arXiv subjects

Qi Song

Publications and source records attributed to Qi Song.

At least 37 records · Page 2Linked to original sources

arXiv2026

PoI: A Filter to Extract Pixel of Interest from Novel Views for Scene Coordinate Regression

Neural View Synthesis (NVS) techniques such as NeRF and 3D Gaussian Splatting (3DGS) have enabled photorealistic rendering from novel viewpoints and are increasingly used to augment training data for visual localization. However, these methods fundamentally rely on observed geometry and radiance; they interpolate existing information but cannot hallucinate unseen 3D structures or recover missing content under sparse or extreme viewpoints. As a result, rendered views often exhibit blur, structural distortion, or incomplete geometry. While such imperfections may be tolerated by Camera Pose Regression (CPR) methods, they severely degrade Scene Coordinate Regression (SCR), which requires accurate per-pixel 3D supervision. To address this limitation, we introduce PoI (Pixel-of-Interest), a framework that enables effective NVS augmentation for SCR-based localization. We first employ 3DGS to render novel views and leverage a single-step diffusion model to refine them, allowing the synthesis of structurally plausible details beyond purely geometry-driven interpolation. However, even diffusion-refined views may contain unreliable pixels. Therefore, we propose a progressive pixel-level filtering strategy based on reprojection error to selectively retain trustworthy synthetic pixels during training while suppressing harmful ones. Extensive experiments on 7Scenes and Cambridge Landmarks demonstrate that our method consistently improves localization accuracy over strong SCR baselines and achieves state-of-the-art performance with competitive training efficiency. Our results reveal that, for SCR, the benefit of novel view augmentation depends not only on generative realism but also on explicit control of pixel-level reliability.

cs.CV↗

arXiv2026

Superconducting phase diagram of multi-layer square-planar nickelates

The discovery of superconductivity in square-planar nickelates has offered a rich materials platform to explore the origins of cuprate-like superconductivity. Experimental investigations however have largely been limited to the infinite-layer $R$NiO$_2$ ($R$=rare-earth) nickelates. Here, we construct a phase diagram of multi-layer square-planar Nd$_{n+1}$Ni$_n$O$_{2n+2}$ compounds and discover signatures of superconductivity for $n$ = 4 - 8. Upon decreasing the dimensionality $n$, the superconducting anisotropy evolves due to 4$f$ electron effects, and electronic structure characteristics approach cuprate-like behavior. Magnetic fluctuations persist from within the superconducting regime and into the over-doped, non-superconducting regime. Remarkably, the superconducting regime overlaps with that of chemically-doped infinite-layer nickelates, demonstrating underlying commonalities and distinct differences across varying structural realizations of square-planar nickelates. Our work establishes this layered template for creating new nickel-based superconductors.

cond-mat.supr-con↗

arXiv2026

ADGaussian: Generalizable Gaussian Splatting for Autonomous Driving via Multi-modal Joint Learning

We present a novel approach, termed ADGaussian, for generalizable street scene reconstruction. The proposed method enables high-quality rendering from merely single-view input. Unlike prior Gaussian Splatting methods that primarily focus on geometry refinement, we emphasize the importance of joint optimization of image and depth features for accurate Gaussian prediction. To this end, we first incorporate sparse LiDAR depth as an additional input modality, formulating the Gaussian prediction process as a joint learning framework of visual information and geometric clue. Furthermore, we propose a Multi-modal Feature Matching strategy coupled with a Multi-scale Gaussian Decoding model to enhance the joint refinement of multi-modal features, thereby enabling efficient multi-modal Gaussian learning. Extensive experiments on Waymo and KITTI demonstrate that our ADGaussian achieves state-of-the-art performance and exhibits superior zero-shot generalization capabilities in novel-view shifting.

cs.CV↗

arXiv2026

Mergers Drive Structural Complexity but Not Starbursts in Lyman-$α$ Emitters at $3 < z < 4$: A JWST Spatially Resolved View

