arXiv subjects

Yu Feng

Publications and source records attributed to Yu Feng.

At least 91 records · Page 5Linked to original sources

arXiv2025

Beyond Random Masking: A Dual-Stream Approach for Rotation-Invariant Point Cloud Masked Autoencoders

Existing rotation-invariant point cloud masked autoencoders (MAE) rely on random masking strategies that overlook geometric structure and semantic coherence. Random masking treats patches independently, failing to capture spatial relationships consistent across orientations and overlooking semantic object parts that maintain identity regardless of rotation. We propose a dual-stream masking approach combining 3D Spatial Grid Masking and Progressive Semantic Masking to address these fundamental limitations. Grid masking creates structured patterns through coordinate sorting to capture geometric relationships that persist across different orientations, while semantic masking uses attention-driven clustering to discover semantically meaningful parts and maintain their coherence during masking. These complementary streams are orchestrated via curriculum learning with dynamic weighting, progressing from geometric understanding to semantic discovery. Designed as plug-and-play components, our strategies integrate into existing rotation-invariant frameworks without architectural changes, ensuring broad compatibility across different approaches. Comprehensive experiments on ModelNet40, ScanObjectNN, and OmniObject3D demonstrate consistent improvements across various rotation scenarios, showing substantial performance gains over the baseline rotation-invariant methods.

cs.CV↗

arXiv2025

Decomposition of global 2-SLE for $κ\in (4,8)$ and an application for critical FK-Ising model

We consider global 2-SLE$_κ$ $(η_1, η_2)$ in a topological rectangle with $κ\in (4,8)$. We derive the law of a random hitting point of the curves and show that, conditional on this random hitting point, the pair of two curves has the same law as Gaussian free field flow lines with proper boundary data. Using a similar idea, we derive the asymptotic of the probability for $η_1\capη_2=\emptyset$. As an application, we derive the asymptotic of the probability for the existence of two disjoint open paths in critical FK-Ising model.

math.PR↗

arXiv2025

Conformally covariant probabilities, operator product expansions, and logarithmic correlations in two-dimensional critical percolation

The large-scale behavior of two-dimensional critical percolation is expected to be described by a conformal field theory (CFT). Moreover, this putative CFT is believed to be of the logarithmic type, exhibiting logarithmic corrections to the most commonly encountered behavior of CFT correlations. While constructing a full-fledged percolation CFT is still an open problem, in this paper we prove various CFT features of the scaling limit of two-dimensional critical percolation. In particular, we provide the first rigorous proof of the emergence of logarithmic singularities in the scaling limit of connection probabilities. More precisely, we study several connectivity events, including arm-events and the events that a vertex is pivotal or belongs to the percolation backbone, whose probabilities have conformally covariant scaling limits and can be interpreted as CFT correlation functions. For some of these probabilities, we prove asymptotic expansions that can be regarded as CFT operator product expansions (OPEs). Our analysis identifies various logarithmic singularities and explains the geometric mechanism that produces them. In follow-up work, the results of this paper are used to define a percolation energy field and its logarithmic partner.

math-ph↗

arXiv2025

ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive

Large language model (LLM) decoding suffers from high latency due to fragmented execution across operators and heavy reliance on off-chip memory for data exchange and reduction. This execution model limits opportunities for fusion and incurs significant memory traffic and kernel launch overhead. While modern architectures such as NVIDIA Hopper provide distributed shared memory and low-latency intra-cluster interconnects, they expose only low-level data movement instructions, lacking structured abstractions for collective on-chip communication. To bridge this software-hardware gap, we introduce two cluster-level communication primitives, ClusterReduce and ClusterGather, which abstract common communication patterns and enable structured, high-speed data exchange and reduction between thread blocks within a cluster, allowing intermediate results to be on-chip without involving off-chip memory. Building on these abstractions, we design ClusterFusion, an execution framework that schedules communication and computation jointly to expand operator fusion scope by composing decoding stages such as QKV Projection, Attention, and Output Projection into a single fused kernels. Evaluations on H100 GPUs show that ClusterFusion outperforms state-of-the-art inference frameworks by 1.61x on average in end-to-end latency across different models and configurations. The source code is available at https://github.com/xinhao-luo/ClusterFusion.

cs.DC↗

arXiv2025

SLTarch: Towards Scalable Point-Based Neural Rendering by Taming Workload Imbalance and Memory Irregularity

