arXiv subjects

Tianhao Liang

Publications and source records attributed to Tianhao Liang.

At least 19 recordsLinked to original sources

arXiv2026

Intern-S2-Preview: Scientific Agentic Foundation Model

Scientific discovery increasingly requires AI systems that can reason over scientific evidence of heterogeneous modalities, interact with scientific tools and environments, and sustain progress across long task horizons. We present Intern-S2-Preview, a series of scientific agentic foundation models designed to support multimodal scientific understanding, reasoning, generation, and long-horizon tasks. The training pipeline begins with scientific multimodal pre-training over rendered scientific documents, interleaved image-text data, and diverse scientific corpora. Starting from the pretrained checkpoint, we apply a unified post-training pipeline consisting of supervised fine-tuning, scalable multi-task reinforcement learning (RL), black- and white-box agentic RL, and on-policy distillation. This pipeline is supported by practical techniques that improve rollout and training stability and efficiency, including partial rollout with off-policy correction, adaptive length regularization, online speculative decoding, robust multi-task optimization, and trace-aware experience assembly for agentic tasks. At the architecture level, Intern-S2-Preview-397B extends time series modelling from efficient long-sequence understanding to numerical forecasting, while Memory Decoder is studied as a separate memory-augmented path for rapid scientific specialization without modifying the frozen 397B backbone. Evaluations across scientific, multimodal, agentic, and general-purpose benchmarks show that Intern-S2-Preview-397B achieves competitive or leading results in multiple settings. The time series modules improve scientific signal understanding and forecasting on SciTS, while the separate Intern-MemDec-4B extension improves the Biology-Instructions average score from 56.92 to 60.32 without modifying the frozen 397B backbone.

cs.LG↗

arXiv2026

Media Meets Communication in 6G: Fundamentals, Key Technologies, and Applications

The rapid advancement of sixth-generation (6G) networks is accelerating the convergence of media intelligence and communication intelligence, driving media communication beyond conventional bit-level delivery toward intelligent, semantic-aware, and generative paradigms. Emerging media services require not only high data rates and low latency, but also semantic awareness, perceptual quality assurance, adaptive resource orchestration, trustworthy content processing, and personalized media generation. Meanwhile, media technologies are evolving from handcrafted signal processing and conventional coding toward artificial intelligence (AI)-driven representation learning, content understanding, and generative reconstruction. Motivated by these trends, this paper presents a systematic survey of media communication technologies for 6G vision communication by revisiting the evolution of communication and media technologies and clarifying the intrinsic relationship between media content processing and wireless transmission. We introduce a unified framework consisting of four key dimensions: AI-driven media technologies, media-aware wireless transmission, large model-enabled media communication, and intelligent network infrastructures. Specifically, AI-driven media technologies encompass media coding, content understanding, quality assessment, security and compliance detection, and AIGC-enabled media generation, while media-aware wireless transmission is examined from three complementary perspectives: semantic joint source-channel optimization, which jointly encodes task-relevant semantic information; source-aware transmission optimization, which leverages media characteristics for channel adaptation, prediction, and compensation; and channel-aware source optimization, which adapts media coding and reconstruction based on real-time channel conditions.

cs.IT↗

arXiv2026

AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities

As Large Language Models (LLMs) evolve into autonomous agents, the need for unified evaluation infrastructure becomes critical. However, current evaluation pipelines remain highly fragmented and tightly coupled, hindering reproducibility and causing redundant engineering. To address this, we introduce AgentCompass, an open-source, lightweight, and extensible infrastructure for evaluating LLM-based agents. AgentCompass organizes the evaluation process around three independent components, namely Benchmark, Harness, and Environment, thereby enabling flexible configurations without requiring the reimplementation of complex execution logic. Furthermore, it features a fault-tolerant asynchronous runtime and comprehensive trajectory analysis tools to transparently diagnose nuanced failure modes like reward-hacking. Natively supporting over 20 benchmarks across five capability dimensions, AgentCompass provides the community with a scalable and reproducible infrastructure for advancing agent research.

cs.AI↗

arXiv2026

Impact of Residual Angular Chirp in a Petawatt-class Laser System on Laser-driven Proton Acceleration