Recent observations with the James Webb Space Telescope (JWST) reveal that the merger fraction among Ly$α$ emitters (LAEs) at redshifts $z > 3$ is significantly higher than previously estimated. In this study, we focus on three high signal-to-noise merging LAE systems at $3 < z < 4$, selected from the VLT/MUSE-Deep survey in the GOODS-S field. We combine new \textit{JWST}/NIRCam broadband and medium-band imaging with archival \textit{HST}/ACS data to perform spatially resolved spectral energy distribution (SED) fitting using the \textsc{Bagpipes} software package. Our analysis reveals that two of the systems are minor mergers, while the third is a major merger. The close agreement between spatially resolved and integrated stellar mass estimates indicates that recent star formation does not significantly outshine the light from older stellar populations in these systems. Moreover, both the individual components and the systems as a whole lie on the star-forming main sequence, further supporting the conclusion that these mergers have not yet triggered substantial starburst activity. Furthermore, we detect prominent color gradients and disturbed dust distributions in these merging systems, indicating that the mergers have already induced significant internal structural perturbations. These morphological and dust-related changes may facilitate the escape of Ly$α$ photons -- potentially through mechanisms such as gas redistribution or a reduced covering fraction of neutral hydrogen -- thereby playing a key role in shaping the observed properties of LAEs.

astro-ph.GA↗

arXiv2026

LLMBind: A Unified Modality-Task Integration Framework

Despite recent progress in Multi-Modal Large Language Models (MLLMs), it remains challenging to integrate diverse tasks ranging from pixel-level perception to high-fidelity generation. Existing approaches often suffer from either restricted task extensibility or severe performance degradation due to modality interference. n this paper, we present LLMBind, an extensible framework that unifies multimodal tasks through a dual-pathway mechanism: In-Situ semantic embeddings for localization-sensitive tasks like semantic segmentation and Ex-Situ task-prompts for generation across image, video, and audio modalities. Additionally, we employ a Mixture-of-Experts (MoE) architecture to route task-specific tokens, thereby achieving modality disentanglement and mitigating negative transfer. We also curate a 400k multi-turn interactive dataset focused on iterative visual refinement to enable human-like interaction. Extensive experiments demonstrate that LLMBind achieves excellent performance across multiple perception and generation benchmarks while maintaining superior expandability.

cs.CL↗

arXiv2026

GraphIF: Enhancing Multi-Turn Instruction Following for Large Language Models with Relation Graph Prompt

Multi-turn instruction following is essential for building intelligent conversational systems that can consistently adhere to instructions across dialogue turns. However, existing approaches to enhancing multi-turn instruction following primarily rely on collecting or generating large-scale multi-turn dialogue datasets to fine-tune large language models (LLMs), which treat each response generation as an isolated task and fail to explicitly incorporate multi-turn instruction following into the optimization objectives. As a result, instruction-tuned LLMs often struggle with complex long-distance constraints. In multi-turn dialogues, relational constraints across turns can be naturally modeled as labeled directed edges, making graph structures particularly suitable for modeling multi-turn instruction following. Despite this potential, leveraging graph structures to enhance the multi-turn instruction following capabilities of LLMs remains unexplored. To bridge this gap, we propose GraphIF, a plug-and-play framework that models multi-turn dialogues as directed relation graphs and leverages graph prompts to enhance the instruction following capabilities of LLMs. GraphIF comprises three key components: (1) an agent-based relation extraction module that captures inter-turn semantic relations via action-triggered mechanisms to construct structured graphs; (2) a relation graph prompt generation module that converts structured graph information into natural language prompts; and (3) a response rewriting module that refines initial LLM outputs using the generated graph prompts. Extensive experiments on two long multi-turn dialogue datasets demonstrate that GraphIF can be seamlessly integrated into instruction-tuned LLMs and leads to significant improvements across all four multi-turn instruction-following evaluation metrics.

cs.CL↗

arXiv2026

Advanced Long-term Earth System Forecasting

Reliable long-term forecasting of Earth system dynamics is fundamentally limited by instabilities in current artificial intelligence (AI) models during extended autoregressive simulations. These failures often originate from inherent spectral bias, leading to inadequate representation of critical high-frequency, small-scale processes and subsequent uncontrolled error amplification. Inspired by the nested grids in numerical models used to resolve small scales, we present TritonCast. At the core of its design is a dedicated latent dynamical core, which ensures the long-term stability of the macro-evolution at a coarse scale. An outer structure then fuses this stable trend with fine-grained local details. This design effectively mitigates the spectral bias caused by cross-scale interactions. In atmospheric science, it achieves state-of-the-art accuracy on the WeatherBench 2 benchmark while demonstrating exceptional long-term stability: executing year-long autoregressive global forecasts and completing multi-year climate simulations that span the entire available $2500$-day test period without drift. In oceanography, it extends skillful eddy forecast to $120$ days and exhibits unprecedented zero-shot cross-resolution generalization. Ablation studies reveal that this performance stems from the synergistic interplay of the architecture's core components. TritonCast thus offers a promising pathway towards a new generation of trustworthy, AI-driven simulations. This significant advance has the potential to accelerate discovery in climate and Earth system science, enabling more reliable long-term forecasting and deeper insights into complex geophysical dynamics.

