arXiv subjects

Hongyu Li

Publications and source records attributed to Hongyu Li.

At least 37 records · Page 2Linked to original sources

arXiv2026

Temporal and Cross-Modal Alignment for Enhanced Audiovisual Video Captioning

While Multimodal Large Language Models (MLLMs) have advanced video understanding, achieving precise temporal and cross-modal alignment in audiovisual video captioning remains a formidable challenge. Most existing approaches suffer from modality detachment and temporal incoherence, failing to accurately bind auditory events to visual entities or capture complex causal dynamics. To address these deficiencies, we propose TCA-Captioner, a framework specifically engineered to enhance Temporal and Cross-Modal Alignment for audiovisual video captioning. We first introduce the Observer-Checker-Corrector (OCC) framework, an iterative refinement strategy that generates high-fidelity, meticulously grounded training data. Leveraging a curated high-density human interaction dataset, TCA-Captioner is optimized to model sophisticated audiovisual interactions. Furthermore, we present TCA-Bench, a diagnostic benchmark utilizing a Decoupled Evaluation Protocol to isolate and quantify model proficiency in audiovisual binding and temporal relational reasoning. Extensive experiments demonstrate that TCA-Captioner sets a new standard for temporally-coherent and synchronized audiovisual narratives.

cs.CV↗

arXiv2026

Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical Reasoning

Recent interest in multimodal large language models (MLLMs) raises a central question: can they reason over dynamic visual evidence rather than merely recognize objects or events in individual frames? This ability, which we refer to as video temporal-logical reasoning, requires models to maintain, update, and compose evidence as visual states evolve across frames. Existing video benchmarks often conflate this capability with scene complexity, static recognition, or uncontrolled temporal variation. To isolate this capability, we introduce Video-MME-Logical, a controlled benchmark organized around five temporal-logical operations: state tracking, sequential counting, temporal ordering, dynamic spatiality, and structural composition. The benchmark contains 25 fine-grained task categories generated with controlled object states, transitions, temporal dependencies, and logical compositions. It enables difficulty-controlled final-answer evaluation by varying temporal horizon and reasoning complexity, and supports intermediate-state diagnostics by verifying whether models recover the required logical reasoning trace before producing the final answer. Experiments with state-of-the-art MLLMs reveal a substantial human-model gap, especially as temporal-logical complexity increases. Supervised fine-tuning on up to 500K generated samples improves performance but remains insufficient to close the reasoning gap, positioning Video-MME-Logical as a scalable testbed for analyzing and improving temporal-logical reasoning in MLLMs.

cs.CV↗

arXiv2026

High-sensitivity and high-resolution collaborative determination of birefringence coefficient using weak measurement

Precise nanofilm birefringence characterization is essential for high-sensitivity polarization response and strong anti-interference detection in photodetectors. We present a high-sensitivity and high-resolution birefringence coefficient determination system for nm-level membranes based on weak measurement, addressing the sensitivity-resolution trade-off. A tunable bandwidth light source is exploited to achieve simultaneous and complementary measurements of momentum (P-pointer) and intensity (I-pointer), enabling calibration-free operation across various bandwidths, and to realize high-precision phase difference monitoring of the measured membranes. This method maps the birefringence effect to a weak-value amplified signal of spectral shift and light intensity. The optimal resolution, achieved at a spectral width of 6 nm, is $1.12 \times 10^{-8}$ RIU, while the optimal sensitivity is achieved when the light source is a narrow-linewidth coherent laser, reaching 4710 mV/RIU. The linear range of the system covers a broad birefringence coefficient range for crystals, from $10^{-6}$ to 0.1. Furthermore, the auxiliary optical path eliminates substrate interference, achieving a detection limit of birefringence coefficient as low as $10^{-8}$ RIU. This approach, characterized by high precision, high sensitivity, and strong robustness, provides an effective solution for the detection of optical nano-thin membrane parameters.

physics.optics↗

arXiv2026

LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Experts

Recent advances in video diffusion models have significantly improved visual quality, yet ultra-high-resolution (UHR) video generation remains a formidable challenge due to the compounded difficulties of motion modeling, semantic planning, and detail synthesis. To address these limitations, we propose \textbf{LUVE}, a \textbf{L}atent-cascaded \textbf{U}HR \textbf{V}ideo generation framework built upon dual frequency \textbf{E}xperts. LUVE employs a three-stage architecture comprising low-resolution motion generation for motion-consistent latent synthesis, video latent upsampling that performs resolution upsampling directly in the latent space to mitigate memory and computational overhead, and high-resolution content refinement that integrates low-frequency and high-frequency experts to jointly enhance semantic coherence and fine-grained detail generation. Extensive experiments demonstrate that our LUVE achieves superior photorealism and content fidelity in UHR video generation, and comprehensive ablation studies further validate the effectiveness of each component. The project is available at \href{https://unicornanrocinu.github.io/LUVE_web/}{https://github.io/LUVE/}.

