arXiv subjects

Yilin Liu

Publications and source records attributed to Yilin Liu.

At least 19 recordsLinked to original sources

arXiv2026

QV-PIC: Query-Aware Visual Position-Independent Caching for Efficient RAG Serving

Retrieval-Augmented Generation (RAG) repeatedly prefills identical text chunks across queries, incurring redundant computations. Position-Independent Caching (PIC) mitigates it by reusing precomputed Key-Value (KV) across positions, but its efficiency is constrained by the large volume of text tokens. Rendering text chunks as images can compress the text into fewer visual tokens, but the rendered-image PIC suffers more severe quality degradation than the text PIC. This representation-specific gap primarily arises from contextual mismatches across independently compiled caches and the loss of fine-grained textual evidence during visual compression. Existing PIC repair methods mainly address the former through selective recomputation, but they incur online computation and cannot recover lost textual details. We propose QV-PIC, a query-aware dual-resolution PIC reuse framework guided by model-native templates. Offline, QV-PIC compiles visual caches under the model's native chat-template prefix, improving PIC quality without online recomputation. Online, it preserves global context with low resolution and restores fine-grained textual evidence within a high-resolution budget by cumulative query relevance scores, retaining the efficiency benefit of visual compression. Across six tasks, QV-PIC improves average F1 by 21.6 points over vanilla rendered-image PIC, closes the gap to vanilla text PIC, and surpasses optimized text PIC by 2.58 F1 while reducing TTFT by 17.2\%. Relative to full prefill, it cuts TTFT by 83.8%.

cs.CL↗

arXiv2026

TopoGS: Planar Reconstruction via Topology-aware 3D Gaussian Splatting

Extracting structured, parametric 3D representations from raw images remains a fundamental challenge in computer vision and graphics. While recent advancements in the 3D Gaussian Splatting (3DGS) pipeline integrate planar primitives to yield compact and editable geometry, these approaches typically treat planes as isolated, discrete sets. This lack of topological connectivity hinders robust geometric reasoning, leading to fragmented reconstructions and misaligned boundaries that fall short of the precision for rigorous spatial analysis and professional design workflows. To address this, we introduce TopoGS, the first 3DGS framework to explicitly integrate both planar and topological constraints for coherent 3D reconstruction. Specifically, we extract global 2D topological relationships from multi-view image segmentations and anchor Gaussian primitives to these structural elements. This formulation enables the joint optimization of plane parameters, rendering fidelity, and topological adjacency. By enforcing strict multi-view consistency alongside these topological constraints, our method significantly mitigates geometric misalignments and produces connected, structured 3D models. Extensive evaluations on the ScanNet++ dataset demonstrate that TopoGS achieves state-of-the-art performance, providing a highly robust solution for generating accurate, topologically sound, and visually faithful scene representations.

cs.CV↗

arXiv2026

DualBrep: A Dual-Field Continuous Representation for B-rep Modelling

Boundary Representation (B-rep) is the most commonly used data format in Computer-Aided Design (CAD) due to its analytical precision and direct support for parametric editing. However, its heterogeneous structure--continuous parametric geometry combined with discrete topological graphs--poses fundamental challenges for deep learning. Existing methods often predict the heterogeneous B-rep graph directly, using fixed-size padding or sequential tokenization to handle varying primitive counts. These approaches struggle with the combinatorial complexity of CAD models. Furthermore, the discrete, non-differentiable nature of graph data prevents end-to-end optimization of geometry and watertightness. In this work, we introduce DualBrep, a novel continuous representation that unifies B-rep geometry and topology within a fully structured Euclidean domain. DualBrep encodes a CAD model using dual scalar fields: a Signed Distance Function (SDF) representing global shape geometry, and an Unsigned Distance Field (UDF) implicitly encoding topological structure via a Voronoi partitioning of surface elements. Rather than processing these fields independently, we compress them into a single latent space. While the dual-field formulation alone provides a flexible, primitive-free segmentation signal that adapts to arbitrary face counts and surface types, the shared latent makes generation tractable. A Flow Matching model can sample geometry and topology jointly from a single code, avoiding the error accumulation that plagues sequential B-rep predictors. Finally, a neural rebuilder extracts explicit B-rep models--comprising both prismatic and free-form primitives--directly from our continuous dual fields. We demonstrate that DualBrep is a robust backbone for CAD learning, achieving strong performance in point cloud reverse engineering and generative modeling via latent flow matching.