cs.LG↗

arXiv2025

Towards Long-window Anchoring in Vision-Language Model Distillation

While large vision-language models (VLMs) demonstrate strong long-context understanding, their prevalent small branches fail on linguistics-photography alignment for a limited window size. We discover that knowledge distillation improves students' capability as a complement to Rotary Position Embeddings (RoPE) on window sizes (anchored from large models). Building on this insight, we propose LAid, which directly aims at the transfer of long-range attention mechanisms through two complementary components: (1) a progressive distance-weighted attention matching that dynamically emphasizes longer position differences during training, and (2) a learnable RoPE response gain modulation that selectively amplifies position sensitivity where needed. Extensive experiments across multiple model families demonstrate that LAid-distilled models achieve up to 3.2 times longer effective context windows compared to baseline small models, while maintaining or improving performance on standard VL benchmarks. Spectral analysis also suggests that LAid successfully preserves crucial low-frequency attention components that conventional methods fail to transfer. Our work not only provides practical techniques for building more efficient long-context VLMs but also offers theoretical insights into how positional understanding emerges and transfers during distillation.

cs.CV↗

arXiv2025

Creating Blank Canvas Against AI-enabled Image Forgery

AIGC-based image editing technology has greatly simplified the realistic-level image modification, causing serious potential risks of image forgery. This paper introduces a new approach to tampering detection using the Segment Anything Model (SAM). Instead of training SAM to identify tampered areas, we propose a novel strategy. The entire image is transformed into a blank canvas from the perspective of neural models. Any modifications to this blank canvas would be noticeable to the models. To achieve this idea, we introduce adversarial perturbations to prevent SAM from ``seeing anything'', allowing it to identify forged regions when the image is tampered with. Due to SAM's powerful perceiving capabilities, naive adversarial attacks cannot completely tame SAM. To thoroughly deceive SAM and make it blind to the image, we introduce a frequency-aware optimization strategy, which further enhances the capability of tamper localization. Extensive experimental results demonstrate the effectiveness of our method.

cs.CV↗

arXiv2025

The Size Evolution and the Size-Mass Relation of Lyman-Alpha Emitters across $3 \lesssim z < 7$ as Observed by JWST

Understanding the morphological structures of Lyman-alpha emitters (LAEs) is crucial for unveiling their formation pathways and the physical origins of Ly$α$ emission. However, the evolution of their sizes and structural scaling relations remains debated. In this study, we analyze a large sample of 876 spectroscopically confirmed LAEs at $3 \lesssim z < 7$, selected from the MUSE, VANDELS, and CANDELSz7 surveys in the GOODS-S, UDS, and COSMOS fields. Utilizing James Webb Space Telescope (JWST) NIRCam imaging data, we measure their rest-frame UV and optical V-band effective radii ($R_{\rm e}$) through two-dimensional Sérsic profile fitting. Our results show that these LAEs are generally compact, with a median $R_{\rm e,UV}$ of 0.50$^{+0.30}_{-0.24}$ kpc and a median $R_{\rm e,V}$ of 0.57$^{+0.33}_{-0.24}$ kpc. The size evolution follows $R_{\rm e,UV} \propto (1 + z)^{-0.91 \pm 0.10}$ and $R_{\rm e,V} \propto (1 + z)^{-0.93 \pm 0.18}$, respectively. Their UV and optical sizes are statistically comparable, indicating negligible UV-to-optical color gradients. For the first time, we establish the rest-frame optical size-mass relation for LAEs at $z>3$, finding slopes comparable to typical star-forming galaxies (SFGs), but with slightly smaller sizes at a given stellar mass. These results provide important clues for understanding structural evolution of LAEs in the early universe.

astro-ph.GA↗

arXiv2025

Turn-on of Current-Induced Spin Torque upon Noncollinear Antiferromagnetic Ordering in Delafossite PdCrO2