Rendering is critical in fields like 3D modeling, AR/VR, and autonomous driving, where high-quality, real-time output is essential. Point-based neural rendering (PBNR) offers a photorealistic and efficient alternative to conventional methods, yet it is still challenging to achieve real-time rendering on mobile platforms. We pinpoint two major bottlenecks in PBNR pipelines: LoD search and splatting. LoD search suffers from workload imbalance and irregular memory access, making it inefficient on off-the-shelf GPUs. Meanwhile, splatting introduces severe warp divergence across GPU threads due to its inherent sparsity. To tackle these challenges, we propose SLTarch, an algorithm-architecture co-designed framework. At its core, SLTarch introduces SLTree, a dedicated subtree-based data structure, and LTcore, a specialized hardware architecture tailored for efficient LoD search. Additionally, we co-design a divergence-free splatting algorithm with our simple yet principled hardware augmentation, SPcore, to existing PBNR accelerators. Compared to a mobile GPU, SLTarch achieves 3.9$\times$ speedup and 98\% energy savings with negligible architecture overhead. Compared to existing accelerator designs, SLTarch achieves 1.8$\times$ speedup with 54\% energy savings.

cs.AR↗

arXiv2025

Conformal covariance of connection probabilities in the 2D critical FK-Ising model

We study connection probabilities between vertices of the square lattice for the critical random-cluster (FK) model with cluster weight 2, which is related to the critical Ising model. We consider the model on the plane and on domains conformally equivalent to the upper half-plane. We prove that, when appropriately rescaled, the connection probabilities between vertices in the domain or on the boundary have nontrivial limits, as the mesh size of the square lattice is sent to zero, and that those limits are conformally covariant. This provides an important step in the proof of the Delfino-Viti conjecture for FK-Ising percolation as well as an alternative proof of the conformal covariance of the Ising spin correlation functions. In an appendix, we also derive new exact formulas for some Ising boundary spin correlation functions.

math.PR↗

arXiv2025

StreamGrid: Streaming Point Cloud Analytics via Compulsory Splitting and Deterministic Termination

Point clouds are increasingly important in intelligent applications, but frequent off-chip memory traffic in accelerators causes pipeline stalls and leads to high energy consumption. While conventional line buffer techniques can eliminate off-chip traffic, they cannot be directly applied to point clouds due to their inherent computation patterns. To address this, we introduce two techniques: compulsory splitting and deterministic termination, enabling fully-streaming processing. We further propose StreamGrid, a framework that integrates these techniques and automatically optimizes on-chip buffer sizes. Our evaluation shows StreamGrid reduces on-chip memory by 61.3\% and energy consumption by 40.5\% with marginal accuracy loss compared to the baselines without our techniques. Additionally, we achieve 10.0$\times$ speedup and 3.9$\times$ energy efficiency over state-of-the-art accelerators.

cs.AR↗

arXiv2025

VQ-LLM: High-performance Code Generation for Vector Quantization Augmented LLM Inference

In this work, we design and implement VQ-LLM, an efficient fused Vector Quantization (VQ) kernel generation framework. We first introduce a software abstraction called codebook cache to optimize codebook access efficiency and support the integration of VQ with various computations. The codebook cache adaptively stores different entries across the GPU's memory hierarchy, including off-chip global memory, on-chip shared memory, and registers. Centered around the codebook cache, we design an efficient computation engine that optimizes memory traffic during computations involving codebooks. This compute engine adopts the codebook-centric dataflow and fusion optimizations. Additionally, we provide adaptive heuristics to tailor parameter selection in our optimizations to diverse VQ configurations. Our optimizations achieve an average latency reduction of 46.13% compared to unoptimized versions. Compared to existing open-source implementations, our methods decrease latency by 64.36% to 99.1%. A final comparison with state-of-the-art element-wise quantization methods like AWQ and KVQuant shows that our VQ-LLM is practically viable, achieving latencies close or even better latencies to those at equivalent bit-widths, potentially offering greater accuracy.

cs.DC↗

arXiv2025

SMPL Normal Map Is All You Need for Single-view Textured Human Reconstruction

Single-view textured human reconstruction aims to reconstruct a clothed 3D digital human by inputting a monocular 2D image. Existing approaches include feed-forward methods, limited by scarce 3D human data, and diffusion-based methods, prone to erroneous 2D hallucinations. To address these issues, we propose a novel SMPL normal map Equipped 3D Human Reconstruction (SEHR) framework, integrating a pretrained large 3D reconstruction model with human geometry prior. SEHR performs single-view human reconstruction without using a preset diffusion model in one forward propagation. Concretely, SEHR consists of two key components: SMPL Normal Map Guidance (SNMG) and SMPL Normal Map Constraint (SNMC). SNMG incorporates SMPL normal maps into an auxiliary network to provide improved body shape guidance. SNMC enhances invisible body parts by constraining the model to predict an extra SMPL normal Gaussians. Extensive experiments on two benchmark datasets demonstrate that SEHR outperforms existing state-of-the-art methods.

cs.CV↗

arXiv2025

STREAMINGGS: Voxel-Based Streaming 3D Gaussian Splatting with Memory Optimization and Architectural Support

