinders the intelligent evolution of such networks and prevents 6G from acquiring the essential sensing foundation to evolve into an "intelligent service engine". To bridge this gap, ISAC must advance toward event-level sensing, which models continuous-time states to enable persistent recognition and prediction of target intent and behavioral semantics. This article presents a comprehensive overview of event-level sensing in 6G ISAC networks. We first introduce its fundamental concepts, sensing types, and representative scenarios. We then review key enabling techniques across waveform design, target state estimation and tracking, and event recognition. Furthermore, focusing on IoV and LAE scenarios, we discuss representative applications of ISAC event-level sensing and the intelligent enhancement of downstream operational functions enabled by event-level information. Finally, we highlight future research trends and potential directions to further advance ISAC event-level sensing toward intelligent and proactive 6G networks.

eess.SP↗

arXiv2026

GD$^2$PO: Mitigating Multi-Reward Conflicts via Group-Dynamic reward-Decoupled Policy Optimization

As LLMs advance, post-training reinforcement learning (RL) increasingly relies on multi-dimensional rewards to cultivate comprehensive capabilities. This shift demands new algorithms capable of optimizing diverse and potentially competing objectives simultaneously. To address this, existing methods such as Group reward-Decoupled Policy Optimization (GDPO) decompose the overall score into independent reward groups, then compute the RL loss separately within each group. However, this strategy still encounters multi-reward conflicts: a single rollout can yield positive advantages on certain reward dimensions but negative ones on others, causing opposing signals to cancel each other out during aggregation, further hindering RL training efficiency. Inspired by Dynamic sAmpling Policy Optimization (DAPO), which improves RL training efficiency by filtering out ineffective rollouts with near-zero advantages, we propose Group-Dynamic reward-Decoupled Policy Optimization (GD$^2$PO). Specifically, GD$^2$PO employs a conflict-aware filtering mechanism to mask out rollouts suffering from severe reward-wise disagreement. By preventing conflicting signals from canceling each other out, this masking strategy preserves and enhances the magnitude of effective RL advantages, thereby significantly accelerating learning efficiency. Furthermore, we introduce query-level reweighting to dynamically adjust the update intensity of each query based on its overall reward consensus. Experiments on various multi-reward scenarios, including tool calling and human preference alignment, demonstrate that GD$^2$PO consistently and significantly outperforms existing baselines. The code is available at https://github.com/Qwen-Applications/GD2PO.

cs.LG↗

arXiv2026

CutVerse: A Compositional GUI Agents Benchmark for Media Post-Production Editing

While GUI agents have made significant progress in web navigation and basic operating system tasks, their capabilities in professional creative workflows remain largely underexplored. To bridge this gap, we introduce Cutverse, a benchmark designed to systematically evaluate autonomous GUI agents in realistic media post-production environments. We curate expert demonstrations across 7 professional applications (e.g., Premiere Pro, Photoshop), covering 186 complex, long-horizon tasks grounded in authentic editing workflows, involving dense multimodal interfaces and tightly coupled interaction sequences. To support scalable evaluation, we develop a lightweight parser that transforms raw screen recordings and low-level interaction logs into structured, compositional GUI action trajectories with precise grounding. Extensive evaluations reveal that existing agents achieve only 36.0\% task success on realistic media editing tasks, underscoring the challenges posed by complex, long-horizon media post-production workflows in our benchmark.While current models demonstrate promising spatial grounding, multimodal alignment, and coordinated action execution, they remain limited in long-horizon reliability and domain-specific planning.

cs.CV↗