We report measurements of the current-induced spin torque produced by the delafossite antiferromagnet PdCrO2 and acting on an adjacent ferromagnetic permalloy layer. The spin torque increases strongly as the temperature is reduced through the Neel temperature, when the PdCrO2 transitions from a paramagnetic phase to a noncollinear antiferromagnetic state. This result is qualitatively consistent with density functional theory calculations regarding how spin-current generation changes upon antiferromagnetic ordering in PdCrO2.

cond-mat.mtrl-sci↗

arXiv2025

Improving Hierarchical Representations of Vectorized HD Maps with Perspective Clues

The construction of vectorized High-Definition (HD) maps from onboard surround-view cameras has become a significant focus in autonomous driving. However, current map vector estimation pipelines face two key limitations: input-agnostic queries struggle to capture complex map structures, and the view transformation leads to information loss. These issues often result in inaccurate shape restoration or missing instances in map predictions. To address this concern, we propose a novel approach, namely \textbf{PerCMap}, which explicitly exploits clues from perspective-view features at both instance and point level. Specifically, at instance level, we propose Cross-view Instance Activation (CIA) to activate instance queries across surround-view images, thereby helping the model recover the instance attributes of map vectors. At point level, we design Dual-view Point Embedding (DPE), which fuses features from both views to generate input-aware positional embeddings and improve the accuracy of point coordinate estimation. Extensive experiments on \textit{nuScenes} and \textit{Argoverse 2} demonstrate that PerCMap achieves strong and consistent performance across benchmarks, reaching 67.1 and 70.5 mAP, respectively.

cs.CV↗

arXiv2025

RJE: A Retrieval-Judgment-Exploration Framework for Efficient Knowledge Graph Question Answering with LLMs

Knowledge graph question answering (KGQA) aims to answer natural language questions using knowledge graphs. Recent research leverages large language models (LLMs) to enhance KGQA reasoning, but faces limitations: retrieval-based methods are constrained by the quality of retrieved information, while agent-based methods rely heavily on proprietary LLMs. To address these limitations, we propose Retrieval-Judgment-Exploration (RJE), a framework that retrieves refined reasoning paths, evaluates their sufficiency, and conditionally explores additional evidence. Moreover, RJE introduces specialized auxiliary modules enabling small-sized LLMs to perform effectively: Reasoning Path Ranking, Question Decomposition, and Retriever-assisted Exploration. Experiments show that our approach with proprietary LLMs (such as GPT-4o-mini) outperforms existing baselines while enabling small open-source LLMs (such as 3B and 8B parameters) to achieve competitive results without fine-tuning LLMs. Additionally, RJE substantially reduces the number of LLM calls and token usage compared to agent-based methods, yielding significant efficiency improvements.

cs.CL↗

arXiv2025

MarkSplatter: Generalizable Watermarking for 3D Gaussian Splatting Model via Splatter Image Structure

The growing popularity of 3D Gaussian Splatting (3DGS) has intensified the need for effective copyright protection. Current 3DGS watermarking methods rely on computationally expensive fine-tuning procedures for each predefined message. We propose the first generalizable watermarking framework that enables efficient protection of Splatter Image-based 3DGS models through a single forward pass. We introduce GaussianBridge that transforms unstructured 3D Gaussians into Splatter Image format, enabling direct neural processing for arbitrary message embedding. To ensure imperceptibility, we design a Gaussian-Uncertainty-Perceptual heatmap prediction strategy for preserving visual quality. For robust message recovery, we develop a dense segmentation-based extraction mechanism that maintains reliable extraction even when watermarked objects occupy minimal regions in rendered views. Project page: https://kevinhuangxf.github.io/marksplatter.

cs.CV↗

arXiv2025

Align 3D Representation and Text Embedding for 3D Content Personalization

Recent advances in NeRF and 3DGS have significantly enhanced the efficiency and quality of 3D content synthesis. However, efficient personalization of generated 3D content remains a critical challenge. Current 3D personalization approaches predominantly rely on knowledge distillation-based methods, which require computationally expensive retraining procedures. To address this challenge, we propose \textbf{Invert3D}, a novel framework for convenient 3D content personalization. Nowadays, vision-language models such as CLIP enable direct image personalization through aligned vision-text embedding spaces. However, the inherent structural differences between 3D content and 2D images preclude direct application of these techniques to 3D personalization. Our approach bridges this gap by establishing alignment between 3D representations and text embedding spaces. Specifically, we develop a camera-conditioned 3D-to-text inverse mechanism that projects 3D contents into a 3D embedding aligned with text embeddings. This alignment enables efficient manipulation and personalization of 3D content through natural language prompts, eliminating the need for computationally retraining procedures. Extensive experiments demonstrate that Invert3D achieves effective personalization of 3D content. Our work is available at: https://github.com/qsong2001/Invert3D.