cs.CV↗

arXiv2026

Cascade of magnetic-field-induced quantum spin states in a spin-1 honeycomb magnet

Quantum fluctuations endow spin systems with surprisingly enriched magnetic phase diagrams. In frustrated magnets, strong quantum fluctuations boosted by either geometrical incompatibility or competitive exchange interactions stabilize cascades of unusual phases of matter. Here we reveal the presence of multiple quantum phases in the honeycomb antiferromagnet Na$_{3}$Ni$_{2}$BiO$_{6}$, both inside and beyond its field-induced one-third magnetization plateau. Comprehensive measurements of thermodynamic quantities demonstrate that the one-third plateau comprises at least three distinct spin states with nearly-degenerate net magnetization, separated by first-order transitions that likely involve sequential spin reconfiguration. Upon further increasing the magnetic field, the system evolves across a myriad of peculiar phases before reaching full polarization; these intermediate phases possess copious low-energy excitations, manifested by anomalous upturns of specific heat at ultralow temperatures -- probably hinting at the development of "hidden" ordered ground states. The complex magnetic phase diagram of Na$_{3}$Ni$_{2}$BiO$_{6}$ underlines the preponderant impact of quantum fluctuations on a honeycomb spin lattice with strong exchange frustration.

cond-mat.str-el↗

arXiv2026

Gen-Searcher: Reinforcing Agentic Search for Image Generation

Recent image generation models have shown strong capabilities in generating high-fidelity and photorealistic images. However, they are fundamentally constrained by frozen internal knowledge, thus often failing on real-world scenarios that are knowledge-intensive or require up-to-date information. In this paper, we present Gen-Searcher, as the first attempt to train a search-augmented image generation agent, which performs multi-hop reasoning and search to collect the textual knowledge and reference images needed for grounded generation. To achieve this, we construct a tailored data pipeline and curate two high-quality datasets, Gen-Searcher-SFT-10k and Gen-Searcher-RL-6k, containing diverse search-intensive prompts and corresponding ground-truth synthesis images. We further introduce KnowGen, a comprehensive benchmark that explicitly requires search-grounded external knowledge for image generation and evaluates models from multiple dimensions. Based on these resources, we train Gen-Searcher with SFT followed by agentic reinforcement learning with dual reward feedback, which combines text-based and image-based rewards to provide more stable and informative learning signals for GRPO training. Experiments show that Gen-Searcher brings substantial gains, improving Qwen-Image by around 16 points on KnowGen and 15 points on WISE. We hope this work can serve as an open foundation for search agents in image generation, and we fully open-source our data, models, and code.

cs.CV↗

arXiv2026

4DThinker: Thinking with 4D Imagery for Dynamic Spatial Understanding

Dynamic spatial reasoning from monocular video is essential for bridging visual intelligence and the physical world, yet remains challenging for vision-language models (VLMs). Prior approaches either verbalize spatial-temporal reasoning entirely as text, which is inherently verbose and imprecise for complex dynamics, or rely on external geometric modules that increase inference complexity without fostering intrinsic model capability. In this paper, we present 4DThinker, the first framework that enables VLMs to "think with 4D" through dynamic latent mental imagery, i.e., internally simulating how scenes evolve within the continuous hidden space. Specifically, we first introduce a scalable, annotation-free data generation pipeline that synthesizes 4D reasoning data from raw videos. We then propose Dynamic-Imagery Fine-Tuning (DIFT), which jointly supervises textual tokens and 4D latents to ground the model in dynamic visual semantics. Building on this, 4D Reinforcement Learning (4DRL) further tackles complex reasoning tasks via outcome-based rewards, restricting policy gradients to text tokens to ensure stable optimization. Extensive experiments across multiple dynamic spatial reasoning benchmarks demonstrate that 4DThinker consistently outperforms strong baselines and offers a new perspective toward 4D reasoning in VLMs. Our code is available at https://github.com/zhangquanchen/4DThinker.