Laser-driven proton acceleration has attracted considerable interest owing to its appealing potential in versatile applications including cancer therapy. Proton energies depend critically on the on-target intensities, yet the detrimental impact of focal spot degradation induced by spatiotemporal couplings on the acceleration remains insufficiently elucidated. In this study, we demonstrate that residual angular chirp (AC), stemming from minor misalignments of the grating compressor in a Petawatt-class laser system, acts as a critical bottleneck for proton acceleration. Experimental results reveal that even around 100 microradians of grating misalignment induces substantial focal-spot elongation and a pronounced reduction in peak intensity. By implementing an in situ spectral-blocking diagnostic, we effectively eliminated the residual AC and restored a near-diffraction-limited focus. This optimization led to a significant recovery of the on-target intensity, resulting in a twofold increase in the proton cutoff energy. Our work presents a successful demonstration of diagnosing and eliminating residual AC. This provides a practical reference for generating high-energy proton beams and supporting their diverse applications in a PW-class laser.

physics.plasm-ph↗

arXiv2026

Towards Effcient Low Altitude Sensing: A Dual Heterogeneous Graph Learning Method for UAV Task Allocation

With the development of low altitude intelligent systems, multiple unmanned aerial vehicles (UAVs) can collaboratively execute more complex tasks. Conventional task allocation methods usually regard tasks and UAVs as isolated entities, making it difficult to capture task dependencies and UAV communication relationships. To address this issue, this paper proposes a dual heterogeneous graph learning based UAV task allocation method. A directed task graph is constructed to represent task dependencies and encode task resource requirements, while an undirected UAV communication graph is built to model communication relationships and encode UAV resource states. The task allocation problem is formulated as a structural matching problem between the task graph and the UAV communication graph. A graph attention network based feature extraction method is introduced to learn structural representations from both graphs through message passing. A cross attention mechanism is further integrated with proximal policy optimization to optimize the matching between task nodes and UAV nodes for task allocation. Simulation results demonstrate that the proposed method achieves a higher task completion rate and shorter task completion time than benchmark methods under different evaluation settings. Furthermore, a UAV sensing and computing application is developed on the AirSim simulation platform. A large language model is employed to convert natural language task requirements into a structured task graph for autonomous UAV task execution, demonstrating the potential of the proposed framework for natural language driven UAV mission planning and execution.

eess.SY↗

arXiv2026

Handover-Aware Trajectory Planning for Cellular-Connected UAVs under STL Specifications and URLLC Constraints

This paper investigates handover-aware trajectory planning for cellular-connected UAVs executing mission-centric tasks under ultra-reliable low-latency communication (URLLC) constraints. Signal temporal logic (STL) provides a formal specification layer for translating mission semantics into time-bounded trajectory requirements, while finite-blocklength URLLC feasibility characterizes reliable command-and-control (C2) links with serving base stations (BSs). We formulate a joint planning problem that optimizes the UAV trajectory, STL mission satisfaction, serving-BS association, and handover behavior. To solve this mixed discrete-continuous problem, we adopt and integrate a Logic Network Flow (LNF) based STL reformulation with B\'ezier-parameterized motion, disk-shaped URLLC service regions, and binary association variables, so that the resulting mixed-integer quadratically constrained formulation can be solved by standard branch-and-bound solvers. Numerical simulations over a library of STL missions show that the proposed planner can execute different mission specifications under the same cellular map while maintaining URLLC feasibility. The results further reveal how mission timing, handover-aware association, and finite-blocklength stringency jointly affect trajectory shape, serving margin, and computational complexity.

eess.SY↗

arXiv2026

Large Language Model-Enhanced Multi-hop Parallel Image Semantic Communication

This paper proposes a large language model-enhanced multi-hop parallel image semantic communication (LLM-MHPSC) framework to mitigate distortion accumulation in multi-hop wireless image transmission. Unlike conventional single-hop semantic communication schemes, LLM-MHPSC deploys an extra residual compensation link at each hop to counteract accumulated distortions. To minimize additional bandwidth overhead, a coarse-to-fine residual compression scheme is designed by integrating a deep learning-based compressor with adaptive arithmetic coding (AAC). Furthermore, a large language model-based residual transmission optimizer (LLM-RTO) is developed to accurately estimate residual distributions and enable channel state and hop-aware rate adjustment, thereby improving residual compression efficiency under varying channel and hop conditions. An adaptive hop selection strategy is also proposed to activate the residual link on demand, striking a balance between transmission performance and computational cost. Experimental results show that LLM-MHPSC outperforms state-of-the-art semantic communication and traditional schemes, realizing robust image transmission with a marginal increase in bandwidth. This framework provides a flexible and effective solution for extending semantic communication to practical multi-hop application scenarios.

