arXiv subjects

Jiaxin Hu

Publications and source records attributed to Jiaxin Hu.

14 recordsLinked to original sources

arXiv2026

InstructVVT: Instruction-Driven Video Virtual Try-On without Auxiliary Spatial Priors

Video virtual try-on is a highly constrained editing task requiring the precise replacement of a target person's clothing while strictly preserving the original video's spatial structure and temporal dynamics. Existing methods heavily rely on auxiliary handcrafted spatial priors (e.g., masks, poses) for editing control. However, these priors are prone to failure in unconstrained real-world videos and often compress rich visual context into incomplete structural signals. Furthermore, standard reconstruction objectives fail to fully capture try-on-specific human preferences. To address these challenges, we propose InstructVVT, an instruction-driven and reference-guided video virtual try-on framework based on a Diffusion Transformer (DiT) that operates without inference-time spatial priors. Our core insight is to recover fine-grained control directly from the input triplet (source video, reference garment, and instruction) via a dual-level reference conditioning scheme. Specifically, an MLLM infers semantic edit tokens for target disambiguation and structural preservation, while a lightweight conditioning pathway explicitly injects fine-grained visual garment details. Finally, we design a try-on-specific reward and utilize the DiffusionNFT algorithm to align the model with human preferences. Extensive experiments on ViViD-S and TripVVT-Bench demonstrate that InstructVVT outperforms state-of-the-art open-source methods in garment fidelity, structural preservation, and temporal consistency, despite requiring fewer inference-time controls.

cs.CV↗

arXiv2026

Neural operator discovery from heterogeneous trajectories

Neural operators provide data-driven mappings for modeling dynamical systems. Extending them to families of systems typically requires explicit conditioning variables such as physical parameters, geometries, or boundary conditions. In many real-world settings, these quantities are unobserved. Here, we formulate neural operator discovery (NOD) as the problem of learning both shared solution operators and system-specific variation directly from heterogeneous trajectories without access to labeled governing factors. We introduce a factorized latent-conditioning formulation that jointly learns a neural operator and a low-dimensional latent representation through factorized prediction, trajectory-decoupled sampling, and dimension selection. Across diverse systems, the learned latent representation captures the intrinsic dimensionality of system variation and organizes system instances in a smooth and approximately invertible latent structure aligned with the underlying governing factors. This organization enables generalization to previously unseen system instances, including zero-shot extrapolation across regimes and stable long-horizon prediction. These results establish an interpretable paradigm for operator learning in the absence of explicit factor supervision.

cs.LG↗

arXiv2025

CogRec: A Cognitive Recommender Agent Fusing Large Language Models and Soar for Explainable Recommendation

Large Language Models (LLMs) have demonstrated a remarkable capacity in understanding user preferences for recommendation systems. However, they are constrained by several critical challenges, including their inherent "Black-Box" characteristics, susceptibility to knowledge hallucination, and limited online learning capacity. These factors compromise their trustworthiness and adaptability. Conversely, cognitive architectures such as Soar offer structured and interpretable reasoning processes, yet their knowledge acquisition is notoriously laborious. To address these complementary challenges, we propose a novel cognitive recommender agent called CogRec which synergizes the strengths of LLMs with the Soar cognitive architecture. CogRec leverages Soar as its core symbolic reasoning engine and leverages an LLM for knowledge initialization to populate its working memory with production rules. The agent operates on a Perception-Cognition-Action(PCA) cycle. Upon encountering an impasse, it dynamically queries the LLM to obtain a reasoned solution. This solution is subsequently transformed into a new symbolic production rule via Soar's chunking mechanism, thereby enabling robust online learning. This learning paradigm allows the agent to continuously evolve its knowledge base and furnish highly interpretable rationales for its recommendations. Extensive evaluations conducted on three public datasets demonstrate that CogRec demonstrates significant advantages in recommendation accuracy, explainability, and its efficacy in addressing the long-tail problem.

cs.AI↗

arXiv2025

FlatQuant: Flatness Matters for LLM Quantization

Recently, quantization has been widely used for the compression and acceleration of large language models (LLMs). Due to the outliers in LLMs, it is crucial to flatten weights and activations to minimize quantization error with equally spaced quantization points. Prior research explores various pre-quantization transformations to suppress outliers, such as per-channel scaling and Hadamard transformation. However, we observe that these transformed weights and activations can still exhibit steep and dispersed distributions. In this paper, we propose FlatQuant (Fast and Learnable Affine Transformation), a new post-training quantization approach that enhances the flatness of weights and activations. Our approach identifies optimal affine transformations for each linear layer, calibrated in hours via a lightweight objective. To reduce runtime overhead of affine transformation, we apply Kronecker product with two lightweight matrices, and fuse all operations in FlatQuant into a single kernel. Extensive experiments demonstrate that FlatQuant establishes a new state-of-the-art benchmark for quantization. For example, it achieves less than 1\% accuracy drop for W4A4 quantization on the LLaMA-3-70B model, surpassing SpinQuant by 7.5\%. Additionally, it provides up to 2.3x prefill speedup and 1.7x decoding speedup compared to the FP16 model. Code is available at: https://github.com/ruikangliu/FlatQuant.