cs.CV↗

arXiv2026

Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning

Currently, enhancing Unified Multimodal Models (UMMs) with image understanding, generation, and editing capabilities mainly relies on mixed multi-task training. Due to inherent task conflicts, such strategy requires complex multi-stage pipelines, massive data mixing, and balancing tricks, merely resulting in a performance trade-off rather than true mutual reinforcement. To break this paradigm, we propose Uni-Edit, an intelligent image editing task that serves as the first general task for UMM tuning. Unlike complex mixed pipelines, Uni-Edit improves performance across all three abilities at once using only one task, one training stage, and one dataset. Specifically, we first identify image editing as an inherently ideal general task, as it naturally demands both visual understanding and generation. However, existing editing data relies on simplistic instructions that severely underutilize a model's understanding capacity. To address this, we introduce the first automated and scalable data synthesis pipeline for intelligent editing, transforming diverse VQA data into complex and effective editing instructions with embedded questions and nested logic. This yields Uni-Edit-148k, pairing diverse reasoning-intensive instructions with high-quality edited images. Extensive experiments on BAGEL and Janus-Pro demonstrate that tuning solely on Uni-Edit achieves comprehensive enhancements across all three capabilities without any auxiliary operations.

cs.CV↗

arXiv2026

AIA: Rethinking Architecture Decoupling Strategy In Unified Multimodal Model

Unified multimodal models for image generation and understanding represent a significant step toward AGI and have attracted widespread attention from researchers. The main challenge of this task lies in the difficulty in establishing an optimal training paradigm due to inherent conflicting targets in understanding and generation tasks. To alleviate these conflicts and pursue higher performance, many researchers adopt varying degrees of architecture decoupling (e.g., Double image encoders, MOE/MOT architecture, or frozen MLLM). However, excessive model decoupling can lead to the loss of interleave generation ability, undermining the original intent of unified models. In this work, we aim to explore how to mitigate task conflicts without resorting to model decoupling. Firstly, we analyze why decoupling boosts performance by studying the cross-modal attention behavior of models. We observe that architecture decoupling does not solve task conflicts, but essentially drives models toward cross-modal interaction patterns of task-specific models, as seen in Qwen3-VL and HunyuanImage-3.0, and that the more thorough the decoupling, the more consistent the behavior becomes. Motivated by this observation, we propose Attention Interaction Alignment (AIA) loss, which explicitly learns task-specific multimodal interaction patterns during training. To demonstrate the generalizability of our AIA loss, we apply it to Emu3 and Janus-Pro during SFT and post-training stage respectively. Without bells and whistles, AIA not only refines cross-modal attention patterns, but also boosts both generation and understanding performance.

cs.CV↗

arXiv2026

Exploring the AI Obedience: Why is Generating a Pure Color Image Harder than CyberPunk?

Recent advances in generative AI have shown human-level performance in complex content creation. However, we identify a "Paradox of Simplicity": models that can render complex scenes often fail at trivial, low-entropy tasks, such as generating a uniform pure color image. We argue this is a systemic failure related to uncontrollable emergent abilities. As models scale, strong priors for aesthetics and complexity override deterministic simplicity, creating an "aesthetic bias" that hinders the model's transition from data simulation to true intellectual abstraction. To better investigate this problem, we formalize the concept of AI Obedience, a hierarchical framework that grades a model's ability to transition from probabilistic approximation to pixel-level determinism (Levels 1 to 5). We introduce Violin, the first systematic benchmark designed to evaluate Level 4 Obedience through three deterministic tasks: color purity, image masking, and geometric shape generation. Using Violin, we evaluate several state-of-the-art models and reveal that closed-source models generally outperform open-source ones in deterministic precision. Interestingly, performance on our benchmark correlates with the benchmark in natural image generation. Our work provides a foundational framework and tools for achieving better alignment between human instructions and model outputs.

cs.CV↗

arXiv2026

Massive MIMO-ISAC System With 1-Bit ADCs/DACs

This paper investigates a hardware-efficient massive multiple-input multiple-output integrated sensing and communication (MIMO-ISAC) system with 1-bit analog-to-digital converters (ADCs)/digital-to-analog converters (DACs). The proposed system, referred to as 1BitISAC, employs 1-bit DACs at the ISAC transmitter and 1-bit ADCs at the sensing receiver, achieving significant reductions in power consumption and hardware costs. For such kind of systems, two 1BitISAC joint transceiver designs, i.e., i) quality of service constrained 1BitISAC design and ii) quality of detection constrained design, are considered and the corresponding problems are formulated. In order to address these problems, we thoroughly analyze the radar detection performance after 1-bit ADCs quantization and the communication bit error rate. This analysis yields new design insights and leads to unique radar and communication metrics, which enables us to simplify the original problems and employ majorization-minimization and integer linear programming methods to solve the problems. Numerical results are provided to validate the performance analysis of the proposed 1BitISAC and to compare with other ISAC configurations. The superiority of the proposed 1BitISAC system in terms of balancing ISAC performance and energy efficiency is also demonstrated.

