Author name cluster

Zhixiang Chen

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

1 author row

NeurIPS Conference 2025 Conference Paper

HOI-Dyn: Learning Interaction Dynamics for Human-Object Motion Diffusion

Lin Wu
Zhixiang Chen
Jianglin Lan

Generating realistic 3D human-object interactions (HOIs) remains a challenging task due to the difficulty of modeling detailed interaction dynamics. Existing methods treat human and object motions independently, resulting in physically implausible and causally inconsistent behaviors. In this work, we present HOI-Dyn, a novel framework that formulates HOI generation as a driver-responder system, where human actions drive object responses. At the core of our method is a lightweight transformer-based interaction dynamics model that explicitly predicts how objects should react to human motion. To further enforce consistency, we introduce a residual-based dynamics loss that mitigates the impact of dynamics prediction errors and prevents misleading optimization signals. The dynamics model is used only during training, preserving inference efficiency. Through extensive qualitative and quantitative experiments, we demonstrate that our approach not only enhances the quality of HOI generation but also establishes a feasible metric for evaluating the quality of generated interactions. Project website: https: //wulin97. github. io/hoi-dyn

PDF Details

AAAI Conference 2025 Conference Paper

Sequential Joint Dependency Aware Human Pose Estimation with State Space Model

Hanxi Yin
Shaodi You
Jungong Han
Zhixiang Chen

In this paper, we present a sequential joint dependency aware model for monocular 2D-to-3D human pose estimation. While existing estimators leverage the (bi)directional joint dependency with graph convolutions and attention, we further propose to exploit the sequential dependency between joints with state space model (SSM). Our sequential dependency takes into consideration the information of kinematic chain, joint hierarchy and the body part. We design a sequential dependency aware representation to transform the pose data into sequential data for our pose SSM module. We tailor the SSM layer in the pose SSM module for pose estimation by learning joint-dependent parameters and introducing pose aware hidden state initialization. Extensive experiments are conducted on two datasets to validate the effectiveness of our proposed SSM module, and the results demonstrate that our pose estimator can deliver impressive performance.

PDF Details DOI

TCS Journal 2014 Journal Article

On the approximability of the exemplar adjacency number problem for genomes with gene repetitions

Zhixiang Chen
Bin Fu
Randy Goebel
Guohui Lin
Weitian Tong
Jinhui Xu
Boting Yang
Zhiyu Zhao

In this paper, we apply a measure, exemplar adjacency number, which complements and extends the well-studied breakpoint distance between two permutations, to measure the similarity between two genomes (or in general, between any two sequences drawn from the same alphabet). For two genomes G and H drawn from the same set of n gene families and containing gene repetitions, we consider the corresponding Exemplar Adjacency Number problem (EAN), in which we delete duplicated genes from G and H such that the resultant exemplar genomes (permutations) G and H have the maximum adjacency number. We obtain the following results. First, we prove that the one-sided 2-repetitive EAN problem, i. e. , when one of G and H is given exemplar and each gene occurs in the other genome at most twice, can be linearly reduced from the Maximum Independent Set problem. This implies that EAN does not admit any O ( n 0. 5 − ϵ ) -approximation algorithm, for any ϵ > 0, unless P = NP. This hardness result also implies that EAN, parameterized by the optimal solution value, is W[1]-hard. Secondly, we show that the two-sided 2-repetitive EAN problem has an O ( n 0. 5 ) -approximation algorithm, which is tight up to a constant factor.

Details DOI

TCS Journal 2013 Journal Article

On testing monomials in multivariate polynomials

Zhixiang Chen
Bin Fu
Yang Liu
Robert Schweller

This paper presents a summary of our initial work on developing a theory of testing monomials in multivariate polynomials. The central question is to ask whether a polynomial represented by certain economically compact structure has a multilinear monomial in its sum-product expansion. The complexity aspects of this problem and its variants are investigated with two objectives. One is to understand how this problem relates to critical problems in complexity, and if so to what extent. The other is to exploit possibilities of applying algebraic properties of polynomials to the study of those problems. A series of results about Π Σ Π and Π Σ polynomials is obtained in this paper, laying a basis for further study along this line. Several randomized and deterministic algorithms are devised for testing multilinear monomials or p -monomials in certain respective types of polynomials, where p is prime.

Details DOI

TCS Journal 1997 Journal Article

Learning counting functions with queries

Zhixiang Chen
Steven Homer

We investigate the problem of learning disjunctions of counting functions, which are general cases of parity and modulo functions, with equivalence and membership queries. We prove that, for any prime number p, the class of disjunctions of integer-weighted counting functions with modulus p over the domain Z q n (or Z n ) for any given integer q ⩾ 2 is polynomial time learnable using at most n + 1 equivalence queries, where the hypotheses issued by the learner are disjunctions of at most n counting functions with weights from Z p. In general, a counting function may have a composite modulus. We prove that, for any given integer q ⩾ 2, over the domain Z 2 n, the class of read-once disjunctions of Boolean-weighted counting functions with modulus q is polynomial-time learnable with only one equivalence query and O(n q ) membership queries.

Details DOI