arXiv subjects

Yishen Li

Publications and source records attributed to Yishen Li.

6 recordsLinked to original sources

arXiv2026

Domain-Adaptive Deep Joint Source-Channel Coding for Image Classification

Deep joint source--channel coding (Deep JSCC) enables visual semantic transmission by mapping inputs directly to channel symbols and task outputs, but its performance can deteriorate under distribution shifts between training and deployment domains. We study single-source domain adaptation for task-oriented Deep JSCC and formulate a classification-capacity-invariance (CCI) function to characterize how the available channel capacity and class-conditional cross-domain invariance affect target domain classification accuracy. A scalar linear analysis of source-domain-optimal solutions and a controlled shallow nonlinear validation show that target domain classification accuracy can vary non-monotonically with the invariance constraint and with available capacity along separate control paths obtained by varying the transmitted dimension or CSNR. We then propose a domain-adaptive Deep JSCC framework that combines pseudo-label-based class-level adversarial alignment with supervised contrastive learning on confidence-filtered target samples. Experiments on digit and PACS datasets over AWGN and Rayleigh fading channels demonstrate improved target domain generalization without introducing additional inference-time networks. On SVHN $\rightarrow$ MNIST, the proposed method achieves 98.15\% target-domain accuracy at a CSNR of 10 dB.

cs.IT↗

arXiv2026

MASFactory: A Graph-centric Framework for Orchestrating LLM-Based Multi-Agent Systems with Vibe Graphing

Large language model-based (LLM-based) multi-agent systems (MAS) are increasingly used to extend agentic problem solving via role specialization and collaboration. MAS workflows can be naturally modeled as directed computation graphs, where nodes execute agents or sub-workflows and edges encode dependencies and message passing. However, implementing complex graph workflows in current frameworks still requires substantial manual effort, offers limited reuse, and makes it difficult to integrate heterogeneous external context sources. To overcome these limitations, we present MASFactory, a graph-centric framework for orchestrating LLM-based MAS. It introduces Vibe Graphing, a human-in-the-loop approach that compiles natural-language intent into an editable workflow specification and then into an executable graph. In addition, the framework provides reusable components, skill support, multimodal message handling, and pluggable context integration, as well as a visualizer for topology preview, runtime tracing, and human-in-the-loop interaction. We evaluate MASFactory on seven public benchmarks, validating both reproduction consistency for representative MAS methods and the effectiveness of Vibe Graphing. Our code (https://github.com/BUPT-GAMMA/MASFactory, licensed under Apache-2.0) and video demonstration (https://youtu.be/ANynzVfY32k) are publicly available.

cs.CL↗

arXiv2026

Deep Joint Source-Channel Coding for Wireless Video Transmission with Asymmetric Context

In this paper, we propose a high-efficiency deep joint source-channel coding (JSCC) method for video transmission based on conditional coding with asymmetric context. The conditional coding-based neural video compression requires to predict the encoding and decoding conditions from the same context which includes the same reconstructed frames. However in JSCC schemes which fall into pseudo-analog transmission, the encoder cannot infer the same reconstructed frames as the decoder even a pipeline of the simulated transmission is constructed at the encoder. In the proposed method, without such a pipeline, we guide and design neural networks to learn encoding and decoding conditions from asymmetric contexts. Additionally, we introduce feature propagation, which allows intermediate features to be independently propagated at the encoder and decoder and help to generate conditions, enabling the framework to greatly leverage temporal correlation while mitigating the problem of error accumulation. To further exploit the performance of the proposed transmission framework, we implement content-adaptive coding which achieves variable bandwidth transmission using entropy models and masking mechanisms. Experimental results demonstrate that our method outperforms existing deep video transmission frameworks in terms of performance and effectively mitigates the error accumulation. By mitigating the error accumulation, our schemes can reduce the frequency of inserting intra-frame coding modes, further enhancing performance.

eess.IV↗

arXiv2025

T2VUnlearning: A Concept Erasing Method for Text-to-Video Diffusion Models

Recent advances in text-to-video (T2V) diffusion models have significantly enhanced the quality of generated videos. However, their capability to produce explicit or harmful content introduces new challenges related to misuse and potential rights violations. To address this newly emerging threat, we propose unlearning-based concept erasing as a solution. First, we adopt negatively-guided velocity prediction fine-tuning and enhance it with prompt augmentation to ensure robustness against prompts refined by large language models (LLMs). Second, to achieve precise unlearning, we incorporate mask-based localization regularization and concept preservation regularization to preserve the model's ability to generate non-target concepts. Extensive experiments demonstrate that our method effectively erases a specific concept while preserving the model's generation capability for all other concepts, outperforming existing methods. We provide the unlearned models in \href{https://github.com/VDIGPKU/T2VUnlearning.git}{https://github.com/VDIGPKU/T2VUnlearning.git}.

cs.CV↗

arXiv2010

Designable integrability of the variable coefficient nonlinear Schrödinger equation

The designable integrability(DI) of the variable coefficient nonlinear Schrödinger equation (VCNLSE) is first introduced by construction of an explicit transformation which maps VCNLSE to the usual nonlinear Schrödinger equation(NLSE). One novel feature of VCNLSE with DI is that its coefficients can be designed artificially and analytically by using transformation. A special example between nonautonomous NLSE and NLSE is given here. Further, the optical super-lattice potentials (or periodic potentials) and multi-well potentials are designed, which are two kinds of important potential in Bose-Einstein condensation(BEC) and nonlinear optical systems. There are two interesting features of the soliton of the VCNLSE indicated by the analytic and exact formula. Specifically, its the profile is variable and its trajectory is not a straight line when it evolves with time $t$.

nlin.SI↗

arXiv1998

Binary Nonlinearization of AKNS Spectral Problem under Higher-Order Symmetry Constraints

Binary nonlinearization of AKNS spectral problem is extended to the cases of higher-order symmetry constraints. The Hamiltonian structures, Lax representations, $r$-matrices and integrals of motion in involution are explicitly proposed for the resulting constrained systems in the cases of the first four orders. The obtained integrals of motion are proved to be functionally independent and thus the constrained systems are completely integrable in the Liouville sense.

solv-int↗