eess.SP↗

arXiv2026

Mass Production of 2023 KMTNet Microlensing Planets. III: Three Planets from the Subprime Field

To complete the analysis of the 2023 KMTNet subprime-field microlensing planetary events identified by its AlertFinder system, we present the analysis of six events, KMT-2023-BLG-(1810, 0084, 1118, 0584, 1697, 2218). We find that the first three events are securely confirmed as planetary, with inferred mass ratios of $\log q \sim -1.9$, $-2.0$, and $-2.6$, respectively. The remaining three events exhibit the well-known degeneracy between binary-lens/single-source (2L1S) and single-lens/binary-source (1L2S) models, and two of these also admit viable stellar binary solutions. A Bayesian analysis indicates that the companions in the confirmed planetary events are likely either super-Jupiters orbiting beyond the snow line of M- or K-dwarf hosts or, for two degenerate solutions of KMT-2023-BLG-1118, Saturn-mass planets orbiting late-type M dwarfs. To date, the 2023 KMTNet sample contains 25 unambiguous planetary events, and its mass-ratio distribution is consistent with that of the KMTNet planetary sample from 2016--2019.

astro-ph.EP↗

arXiv2026

Antenna Coding Design for Pixel Antenna Empowered Rate-Splitting Multiple Access

This work explores the integration of pixel antennas and rate-splitting multiple access (RSMA) to enhance spectral efficiency in multi-user multiple-input single-output (MU-MISO) systems. Pixel antennas offer controllable antenna characteristics via antenna coding from the analog domain, whereas RSMA provides efficient interference management from the digital domain. We propose a novel pixel antenna empowered RSMA transmission framework where each user employs a pixel antenna. Under imperfect channel state information at the transmitter, we formulate a joint precoding and antenna coding design problem to maximize the ergodic sum-rate. An alternating optimization algorithm based on the weighted minimum mean square error (WMMSE) approach and the successive exhaustive Boolean optimization (SEBO) is first developed to solve the problem. We then propose an efficient online antenna coder selection algorithm relying on an offline-designed codebook to reduce computational complexity. Numerical results show that the proposed pixel antenna empowered RSMA significantly improves spectral efficiency compared to both RSMA with fixed antennas and space-division multiple access (SDMA) employing the same pixel antenna configuration. Moreover, compared to SDMA, RSMA maintains the same performance with a simpler pixel antenna configuration or a smaller codebook size.

eess.SP↗

arXiv2026

OmniAlpha: Aligning Transparency-Aware Generation via Multi-Task Unified Reinforcement Learning

Transparency-aware generation requires modeling not only RGB appearance but also alpha-based opacity and cross-layer composition, which are essential for tasks such as image matting, object removal, layer decomposition, and multi-layer content creation. However, existing RGBA-related methods remain largely fragmented, with separate pipelines designed for individual tasks. While a unified model is desirable, supervised fine-tuning alone is insufficient, as localized regression objectives cannot directly optimize the compositional fidelity, alpha-boundary precision, and structural consistency required for high-quality RGBA generation. To address this, we propose OmniAlpha, a unified multi-task reinforcement learning framework for transparency-aware generation and manipulation. OmniAlpha combines an end-to-end alpha-aware VAE and a sequence-to-sequence Diffusion Transformer, with a bi-directional layer axis in positional encoding to jointly model multiple RGBA inputs and outputs within a single forward pass. Built on a multi-task SFT cold start, it further performs GRPO-style post-training with layer-aware rewards defined on decoded RGBA outputs, enabling direct optimization of cross-layer coherence and fine transparency details. Experiments across five categories of transparency-aware tasks show that OmniAlpha consistently outperforms its unified SFT baseline and achieves strong performance against specialized expert models, including a 9.07% relative reduction in RGB L1 on layer decomposition and 74%/68% improvements over conventional matting tools on SAD/Grad for automatic matting.