cs.CL↗

arXiv2025

GFocal: A Global-Focal Neural Operator for Solving PDEs on Arbitrary Geometries

Transformer-based neural operators have emerged as promising surrogate solvers for partial differential equations, by leveraging the effectiveness of Transformers for capturing long-range dependencies and global correlations, profoundly proven in language modeling. However, existing methodologies overlook the coordinated learning of interdependencies between local physical details and global features, which are essential for tackling multiscale problems, preserving physical consistency and numerical stability in long-term rollouts, and accurately capturing transitional dynamics. In this work, we propose GFocal, a Transformer-based neural operator method that enforces simultaneous global and local feature learning and fusion. Global correlations and local features are harnessed through Nyström attention-based \textbf{g}lobal blocks and slices-based \textbf{focal} blocks to generate physics-aware tokens, subsequently modulated and integrated via convolution-based gating blocks, enabling dynamic fusion of multiscale information. GFocal achieves accurate modeling and prediction of physical features given arbitrary geometries and initial conditions. Experiments show that GFocal achieves state-of-the-art performance with an average 15.2\% relative gain in five out of six benchmarks and also excels in industry-scale simulations such as aerodynamics simulation of automotives and airfoils.

cs.LG↗

arXiv2025

Astra: Toward General-Purpose Mobile Robots via Hierarchical Multimodal Learning

Modern robot navigation systems encounter difficulties in diverse and complex indoor environments. Traditional approaches rely on multiple modules with small models or rule-based systems and thus lack adaptability to new environments. To address this, we developed Astra, a comprehensive dual-model architecture, Astra-Global and Astra-Local, for mobile robot navigation. Astra-Global, a multimodal LLM, processes vision and language inputs to perform self and goal localization using a hybrid topological-semantic graph as the global map, and outperforms traditional visual place recognition methods. Astra-Local, a multitask network, handles local path planning and odometry estimation. Its 4D spatial-temporal encoder, trained through self-supervised learning, generates robust 4D features for downstream tasks. The planning head utilizes flow matching and a novel masked ESDF loss to minimize collision risks for generating local trajectories, and the odometry head integrates multi-sensor inputs via a transformer encoder to predict the relative pose of the robot. Deployed on real in-house mobile robots, Astra achieves high end-to-end mission success rate across diverse indoor environments.

cs.RO↗

arXiv2024

FastAttention: Extend FlashAttention2 to NPUs and Low-resource GPUs

FlashAttention series has been widely applied in the inference of large language models (LLMs). However, FlashAttention series only supports the high-level GPU architectures, e.g., Ampere and Hopper. At present, FlashAttention series is not easily transferrable to NPUs and low-resource GPUs. Moreover, FlashAttention series is inefficient for multi- NPUs or GPUs inference scenarios. In this work, we propose FastAttention which pioneers the adaptation of FlashAttention series for NPUs and low-resource GPUs to boost LLM inference efficiency. Specifically, we take Ascend NPUs and Volta-based GPUs as representatives for designing our FastAttention. We migrate FlashAttention series to Ascend NPUs by proposing a novel two-level tiling strategy for runtime speedup, tiling-mask strategy for memory saving and the tiling-AllReduce strategy for reducing communication overhead, respectively. Besides, we adapt FlashAttention for Volta-based GPUs by redesigning the operands layout in shared memory and introducing a simple yet effective CPU-GPU cooperative strategy for efficient memory utilization. On Ascend NPUs, our FastAttention can achieve a 10.7$\times$ speedup compared to the standard attention implementation. Llama-7B within FastAttention reaches up to 5.16$\times$ higher throughput than within the standard attention. On Volta architecture GPUs, FastAttention yields 1.43$\times$ speedup compared to its equivalents in \texttt{xformers}. Pangu-38B within FastAttention brings 1.46$\times$ end-to-end speedup using FasterTransformer. Coupled with the propose CPU-GPU cooperative strategy, FastAttention supports a maximal input length of 256K on 8 V100 GPUs. All the codes will be made available soon.

cs.LG↗

arXiv2024

Evolutionary dynamics in stochastic nonlinear public goods games

Understanding the evolution of cooperation in multiplayer games is of vital significance for natural and social systems. An important challenge is that group interactions often leads to nonlinear synergistic effects. However, previous models mainly focus on deterministic nonlinearity where the arise of synergy or discounting effect is determined by certain conditions, ignoring uncertainty and stochasticity in real-world systems. Here, we develop a probabilistic framework to study the cooperative behavior in stochastic nonlinear public goods games. Through both analytical treatment and Monte Carlo simulations, we provide comprehensive understanding of social dilemmas with stochastic nonlinearity in both well-mixed and structured populations. We find that increasing the degree of nonlinearity makes synergy more advantageous when competing with discounting, thereby promoting cooperation. Interestingly, we show that network reciprocity loses effectiveness when the probability of synergy is small. Moreover, group size exhibits nonlinear effects on group cooperation regardless of the underlying structure. Our findings thus provide novel insights into how stochastic nonlinearity influences the emergence of prosocial behavior.