eess.IV↗

arXiv2026

HotLoop Optimization of Petawatt Laser Focal Spot via a Twin-Focus Scheme

Achieving diffraction-limited focusing of high-power laser pulses to generate ultra-high intensities is crucial for developing compact laser-driven particle accelerators and exploring strong-field quantum electrodynamics. However, accurately diagnosing and optimizing the focal spots of petawatt (PW) laser pulses remains a significant challenge. In this work, we present an experimental methodology utilizing a twin-focus scheme to precisely characterize the intensity distribution and wavefront of focused PW femtosecond laser pulses, and employ it to elucidate their power-dependent evolution. Furthermore, we optimized the focal spots at full power via our in-situ wavefront correction method termed ``HotLoop', achieving a Strehl ratio of 0.80 for 1 PW laser pulses. Consequently, the cutoff proton energies in laser proton acceleration experiments were significantly enhanced. The success of this approach underscores the necessity of in-situ high-energy wavefront correction for ultra-high intensity laser-matter interactions.

physics.optics↗

arXiv2026

UAV Control and Communication Enabled Low-Altitude Economy: Challenges, Resilient Architecture and Co-design Strategies

The emerging low-altitude economy has catalyzed the large-scale deployment of unmanned aerial vehicles (UAVs), driving a paradigm shift in environment monitoring, logistics, and emergency response. However, operating within these environments presents notable challenges as pervasive coverage holes, unpredictable interference, and spectrum scarcity. To this end, this article present a communication and control co-design framework to enable a resilient architecture for cellular-connected UAVs. Specifically, we first characterize typical service applications and their stringent performance requirements, followed by a comprehensive analysis of the unique challenges. To bridge the gap between volatile wireless links and rigid flight stability, a three layered architecture is proposed, integrating pre-flight strategic planning, in-flight adaptive action, and system-level resource orchestration. Furthermore, we detail the key enabling technologies for communication and control co-design. Preliminary case studies are proposed to validate that the co-design framework significantly improve the resilience of cellular-connected UAV systems, providing a robust foundation for the evolution of intelligent low-altitude networks.

cs.NI↗

arXiv2026

LLM-Enabled Low-Altitude UAV Natural Language Navigation via Signal Temporal Logic Specification Translation and Repair

Natural language (NL) navigation for low-altitude unmanned aerial vehicles (UAVs) offers an intelligent and convenient solution for low-altitude aerial services by enabling an intuitive interface for non-expert operators. However, deploying this capability in urban environments necessitates the precise grounding of underspecified instructions into safety-critical, dynamically feasible motion plans subject to spatiotemporal constraints. To address this challenge, we propose a unified framework that translates NL instructions into Signal Temporal Logic (STL) specifications and subsequently synthesizes trajectories via mixed-integer linear programming (MILP). Specifically, to generate executable STL formulas from free-form NL, we develop a reasoning-enhanced large language model (LLM) leveraging chain-of-thought (CoT) supervision and group-relative policy optimization (GRPO), which ensures high syntactic validity and semantic consistency. Furthermore, to resolve infeasibilities induced by stringent logical or spatial requirements, we introduce a specification repair mechanism. This module combines MILP-based diagnosis with LLM-guided semantic reasoning to selectively relax task constraints while strictly enforcing safety guarantees. Extensive simulations and real-world flight experiments demonstrate that the proposed closed-loop framework significantly improves NL-to-STL translation robustness, enabling safe, interpretable, and adaptable UAV navigation in complex scenarios.

cs.RO↗

arXiv2026

LSAI: A Large Small AI Model Codesign Framework for Agentic Robot Scenarios

The development of Artificial Intelligence (AI) has enabled agentic robots an appealing paradigm for various applications, such as research and rescue in complex environment. In this context, the next wireless communication technology facilitates robot cooperation for efficient environment sensing and exploration. However, traditional AI solutions cannot always provide reasonable resource utilization decisions, which makes it challenging to achieve both accurate and low-latency research and rescue. To address this issue, we propose a, LSAI, a large small AI model codesign framework to achieve highly accurate and real-time robot cooperation with deep interaction between large AI model and small AI model. We first propose an attention-based model aggregation for LAI construction. It can assist agentic robots in accurately sensing physical environments. Next, we design an adaptive model splitting and update algorithm to enable the robots to perform accurate path planning for high-efficiency environment sensing with low energy consumption. Finally, we demonstrate the effectiveness of our proposed LSAI framework. The simulation results indicate that our solution achieves sensing accuracy of up to 20.4% while reducing sensing cooperation latency by an average of 17.9% compared to traditional AI solutions.