cs.CV↗

arXiv2025

High-sensitivity Optical Microcavity Acoustic Sensor Covering Free Spectral Range

Optical whispering gallery mode microcavity acoustic sensors have emerged significant potential in high-sensitivity acoustic signal detection, but the narrow dynamic range limits the application prospect. To address the challenge, we propose and experimentally demonstrate a high-sensitivity acoustic sensor in optical whispering gallery mode microcavity. The proposed sensor integrates an extended Mach-Zehnder polarization interferometer with postselection, extending the dynamic range to the free spectral range. The sensing regions can be categorized into phase-drastic and phase-enhanced regions, both of which yield an optimal acoustic response that surpasses traditional transmission method. Experiment results demonstrate improvements of 57.87 dB in detection sensitivity and 26 times in minimal detectable acoustic pressure over the transmission method. Moreover, the application of coherent state and heterodyne detection can enhance response amplitude, further improving the detection sensitivity. Given the wide application range for acoustic dispersion and dissipation response, as well as the performance advantages of high sensitivity and wide dynamic range, the proposed WGM sensor offers a promising solution for acoustic sensing. Potentially, the structural design may be adaptable to other application scenarios involving time-varying signals through optical microcavity sensing.

physics.optics↗

arXiv2025

Heterogeneity-Oblivious Robust Federated Learning

Federated Learning (FL) remains highly vulnerable to poisoning attacks, especially under real-world hyper-heterogeneity, where clients differ significantly in data distributions, communication capabilities, and model architectures. Such heterogeneity not only undermines the effectiveness of aggregation strategies but also makes attacks more difficult to detect. Furthermore, high-dimensional models expand the attack surface. To address these challenges, we propose Horus, a heterogeneity-oblivious robust FL framework centered on low-rank adaptations (LoRAs). Rather than aggregating full model parameters, Horus inserts LoRAs into empirically stable layers and aggregates only LoRAs to reduce the attack uncover a key empirical observation that the input projection (LoRA-A) is markedly more stable than the output projection (LoRA-B) under heterogeneity and poisoning. Leveraging this, we design a Heterogeneity-Oblivious Poisoning Score using the features from LoRA-A to filter poisoned clients. For the remaining benign clients, we propose projection-aware aggregation mechanism to preserve collaborative signals while suppressing drifts, which reweights client updates by consistency with the global directions. Extensive experiments across diverse datasets, model architectures, and attacks demonstrate that Horus consistently outperforms state-of-the-art baselines in both robustness and accuracy.

cs.LG↗

arXiv2025

The JWST Unveils the Bimodal Nature of Lyman Alpha Emitters at 3 <z<7: Pristine versus Merger-Driven Populations

We present a systematic study of merging galaxies among Lyman-alpha emitters (LAEs) using JWST/NIRCam high-resolution imaging data. From a large sample of 817 spectroscopically confirmed LAEs at $3 8.5$) and bright ($M_{\rm UV}<-19.5$) systems. At fixed $M_*$ and $M_{\rm UV}$, we find negligible differences in the UV slope ($β$) between late-stage mergers and isolated LAEs; however, a clear bimodal distribution emerges in the $M_*$-sSFR plane, where isolated LAEs peak at $\log(M_*/M_\odot)\approx7.8$ and $\log({\rm sSFR/yr^{-1}})\approx-7.4$, and late-stage mergers peak at $\log(M_*/M_\odot)\approx8.6$ and $\log({\rm sSFR/yr^{-1}})\approx-7.6$. Our results reveal two evolutionary classes -- Pristine LAEs, low-mass ($M_*<10^{8.5}M_\odot$), isolated systems that represent early-stage galaxies with minimal merger interactions, and Merger-driven LAEs, massive ($M_*>10^{8.5}M_\odot$) systems in which mergers enhance star formation and facilitate the escape of Lyman-alpha photons or accrete pristine LAEs -- both of which are consistent with both observational and theoretical expectations and collectively demonstrate that mergers are a central driver of LAE evolution across the first two billion years.

astro-ph.GA↗