physics.soc-ph↗

arXiv2023

Multiway Spherical Clustering via Degree-Corrected Tensor Block Models

We consider the problem of multiway clustering in the presence of unknown degree heterogeneity. Such data problems arise commonly in applications such as recommendation system, neuroimaging, community detection, and hypergraph partitions in social networks. The allowance of degree heterogeneity provides great flexibility in clustering models, but the extra complexity poses significant challenges in both statistics and computation. Here, we develop a degree-corrected tensor block model with estimation accuracy guarantees. We present the phase transition of clustering performance based on the notion of angle separability, and we characterize three signal-to-noise regimes corresponding to different statistical-computational behaviors. In particular, we demonstrate that an intrinsic statistical-to-computational gap emerges only for tensors of order three or greater. Further, we develop an efficient polynomial-time algorithm that provably achieves exact clustering under mild signal conditions. The efficacy of our procedure is demonstrated through two data applications, one on human brain connectome project, and another on Peru Legislation network dataset.

math.ST↗

arXiv2022

The weak elliptic Harnack inequality revisited

In this paper we firstly derive the weak elliptic Harnack inequality from the generalized capacity condition, the tail estimate of jump measure and the Poincaré inequality, for any regular Dirichlet form without killing part on a measure metric space, by using the lemma of growth and the John-Nirenberg inequality. We secondly show several equivalent characterizations of the weak elliptic Harnack inequality for any (not necessarily regular) Dirichlet form. We thirdly present some consequences of the weak elliptic Harnack inequality.

math.AP↗

arXiv2022

A dichotomy on the self-similarity of graph-directed attractors

This paper seeks conditions that ensure that the attractor of a graph directed iterated function system (GD-IFS) cannot be realised as the attractor of a standard iterated function system (IFS). For a strongly connected directed graph, it is known that, if all directed circuits go through a vertex, then for any GD-IFS of similarities on $\mathbb{R}$ based on the graph and satisfying the convex open set condition (COSC), its attractor associated with this vertex is also the attractor of a (COSC) standard IFS. In this paper we show the following complementary result. If a directed circuit does not go through a vertex, then there exists a GD-IFS based on the graph such that the attractor associated with this vertex is not the attractor of any standard IFS of similarities. Indeed, we give algebraic conditions for such GD-IFS attractors not to be attractors of standard IFSs, and thus show that `almost-all' COSC GD-IFSs based on the graph have attractors associated with this vertex that are not the attractors of any COSC standard IFS.

math.DS↗

arXiv2021

Supervised tensor decomposition with features on multiple modes

Higher-order tensors have received increased attention across science and engineering. While most tensor decomposition methods are developed for a single tensor observation, scientific studies often collect side information, in the form of node features and interactions thereof, together with the tensor data. Such data problems are common in neuroimaging, network analysis, and spatial-temporal modeling. Identifying the relationship between a high-dimensional tensor and side information is important yet challenging. Here, we develop a tensor decomposition method that incorporates multiple feature matrices as side information. Unlike unsupervised tensor decomposition, our supervised decomposition captures the effective dimension reduction of the data tensor confined to feature space of interest. An efficient alternating optimization algorithm with provable spectral initialization is further developed. Our proposal handles a broad range of data types, including continuous, count, and binary observations. We apply the method to diffusion tensor imaging data from human connectome project and multi-relational political network data. We identify the key global connectivity pattern and pinpoint the local regions that are associated with available features. Our simulation code, R-package tensorregress, and datasets used in the paper are available at https://CRAN.R-project.org/package=tensorregress.

stat.ME↗

arXiv2017

The Davies method revisited for heat kernel upper bounds of regular Dirichlet forms on metric measure spaces

We apply the Davies method to prove that for any regular Dirichlet form on a metric measure space, an off-diagonal stable-type upper bound of the heat kernel is equivalent to the conjunction of the on-diagonal upper bound, a cutoff inequality on any two concentric balls, and the jump kernel upper bound, for any walk dimension. If in addition the jump kernel vanishes, that is, if the Dirichlet form is strongly local, we obtain sub-Gaussian upper bound. This gives a unified approach to obtaining heat kernel upper bounds for both the non-local and the local Dirichlet forms.

math.AP↗

arXiv2011

Inhomogeneous parabolic equations on unbounded metric measure spaces

We study inhomogeneous semilinear parabolic equations with source term f independent of time u_{t}=Δu+u^{p}+f(x) on a metric measure space, subject to the conditions that f(x)\geq 0 and u(0,x)=ϕ(x)\geq 0. By establishing Harnack-type inequalities in time t and some powerful estimates, we give sufficient conditions for non-existence, local existence, and global existence of weak solutions. This paper generalizes previous results on Euclidean spaces to general metric measure spaces.

math-ph↗