cs.CV↗

arXiv2026

OneThinker: All-in-one Reasoning Model for Image and Video

Reinforcement learning (RL) has recently achieved remarkable success in eliciting visual reasoning within Multimodal Large Language Models (MLLMs). However, existing approaches typically train separate models for different tasks and treat image and video reasoning as disjoint domains. This results in limited scalability toward a multimodal reasoning generalist, which restricts practical versatility and hinders potential knowledge sharing across tasks and modalities. To this end, we propose OneThinker, an all-in-one reasoning model that unifies image and video understanding across diverse fundamental visual tasks, including question answering, captioning, spatial and temporal grounding, tracking, and segmentation. To achieve this, we construct the OneThinker-600k training corpus covering all these tasks and employ commercial models for CoT annotation, resulting in OneThinker-SFT-340k for SFT cold start. Furthermore, we propose EMA-GRPO to handle reward heterogeneity in multi-task RL by tracking task-wise moving averages of reward standard deviations for balanced optimization. Extensive experiments on diverse visual benchmarks show that OneThinker delivers strong performance on 31 benchmarks, across 10 fundamental visual understanding tasks. Moreover, it exhibits effective knowledge transfer between certain tasks and preliminary zero-shot generalization ability, marking a step toward a unified multimodal reasoning generalist. All code, model, and data are released.

cs.CV↗

arXiv2026

LoViF 2026 Challenge on Real-World All-in-One Image Restoration: Methods and Results

This paper presents a review for the LoViF Challenge on Real-World All-in-One Image Restoration. The challenge aimed to advance research on real-world all-in-one image restoration under diverse real-world degradation conditions, including blur, low-light, haze, rain, and snow. It provided a unified benchmark to evaluate the robustness and generalization ability of restoration models across multiple degradation categories within a common framework. The competition attracted 124 registered participants and received 9 valid final submissions with corresponding fact sheets, significantly contributing to the progress of real-world all-in-one image restoration. This report provides a detailed analysis of the submitted methods and corresponding results, emphasizing recent progress in unified real-world image restoration. The analysis highlights effective approaches and establishes a benchmark for future research in real-world low-level vision.

cs.CV↗

arXiv2026

Active Beyond-Diagonal Reconfigurable Intelligent Surface with Hybrid Transmitting and Reflecting Mode

Beyond-diagonal reconfigurable intelligent surfaces (BD-RISs), originally in the passive form, have attracted attention due to their benefits in enhanced wave manipulating through flexible inter-element connections and element arrangements. To mitigate the severe multiplicative fading, the concept of active BD-RISs with signal amplification capability has recently been proposed. Inspired by this, we investigate the hybrid transmitting and reflecting mode of active BD-RISs to achieve full-space coverage. We start by deriving a physics compliant communication model applying active BD-RIS with hybrid mode. We further propose novel architectures including reciprocal and non-reciprocal implementations with cell-wise single, group, and fully connections. We also develop a unified optimization framework for the joint transmit precoding and hybrid mode active BD-RIS design to maximize the sum rate of multi-user communication systems, which is applicable to all considered architectures. Numerical results demonstrate that, under the same total power budget, the proposed active BD-RIS with hybrid mode substantially outperforms active and passive simultaneous transmitting and reflecting RISs as well as passive BD-RISs with hybrid mode. This shows the synergy gain from inter-element connection, element arrangements, and active amplification.

eess.SP↗

arXiv2026

Visualizing the interplay of dual electronic nematicities in kagome superconductors

Kagome superconductor AV$_3$Sb$_5$ (A stands for K, Rb, and Cs) hosts a wealth of intertwined electronic orders driven by geometric frustration and electron correlations. Among them, the breaking of rotational and/or time-reversal symmetry, observed within the triple-$Q$ charge density wave (CDW) phase yet exhibiting a more complex temperature dependence, remains a central puzzle. Here, by using scanning tunneling microscopy to study the electronic structures of CsV$_3$Sb$_5$ as a function of temperature and Ti doping, we disentangle the interrelation between two distinct nematic order parameters, one associated with the CDW and the other manifested as $C_2$ distortion of the V-$d_{x^{2}-y^{2}}$ Fermi pockets without breaking transition symmetry. The latter persists to high doping levels and high temperatures where the long-range CDW is fully suppressed. Moreover, its nematic director is oriented in a lattice direction distinct from that of the CDW-induced nematicity at intermediate doping, and eventually aligns with the strong nematic CDW order in the pristine compound where the quasiparticles of vanadium orbitals become coherent below a lower characteristic temperature. These observations, combined with Ginzburg-Landau analysis, reveal a rich interplay between two nematic orders that can be assigned to distinct kagome-lattice orbitals. Our results shed new light on the enigmatic intertwined orders in this family and establish a rare material platform in which dual nematic orders coexist and couple to give rise to unusual correlated phenomena.

cond-mat.supr-con↗