eess.SY↗

arXiv2026

Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation

Reinforcement learning (RL) has emerged as a promising paradigm for enhancing image editing and text-to-image (T2I) generation. However, current reward models, which act as critics during RL, often suffer from hallucinations and assign noisy scores, inherently misguiding the optimization process. In this paper, we present FIRM (Faithful Image Reward Modeling), a comprehensive framework that develops robust reward models to provide accurate and reliable guidance for faithful image generation and editing. First, we design tailored data curation pipelines to construct high-quality scoring datasets. Specifically, we evaluate editing using both execution and consistency, while generation is primarily assessed via instruction following. Using these pipelines, we collect the FIRM-Edit-370K and FIRM-Gen-293K datasets, and train specialized reward models (FIRM-Edit-8B and FIRM-Gen-8B) that accurately reflect these criteria. Second, we introduce FIRM-Bench, a comprehensive benchmark specifically designed for editing and generation critics. Evaluations demonstrate that our models achieve superior alignment with human judgment compared to existing metrics. Furthermore, to seamlessly integrate these critics into the RL pipeline, we formulate a novel "Base-and-Bonus" reward strategy that balances competing objectives: Consistency-Modulated Execution (CME) for editing and Quality-Modulated Alignment (QMA) for generation. Empowered by this framework, our resulting models FIRM-Qwen-Edit and FIRM-SD3.5 achieve substantial performance breakthroughs. Comprehensive experiments demonstrate that FIRM mitigates hallucinations, establishing a new standard for fidelity and instruction adherence over existing general models. All of our datasets, models, and code have been publicly available at https://firm-reward.github.io.

cs.CV↗

arXiv2025

Uncertainty-Aware 3D UAV Tracking Using Single-Anchor UWB Measurements

In this letter, we present an uncertainty-aware single-anchor Ultra-Wideband (UWB)-based 3D tracking framework. Specifically, a mobile Unmanned Aerial Vehicle (UAV) maintains a desired standoff distance to a moving target using range and 3D bearing measurements from a multi-antenna UWB anchor rigidly mounted on the UAV. To enhance the stability and safety under measurement degradation and motion uncertainty, we jointly design a robust factor-graph-based target localization method and a covariance-aware control Lyapunov function--control barrier function (CLF--CBF) tracking controller. This controller adaptively adjusts distance bounds and safety margins based on the posterior target covariance provided by the factor graph. The proposed system is evaluated through numerical simulations and real-world experiments carried out in a narrow indoor corridor environment.

eess.SY↗

arXiv2025

Handover-Aware URLLC UAV Trajectory Planning: A Continuous-Time Trajectory Optimization via Graphs of Convex Sets

In this paper, we study a cellular-connected unmanned aerial vehicle (UAV) which aims to fly between two predetermined locations while maintaining ultra-reliable low-latency communications (URLLC) for command-and-control (C2) links with terrestrial base stations (BSs). Long-range flights often trigger frequent inter-cell handovers, which may introduce delays and synchronization overhead. We jointly optimize the continuous trajectory and BS association to minimize handovers, path length, and flying time, subject to communication reliability and kinematic constraints. To address this problem, we reformulate it as an optimization based on the graph of convex sets (GCS). First, the URLLC requirement is translated into spatially feasible regions in the flight plane for each BS. And an intersection graph is constructed including the start and goal points. Each graph node is associated with a smooth and dynamically feasible trajectory segment. The trajectory is parameterized in space by Bézier curves and in time by a monotonic Bézier scaling, together with convex constraints that ensure continuity and enforce speed bounds. Next, we impose unit-flow constraints to enforce a single path, and by coupling the resulting binary edge-selection variables with the convex constraints, we obtain a mixed-integer convex program (MICP). Applying a convex relaxation and rounding to the mixed-integer convex program produces nearly globally optimal routes, and a final refinement yields smooth, dynamically feasible trajectories. Simulations verify that the method preserves URLLC connectivity while achieving a clear trade-off between fewer handovers and flight efficiency.