cs.GR↗

arXiv2026

Modeling Spectral Energy Shifts in Spatio-Temporal Graph Anomaly Detection

Graph anomaly detection methods aim to distinguish anomalous nodes. While prior methods characterize anomalies through increased variation in the spectral energy distributions, they overlook those that result in decreased variation, i.e., camouflaged anomalies that appear normal. We show that this type of anomaly persists across multiple datasets and remains undetectable by existing spectral approaches. To address this limitation, we propose a node-level spectral energy formulation that is fully compatible with message passing and enables the detection of camouflaged anomalies. Building on this formulation, we introduce an energy-aware graph learning framework that models spectral shifts through energy-driven message passing in both static and time-series graphs. Besides, our unified architecture extends to temporal settings without introducing specialized sequence modules, enabling efficient learning under long sliding windows. Extensive experiments on large-scale benchmarks demonstrate the effectiveness and scalability of our approach.

cs.LG↗

arXiv2026

Memento: Personalized RAG-Style Long-Retention Data Scaling for META Ads Recommendation

Modeling of long history data suffers from long-context window attention dilution, system efficiency and catastrophic forgetting problems, where naive linear scaling approach like LastN would fail. We introduce Memento, a personalized retrieval-augmented framework that treats historical user engagements as a document corpus and ad requests as queries, retrieving relevant interactions via Maximal Marginal Relevance (MMR) to balance similarity with diversity. We identify two complementary applications: Representation Memento, which retrieves historical embeddings for feature augmentation, and Data Memento, which retrieves past training examples for multipass training. Through infrastructure co-design -- temporal chunking, INT8 quantization, and asynchronous serving -- Memento achieves 5-10$\times$ resource efficiency over linear scaling. Memento processes daily requests with sub-10ms latency, yielding 0.25-0.3% Normalized Entropy gain on both click-through and conversion prediction. In production, Memento delivers a 1% CTR lift on Facebook Feed and Reels and a 1.2% CVR lift, scaling personalization to 365+ days of history.

cs.IR↗

arXiv2026

CHOIR: Contact-aware 4D Hand-Object Interaction Reconstruction

We ask whether everyday open-world monocular videos can be turned into reusable 4D interaction primitives: articulated hand motion, object shape with 6D pose over time, and the when/where of contact. Such a capability would enable scalable mining of real interactions and, beyond reconstruction, support scene-aware synthesis and planning. However, reconstructing hand-object interaction (HOI) from challenging monocular videos remains difficult: methods often assume known objects or curated scenes, and separately estimated hands and objects easily become misaligned under clutter, occlusion, and unseen object geometries. Targeting this setting, we present CHOIR, a Contact-aware HOI Reconstruction framework for a monocular camera, using contact as an explicit coupling signal between hands and objects. CHOIR first initializes a coarse, contact-agnostic 4D HOI sequence from open-world visual priors. It then introduces a generative HOI spatial rectification module to predict ray-depth corrections and rectify hand-object relative placement, then derive initial per-frame contact correspondences on the rectified geometry. Last, a contact-aware joint optimization with dynamically updated contact constraints enforces geometric, temporal, and contact consistency. Experiments on controlled and challenging videos show that CHOIR improves object reconstruction, physical plausibility, and temporal consistency over state-of-the-art methods.

cs.CV↗

arXiv2026

AI-Assisted Competency Assessment from Egocentric Video in Simulation-Based Nursing Education

