arXiv subjects

Qipeng Zhang

Publications and source records attributed to Qipeng Zhang.

5 recordsLinked to original sources

arXiv2025

Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem

Agentic crafting requires LLMs to operate in real-world environments over multiple turns by taking actions, observing outcomes, and iteratively refining artifacts. Despite its importance, the open-source community lacks a principled, end-to-end ecosystem to streamline agent development. We introduce the Agentic Learning Ecosystem (ALE), a foundational infrastructure that optimizes the production pipeline for agentic model. ALE consists of three components: ROLL, a post-training framework for weight optimization; ROCK, a sandbox environment manager for trajectory generation; and iFlow CLI, an agent framework for efficient context engineering. We release ROME, an open-source agent grounded by ALE and trained on over one million trajectories. Our approach includes data composition protocols for synthesizing complex behaviors and a novel policy optimization algorithm, Interaction-Perceptive Agentic Policy Optimization (IPA), which assigns credit over semantic interaction chunks rather than individual tokens to improve long-horizon training stability. Empirically, we evaluate ROME within a structured setting and introduce Terminal Bench Pro, a benchmark with improved scale and contamination control. ROME demonstrates strong performance across benchmarks like SWE-bench Verified and Terminal Bench, proving the effectiveness of ALE.

cs.AI↗

arXiv2025

Bifurcation of limit cycles from a cubic reversible isochrone

This paper is devoted to study the limit cycle problem of a cubic reversible system with an isochronous center, when it is perturbed inside a class of polynomials. An upper bound of the number of limit cycles is obtained using the Abelian integral. The algebraic structure of the Abelian integral is acquired thanks to some iterative formulas, which differs in many aspects from other methods. Some numerical simulations verify the existence of limit cycles.

math.DS↗

arXiv2025

Limit cycles appearing from the perturbation of a cubic isochronous center

For a polynomial differential system $$\dot{x}=-y+\sum\limits_{i+j=3}α_{i,j}x^iy^j,\quad \dot{y}=x+\sum\limits_{i+j=3}β_{i,j}x^iy^j,$$ Pleshkan (Differ. Equations, 1969) proved that the origin is an isochronous center of this system iff it can be brought to one of $S^*_1$, $S^*_2$, $S^*_3$ or $S^*_4$. The bifurcation of limit cycles for these four types of isochronous differential systems have not yet been studied, except for $S^*_1$. This paper is devoted to study the limit cycle problem of $S^*_2$ when we perturb it with an arbitrary polynomial vector field. An upper bound of the number of limit cycles is obtained using the Abelian integral.

math.DS↗

arXiv2023

Sign Language Production with Latent Motion Transformer

Sign Language Production (SLP) is the tough task of turning sign language into sign videos. The main goal of SLP is to create these videos using a sign gloss. In this research, we've developed a new method to make high-quality sign videos without using human poses as a middle step. Our model works in two main parts: first, it learns from a generator and the video's hidden features, and next, it uses another model to understand the order of these hidden features. To make this method even better for sign videos, we make several significant improvements. (i) In the first stage, we take an improved 3D VQ-GAN to learn downsampled latent representations. (ii) In the second stage, we introduce sequence-to-sequence attention to better leverage conditional information. (iii) The separated two-stage training discards the realistic visual semantic of the latent codes in the second stage. To endow the latent sequences semantic information, we extend the token-level autoregressive latent codes learning with perceptual loss and reconstruction loss for the prior model with visual perception. Compared with previous state-of-the-art approaches, our model performs consistently better on two word-level sign language datasets, i.e., WLASL and NMFs-CSL.

cs.CV↗

arXiv2023

G2P-DDM: Generating Sign Pose Sequence from Gloss Sequence with Discrete Diffusion Model

The Sign Language Production (SLP) project aims to automatically translate spoken languages into sign sequences. Our approach focuses on the transformation of sign gloss sequences into their corresponding sign pose sequences (G2P). In this paper, we present a novel solution for this task by converting the continuous pose space generation problem into a discrete sequence generation problem. We introduce the Pose-VQVAE framework, which combines Variational Autoencoders (VAEs) with vector quantization to produce a discrete latent representation for continuous pose sequences. Additionally, we propose the G2P-DDM model, a discrete denoising diffusion architecture for length-varied discrete sequence data, to model the latent prior. To further enhance the quality of pose sequence generation in the discrete space, we present the CodeUnet model to leverage spatial-temporal information. Lastly, we develop a heuristic sequential clustering method to predict variable lengths of pose sequences for corresponding gloss sequences. Our results show that our model outperforms state-of-the-art G2P models on the public SLP evaluation benchmark. For more generated results, please visit our project page: \textcolor{blue}{\url{https://slpdiffusier.github.io/g2p-ddm}}

cs.CV↗