eess.SY↗

arXiv2025

MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization

While current Multimodal Large Language Models (MLLMs) have demonstrated proficiency in reasoning tasks such as mathematics and logic, their capacity for long-chain reflective reasoning, a prerequisite for solving complex real-world problems, remains largely underexplored. In this work, we first conduct an extensive empirical investigation to evaluate this capability. Leveraging a carefully designed data synthesis engine, we construct MM-HELIX, a multimodal benchmark consisting 1,260 samples of 42 challenging synthetic tasks that require iterative thinking and backtracking. Empirical results on this benchmark reveal that existing MLLMs exhibit significant performance deficits in long-chain reflective reasoning. To address this limitation, we generate post-training data and further explore learning paradigms for exploiting such data. We first develop the Step-Elicited Response Generation pipeline to create MM-HELIX-100K, a large-scale dataset of 100k high-quality, reflective reasoning traces for instruction-tuning stage. Given that standard Reinforcement Learning fails on complex tasks due to sparse reward signals and catastrophic forgetting after Supervised Fine-Tuning, we propose Adaptive Hybrid Policy Optimization (AHPO), a novel training strategy that dynamically unifies offline supervision and online optimization into a single stage. This strategy enables the model to learn from expert data when rewards are sparse and conduct independent exploration once proficient. When applied to the Qwen2.5-VL-7B baseline, our method achieves a +18.6\% accuracy improvement on MM-HELIX benchmark and demonstrates strong generalization with a +5.7\% average performance gain on general mathematic and logic tasks. Our work demonstrate that reflective reasoning in MLLMs can be effectively learned and generalized, paving the way for developing more capable MLLMs.

cs.CV↗

arXiv2025

Sensing, Detection and Localization for Low Altitude UAV: A RF-Based Framework via Multiple BSs Collaboration

The rapid growth of the low-altitude economy has resulted in a significant increase in the number of Low, slow, and small (LLS) unmanned aerial vehicles (UAVs), raising critical challenges for secure airspace management and reliable trajectory planning. To address this, this paper proposes a cooperative radio-frequency (RF) detection and localization framework that leverages existing cellular base stations. The proposed approach features a robust scheme for LSS target identification, integrating a cell averaging-constant false alarm rate (CA-CFAR) detector with a micro-Doppler signature (MDS) based recognition method. Multi-station measurements are fused through a grid-based probabilistic algorithm combined with clustering techniques, effectively mitigating ghost targets and improving localization accuracy in multi-UAV scenarios. Furthermore, the Cramer-Rao lower bound (CRLB) is derived as a performance benchmark and reinforcement learning (RL)-based optimization is employed to balance localization accuracy against station resource usage. Simulations demonstrate that increasing from one to multiple BSs reduces the positioning error to near the CRLB, while practical experiments further verify the framework's effectiveness. Furthermore, our RL-based optimization can find solutions that maintain high accuracy while minimizing resource usage, highlighting its potential as a scalable solution for ensuring airspace safety in the emerging low-altitude economy.

eess.SY↗

arXiv2025

Enhancing Low-Altitude Airspace Security: MLLM-Enabled UAV Intent Recognition

The rapid development of the low-altitude economy emphasizes the critical need for effective perception and intent recognition of non-cooperative unmanned aerial vehicles (UAVs). The advanced generative reasoning capabilities of multimodal large language models (MLLMs) present a promising approach in such tasks. In this paper, we focus on the combination of UAV intent recognition and the MLLMs. Specifically, we first present an MLLM-enabled UAV intent recognition architecture, where the multimodal perception system is utilized to obtain real-time payload and motion information of UAVs, generating structured input information, and MLLM outputs intent recognition results by incorporating environmental information, prior knowledge, and tactical preferences. Subsequently, we review the related work and demonstrate their progress within the proposed architecture. Then, a use case for low-altitude confrontation is conducted to demonstrate the feasibility of our architecture and offer valuable insights for practical system design. Finally, the future challenges are discussed, followed by corresponding strategic recommendations for further applications.

eess.SY↗

arXiv2025

Relative Localization of UAV Swarms in GNSS-Denied Conditions

Relative localization of unmanned aerial vehicle (UAV) swarms in global navigation satellite system (GNSS) denied environments is essential for emergency rescue and battlefield reconnaissance. Existing methods suffer from significant localization errors among UAVs due to packet loss and high computational complexity in large swarms. This paper proposes a clustering-based framework where the UAVs simultaneously use communication signals for channel estimation and ranging. Firstly, the spectral clustering is utilized to divide the UAV swarm into different sub-clusters, where matrix completion and multidimensional scaling yield high-precision relative coordinates. Subsequently, a global map is created by the inter-cluster anchor fusion. A case study of UAV integrated communication and sensing (ISAC) system is presented, where the Orthogonal Time Frequency Space (OTFS) is adopted for ranging and communication. Experimental results show that the proposed method reduces localization errors in large swarms and loss of range information. It also explores the impact of signal parameters on communication and localization, highlighting the interplay between communication and localization performance.

eess.SP↗