Assessing learner competency in clinical simulation requires expert observation that is time-intensive, difficult to scale, and subject to inter-rater variability. Vision-language models have emerged as a promising tool for understanding complex visual behavior. In this work, we investigate whether visual observations can provide educationally meaningful signals for competency assessment through a three-stage framework that (1) extracts action timelines from egocentric nursing simulation video using frozen visual encoders and few-shot learning, (2) derives sequence-level features and per-session recognition metrics, and (3) relates these to instructor-rated competency. Across 22 densely annotated sessions (3.8 hours, 493 actions), a frozen DINOv2 backbone with HMM Viterbi decoding achieves 57.4% MOF in leave-one-out 1-shot recognition. Surprisingly, we observe a negative trend between recognition accuracy and competency (rho = -0.524, p = 0.012 for mIoU), robust to six confound controls: more competent students produce diverse, harder-to-classify workflows, while simple sequence features show no such relationship. Per-item analysis identifies patient safety protocols and team communication as the expected behaviors most reflected in this pattern, and process model comparisons reveal that higher-competency students exhibit more protocol-consistent action transitions. These findings suggest that recognition accuracy may complement predicted action timelines as a pedagogically informative signal in automated competency assessment.

cs.CV↗

arXiv2025

Learning to Solve PDEs on Neural Shape Representations

Solving partial differential equations (PDEs) on shapes underpins many shape analysis and engineering tasks; yet, prevailing PDE solvers operate on polygonal/triangle meshes while modern 3D assets increasingly live as neural representations. This mismatch leaves no suitable method to solve surface PDEs directly within the neural domain, forcing explicit mesh extraction or per-instance residual training, preventing end-to-end workflows. We present a novel, meshfree formulation that learns a local update operator conditioned on neural (local) shape attributes, enabling surface PDEs to be solved directly where the (neural) data lives. The operator integrates naturally with prevalent neural surface representations, is trained once on a single representative shape, and generalizes across shape and topology variations, enabling accurate, fast inference without explicit meshing or per-instance optimization while preserving differentiability. Across analytic benchmarks (heat diffusion and Poisson equations on the sphere) and on diverse shapes and neural surface representations, our method achieves accuracy comparable to classical solvers while enabling a unified, end-to-end pipeline across neural and traditional surface representations. Our source code and project page: https://welschinger.github.io/Learning-to-Solve-PDEs-on-Neural-Shape-Representations/.

cs.LG↗

arXiv2025

AutoBrep: Autoregressive B-Rep Generation with Unified Topology and Geometry

The boundary representation (B-Rep) is the standard data structure used in Computer-Aided Design (CAD) for defining solid models. Despite recent progress, directly generating B-Reps end-to-end with precise geometry and watertight topology remains a challenge. This paper presents AutoBrep, a novel Transformer model that autoregressively generates B-Reps with high quality and validity. AutoBrep employs a unified tokenization scheme that encodes both geometric and topological characteristics of a B-Rep model as a sequence of discrete tokens. Geometric primitives (i.e., surfaces and curves) are encoded as latent geometry tokens, and their structural relationships are defined as special topological reference tokens. Sequence order in AutoBrep naturally follows a breadth first traversal of the B-Rep face adjacency graph. At inference time, neighboring faces and edges along with their topological structure are progressively generated. Extensive experiments demonstrate the advantages of our unified representation when coupled with next-token prediction for B-Rep generation. AutoBrep outperforms baselines with better quality and watertightness. It is also highly scalable to complex solids with good fidelity and inference speed. We further show that autocompleting B-Reps is natively supported through our unified tokenization, enabling user-controllable CAD generation with minimal changes. Code is available at https://github.com/AutodeskAILab/AutoBrep.

cs.CV↗

arXiv2025

NegoCollab: A Common Representation Negotiation Approach for Heterogeneous Collaborative Perception