3D Gaussian Splatting (3DGS) has gained popularity for its efficiency and sparse Gaussian-based representation. However, 3DGS struggles to meet the real-time requirement of 90 frames per second (FPS) on resource-constrained mobile devices, achieving only 2 to 9 FPS.Existing accelerators focus on compute efficiency but overlook memory efficiency, leading to redundant DRAM traffic. We introduce STREAMINGGS, a fully streaming 3DGS algorithm-architecture co-design that achieves fine-grained pipelining and reduces DRAM traffic by transforming from a tile-centric rendering to a memory-centric rendering. Results show that our design achieves up to 45.7 $\times$ speedup and 62.9 $\times$ energy savings over mobile Ampere GPUs.

cs.GR↗

arXiv2025

Lumina: Real-Time Mobile Neural Rendering by Exploiting Computational Redundancy

3D Gaussian Splatting (3DGS) has vastly advanced the pace of neural rendering, but it remains computationally demanding on today's mobile SoCs. To address this challenge, we propose Lumina, a hardware-algorithm co-designed system, which integrates two principal optimizations: a novel algorithm, S^2, and a radiance caching mechanism, RC, to improve the efficiency of neural rendering. S2 algorithm exploits temporal coherence in rendering to reduce the computational overhead, while RC leverages the color integration process of 3DGS to decrease the frequency of intensive rasterization computations. Coupled with these techniques, we propose an accelerator architecture, LuminCore, to further accelerate cache lookup and address the fundamental inefficiencies in Rasterization. We show that Lumina achieves 4.5x speedup and 5.3x energy reduction against a mobile Volta GPU, with a marginal quality loss (< 0.2 dB peak signal-to-noise ratio reduction) across synthetic and real-world datasets.

cs.AR↗

arXiv2025

My Words Imply Your Opinion: Reader Agent-based Propagation Enhancement for Personalized Implicit Emotion Analysis

The subtlety of emotional expressions makes implicit emotion analysis (IEA) particularly sensitive to user-specific characteristics. Current studies personalize emotion analysis by focusing on the author but neglect the impact of the intended reader on implicit emotional feedback. In this paper, we introduce Personalized IEA (PIEA) and present the RAPPIE model, which addresses subjective variability by incorporating reader feedback. In particular, (1) we create reader agents based on large language models to simulate reader feedback, overcoming the issue of ``spiral of silence effect'' and data incompleteness of real reader reaction. (2) We develop a role-aware multi-view graph learning to model the emotion interactive propagation process in scenarios with sparse reader information. (3) We construct two new PIEA datasets covering English and Chinese social media with detailed user metadata, addressing the text-centric limitation of existing datasets. Extensive experiments show that RAPPIE significantly outperforms state-of-the-art baselines, demonstrating the value of incorporating reader feedback in PIEA.

cs.CL↗

arXiv2025

An Efficient Private GPT Never Autoregressively Decodes

The wide deployment of the generative pre-trained transformer (GPT) has raised privacy concerns for both clients and servers. While cryptographic primitives can be employed for secure GPT inference to protect the privacy of both parties, they introduce considerable performance overhead.To accelerate secure inference, this study proposes a public decoding and secure verification approach that utilizes public GPT models, motivated by the observation that securely decoding one and multiple tokens takes a similar latency. The client uses the public model to generate a set of tokens, which are then securely verified by the private model for acceptance. The efficiency of our approach depends on the acceptance ratio of tokens proposed by the public model, which we improve from two aspects: (1) a private sampling protocol optimized for cryptographic primitives and (2) model alignment using knowledge distillation. Our approach improves the efficiency of secure decoding while maintaining the same level of privacy and generation quality as standard secure decoding. Experiments demonstrate a $2.1\times \sim 6.0\times$ speedup compared to standard decoding across three pairs of public-private models and different network conditions.

cs.CR↗

arXiv2025

Imputation-free and Alignment-free: Incomplete Multi-view Clustering Driven by Consensus Semantic Learning

In incomplete multi-view clustering (IMVC), missing data induce prototype shifts within views and semantic inconsistencies across views. A feasible solution is to explore cross-view consistency in paired complete observations, further imputing and aligning the similarity relationships inherently shared across views. Nevertheless, existing methods are constrained by two-tiered limitations: (1) Neither instance- nor cluster-level consistency learning construct a semantic space shared across views to learn consensus semantics. The former enforces cross-view instances alignment, and wrongly regards unpaired observations with semantic consistency as negative pairs; the latter focuses on cross-view cluster counterparts while coarsely handling fine-grained intra-cluster relationships within views. (2) Excessive reliance on consistency results in unreliable imputation and alignment without incorporating view-specific cluster information. Thus, we propose an IMVC framework, imputation- and alignment-free for consensus semantics learning (FreeCSL). To bridge semantic gaps across all observations, we learn consensus prototypes from available data to discover a shared space, where semantically similar observations are pulled closer for consensus semantics learning. To capture semantic relationships within specific views, we design a heuristic graph clustering based on modularity to recover cluster structure with intra-cluster compactness and inter-cluster separation for cluster semantics enhancement. Extensive experiments demonstrate, compared to state-of-the-art competitors, FreeCSL achieves more confident and robust assignments on IMVC task.