Collaborative perception improves task performance by expanding the perception range through information sharing among agents. . Immutable heterogeneity poses a significant challenge in collaborative perception, as participating agents may employ different and fixed perception models. This leads to domain gaps in the intermediate features shared among agents, consequently degrading collaborative performance. Aligning the features of all agents to a common representation can eliminate domain gaps with low training cost. However, in existing methods, the common representation is designated as the representation of a specific agent, making it difficult for agents with significant domain discrepancies from this specific agent to achieve proper alignment. This paper proposes NegoCollab, a heterogeneous collaboration method based on the negotiated common representation. It introduces a negotiator during training to derive the common representation from the local representations of each modality's agent, effectively reducing the inherent domain gap with the various local representations. In NegoCollab, the mutual transformation of features between the local representation space and the common representation space is achieved by a pair of sender and receiver. To better align local representations to the common representation containing multimodal information, we introduce structural alignment loss and pragmatic alignment loss in addition to the distribution alignment loss to supervise the training. This enables the knowledge in the common representation to be fully distilled into the sender.

cs.CV↗

arXiv2025

SAGE: Structure-Aware Generative Video Transitions between Diverse Clips

Video transitions aim to synthesize intermediate frames between two clips, but naive approaches such as linear blending introduce artifacts that limit professional use or break temporal coherence. Traditional techniques (cross-fades, morphing, frame interpolation) and recent generative inbetweening methods can produce high-quality plausible intermediates, but they struggle with bridging diverse clips involving large temporal gaps or significant semantic differences, leaving a gap for content-aware and visually coherent transitions. We address this challenge by drawing on artistic workflows, distilling strategies such as aligning silhouettes and interpolating salient features to preserve structure and perceptual continuity. Building on these strategies, we propose SAGE (Structure-Aware Generative vidEo transitions) as a simple yet effective zeroshot approach that combines structural guidance, provided via line maps and motion flow, with generative synthesis, enabling smooth, motion-consistent transitions without fine-tuning. Extensive experiments and comparison with current alternatives, namely [FILM, TVG, DiffMorpher, VACE, GI], demonstrate that SAGE outperforms both classical and the latest generative baselines on quantitative metrics and user studies for producing transitions between diverse clips. The simple method effectively bypasses the need to acquire suitable training data, which is particularly difficult in our creative setting involving diverse clips. Code is available via the project page at https://kan32501.github.io/sage.github.io/.

cs.CV↗

arXiv2025

AgenticMath: Enhancing LLM Reasoning via Agentic-based Math Data Generation

The creation of high-quality datasets to improve Large Language Model (LLM) reasoning remains a significant challenge, as current methods often suffer from generating low-quality/incorrect answers and limited information richness from available data sources. To address this, we propose AgenticMath, a novel agentic method for generating high-quality mathematical question-answer pairs to enhance the supervised fine-tuning of LLMs. Our method operates through four stages: (1) Seed Question Filter that selects questions with high information richness, complexity, and clarity; (2) an Agentic Question Rephrase step that employs a multi-agent system to generate diverse, logically consistent paraphrases; (3) an Answer Augment step where rewrite answers using chain-of-thought reasoning to enhance numerical and logical correctness, without reliance on human-provided labels; and (4) a final Question and Answer Evaluation that retains only the most superior pairs. Extensive experiments demonstrate that, fine-tuning 3B-8B parameter LLMs on AgenticMath generated datasets (comprising only 30-60K math samples) achieves competitive or superior performance on diverse in domain and out-of-domain mathematical reasoning benchmarks compared to baselines trained on much more data (e.g., 400K or 2.3M samples). Our work demonstrates that targeted, high-quality data generation is a more efficient path to improving mathematical reasoning in LLMs than large-scale, low-quality alternatives.

cs.CL↗

arXiv2025

Can GRPO Boost Complex Multimodal Table Understanding?

Existing table understanding methods face challenges due to complex table structures and intricate logical reasoning. While supervised finetuning (SFT) dominates existing research, reinforcement learning (RL), such as Group Relative Policy Optimization (GRPO), has shown promise but struggled with low initial policy accuracy and coarse rewards in tabular contexts. In this paper, we introduce Table-R1, a three-stage RL framework that enhances multimodal table understanding through: (1) Warm-up that prompts initial perception and reasoning capabilities, (2) Perception Alignment GRPO (PA-GRPO), which employs continuous Tree-Edit-Distance Similarity (TEDS) rewards for recognizing table structures and contents, and (3) Hint-Completion GRPO (HC-GRPO), which utilizes fine-grained rewards of residual steps based on the hint-guided question. Extensive experiments demonstrate that Table-R1 can boost the model's table reasoning performance obviously on both held-in and held-out datasets, outperforming SFT and GRPO largely. Notably, Qwen2-VL-7B with Table-R1 surpasses larger specific table understanding models (e.g., Table-LLaVA 13B), even achieving comparable performance to the closed-source model GPT-4o on held-in datasets, demonstrating the efficacy of each stage of Table-R1 in overcoming initialization bottlenecks and reward sparsity, thereby advancing robust multimodal table understanding.

cs.CL↗

arXiv2025

B-repLer: Language-guided Editing of CAD Models

Computer-Aided Design (CAD) models, given their compactness and precision, remain the industry standard for designing and fabricating engineering objects. However, language-guided CAD editing is still in its infancy, largely due to missing semantic connection between user commands and underlying shape geometry, a problem exacerbated by the shortage of paired text-and-edit CAD datasets. While recent Multimodal Large Language Models (mLLMs) have attempted to bridge this gap, their reliance on CAD construction history -- often an expensive and hard to obtain input -- severely limits their expressiveness and restricts their usage. We present B-repLer, a novel framework that directly connects natural language with editing CAD models by operating in a learned latent space. Importantly, our approach bypasses the need for construction history, enabling semantic edits on a wide range of geometries, from simple prismatic parts to complex freeform shapes defined by B-Spline surfaces. To facilitate this research, we introduce BrepEDIT-240K, the first large-scale dataset for this task. We demonstrate how this paired dataset can be automatically generated, (user) validated, and scaled by leveraging existing CAD tools, in conjunction with mLLMs, to create the required paired data without relying on any external annotations. Our results demonstrate that B-repLer can accurately perform complex edits on complex CAD shapes, even when the input edit specifications are high-level and ambiguous to interpret, consistently producing valid, high-quality CAD outputs enabling a class of text-guided edits not previously possible.

cs.GR↗

arXiv2025

Constraining fuzzy dark matter with the 21-cm power spectrum from Cosmic Dawn and Reionization

The 21-cm signals from Cosmic Dawn and the Epoch of Reionization contain valuable information on cosmological structure formation dominated by dark matter. Measurements of the 21-cm power spectrum can thus probe certain dark matter candidates. Here we investigate the impacts of fuzzy dark matter (FDM) on the 21-cm signals, taking into account both the linear matter power spectrum and the halo mass function (HMF) in FDM cosmologies. The full FDM dynamics are implemented in reionization simulations, along with a new ansatz on modulation of the FDM HMF by the linear overdensity. Not only does the suppression of FDM halos on small scales give rise to delay of the signature epochs during cosmic reionization, but these epochs are also shortened relative to the cold dark matter cosmology. In addition, we find that while the FDM effects on the 21-cm power spectrum are dominated by its linear dynamics early in Cosmic Dawn, a correct FDM HMF resulting from nonlinear wave dynamics must be considered when X-ray heating begins. We forecast the constraints on the FDM model parameters from upcoming 21-cm power spectrum measurements by SKA1-Low (central area). In FDM cosmologies with $m_\mathrm{FDM}=10^{-21}$ eV, SKA1-Low will be able to constrain the boson mass to within $\sim10$% at 2$\sigma$ confidence with a mock 1080-hour observation, if the ionizing efficiency is mass independent. However, our results show that realistic astrophysical processes are degenerate with the FDM effects, which shall severely loosen the constraints on the boson mass from 21-cm power spectrum data alone.