cs.CV↗

arXiv2025

CartoAgent: a multimodal large language model-powered multi-agent cartographic framework for map style transfer and evaluation

The rapid development of generative artificial intelligence (GenAI) presents new opportunities to advance the cartographic process. Previous studies have either overlooked the artistic aspects of maps or faced challenges in creating both accurate and informative maps. In this study, we propose CartoAgent, a novel multi-agent cartographic framework powered by multimodal large language models (MLLMs). This framework simulates three key stages in cartographic practice: preparation, map design, and evaluation. At each stage, different MLLMs act as agents with distinct roles to collaborate, discuss, and utilize tools for specific purposes. In particular, CartoAgent leverages MLLMs' visual aesthetic capability and world knowledge to generate maps that are both visually appealing and informative. By separating style from geographic data, it can focus on designing stylesheets without modifying the vector-based data, thereby ensuring geographic accuracy. We applied CartoAgent to a specific task centered on map restyling-namely, map style transfer and evaluation. The effectiveness of this framework was validated through extensive experiments and a human evaluation study. CartoAgent can be extended to support a variety of cartographic design decisions and inform future integrations of GenAI in cartography.

cs.HC↗

arXiv2025

Nonsymmetric traveling wave solution to a Hele-Shaw type tumor growth model

We consider a Hele-Shaw model that describes tumor growth subject to nutrient supply. The model is derived by taking the incompressible limit of porous medium type equations, and the boundary instability of this model was recently studied in \cite{feng2022tumor} using asymptotic analysis. In this paper, we further prove the existence of nonsymmetric traveling wave solutions to the model in a two dimensional tube-like domain, which reflect intrinsic boundary instability in tumor growth dynamics.

math.AP↗

arXiv2025

The HalfDome Multi-Survey Cosmological Simulations: N-body Simulations

Upcoming cosmological surveys have the potential to reach groundbreaking discoveries on multiple fronts, including the neutrino mass, dark energy, and inflation. Most of the key science goals require the joint analysis of datasets from multiple surveys to break parameter degeneracies and calibrate systematics. To realize such analyses, a large set of mock simulations that realistically model correlated observables is required. In this paper we present the N-body component of the HalfDome cosmological simulations, designed for the joint analysis of Stage-IV cosmological surveys, such as Rubin LSST, Euclid, SPHEREx, Roman, DESI, PFS, Simons Observatory, CMB-S4, and LiteBIRD. Our 300TB initial data release includes full-sky lightcones and halo catalogs between $z$=0--4 for 11 fixed cosmology realizations, as well as an additional run with local primordial non-Gaussianity ($f_{\rm NL}$=20). The simulations evolve $6144^3$ particles in a 3.75$\,h^{-1} {\rm Gpc}$ box, reaching a minimum halo mass of $\sim 6 \times 10^{12}\,h^{-1} M_\odot$ and maximum scale of $k \sim 1\,h{\rm Mpc}^{-1}$. Our data is publicly available: instructions to access the data and plans for future data releases can be found at https://halfdomesims.github.io.

astro-ph.CO↗

arXiv2025

Control-Oriented Modelling and Adaptive Parameter Estimation for Hybrid Wind-Wave Energy Systems

Hybrid wind-wave energy system, integrating floating offshore wind turbine and wave energy converters, has received much attention in recent years due to its potential benefit in increasing the power harvest density and reducing the levelized cost of electricity. Apart from the design complexities of the hybrid wind-wave energy systems, their energy conversion efficiency, power output smoothness and their safe operations introduce new challenges for their control system designs. Recent studies show that advanced model-based control strategies have the great potential to significantly improve their overall control performance. However the performance of these advanced control strategies rely on the computationally efficient control-oriented models with sufficient fidelity, which are normally difficult to derive due to the complexity of the hydro-, aero-dynamic effects and the couplings.In most available results, the hybrid wind-wave energy system models are established by using the Boundary Element Method, devoting to understanding the hydrodynamic responses and performance analysis. However, such models are complex and involved relatively heavy computational burden, which cannot be directly used for the advanced model-based control methods that are essential for improving power capture efficiency from implementing in practice. To overcome this issue, this paper proposes a control-oriented model of the hybrid windwave energy system with six degrees of freedom. First, ...

eess.SY↗