astro-ph.CO↗

arXiv2025

Spin light-emitting devices in a 2D magnet

Emerging two-dimensional (2D) magnetic semiconductors represent transformative platforms to explore magneto-optics and opto-spintronic applications. Though 2D opto-spintronics has attracted tremendous research efforts in spin-dependent photodetectors and non-volatile memory components, the realization of one core application - spin-modulated light-emitting device (spin-LED) - remains elusive so far. Here we successfully realize prototype spin-LED integrated with a 2D semiconducting magnet CrSBr, demonstrating considerable electroluminescence (EL) down to bilayers. Intriguingly, the EL of the spin-LED is discovered to be directly manipulated by spin-flip and spin-canting transitions. Notably, spin-flip transitions enable unprecedented hysteretic behaviors of EL characteristics, while spin-canting transitions induce EL continuous modulation with robust anisotropy. This versatile manipulation is originated from the synergy of magnetic-order mediated excitonic transitions and spintronic transport. The prototype demonstration of spin-LED establishes an indispensable scheme of opto-spintronic devices leveraging 2D spin transitions and strong excitonic effects, presenting a critical step towards integrated 2D opto-spintronics.

physics.app-ph↗

arXiv2025

Building LOD Representation for 3D Urban Scenes

The advances in 3D reconstruction technology, such as photogrammetry and LiDAR scanning, have made it easier to reconstruct accurate and detailed 3D models for urban scenes. Nevertheless, these reconstructed models often contain a large number of geometry primitives, making interactive manipulation and rendering challenging, especially on resource-constrained devices like virtual reality platforms. Therefore, the generation of appropriate levels-of-detail (LOD) representations for these models is crucial. Additionally, automatically reconstructed 3D models tend to suffer from noise and lack semantic information. Dealing with these issues and creating LOD representations that are robust against noise while capturing the semantic meaning present significant challenges. In this paper, we propose a novel algorithm to address these challenges. We begin by analysing the properties of planar primitives detected from the input and group these primitives into multiple level sets by forming meaningful 3D structures. These level sets form the nodes of our innovative LOD-Tree. By selecting nodes at appropriate depths within the LOD-Tree, different LOD representations can be generated. Experimental results on real and complex urban scenes demonstrate the merits of our approach in generating clean, accurate, and semantically meaningful LOD representations.

cs.GR↗

arXiv2025

Strain Induced Robust Skyrmion lattice at Room Temperature in van der Waals Ferromagnet

Manipulating topological magnetic orders of two-dimensional (2D) magnets by strain, once achieved, offers enormous potential for future low-power flexible spintronic applications. In this work, by placing Fe3GaTe2 (FGaT), a room-temperature 2D ferromagnet, on flexible substrate, we demonstrate a field-free and robust formation of skyrmion lattice induced by strain. By applying a minimal strain of ~0.80% to pre-annealed FGaT flakes, the Magnetic Force Microscopy (MFM) tip directly triggers the transition from maze-like domains to an ordered skyrmion lattice while scanning the sample surface. The skyrmion lattice is rather stable against extensive cyclic mechanical testing (stretching, bending, and twisting over 2000 cycles each). It also exhibited stability across a wide range of magnetic fields (~2.9 kOe) and temperatures (~ 323 K), as well as long-term retention stability, highlighting its robustness and field free stabilization. The strain effect reduces the lattice symmetry and enhances the Dzyaloshinskii-Moriya interaction (DMI) of FGaT, thus stabilizing the skyrmion lattice. Our findings highlight the potential of FGaT for integrating magnetic skyrmions into future low-power-consumption flexible spintronics devices.

cond-mat.mtrl-sci↗