Zuoqiang Shi

Reconstruction and Range Characterization for a Directional Confocal Non-Line-of-Sight Imaging Model

We study the reconstruction of a directional albedo field from confocal non-line-of-sight measurements. For mirror-symmetric vector fields in Sobolev spaces, radial preprocessing reduces the data to spherical means of the divergence with centers on the relay wall. Full data determine this divergence uniquely, with dive...

Weighted Laplacian Flow: A Deterministic Particle Flow with Provable Convergence

Weighted Laplacian Flow: A Deterministic Particle Flow with Exponential Convergence

We introduce weighted Laplacian flow (WLF), a deterministic particle-flow framework for sampling from a target distribution known only up to normalization. The proposed method evolves the logarithmic density ratio through a transport equation and determines the particle velocity from a target-weighted Poisson problem,...

OLEDLM: A Unified Language Model for OLED Molecular Design

This work proposes an inverse molecular design framework based on causal language models, and represents the first successful adaptation of LLMs specifically for the OLED domain, bridging the gap between generic molecular generation and the stringent structural requirements of optoelectronic materials.

Constructing mesoscale functionomics by neural dynamics subspace clustering

Function subspace clustering based on sparse Representation of Intrinsic Dynamics (FRID), an unsupervised approach for identifying neurons with shared microcircuit connectivity and information encoding properties (referred to as ‘Functionomics’) from mesoscale neural recordings significantly outperforms correlated-firi...

Mean-to-Score Discrete Diffusion: Posterior-Mean Denoisers for Score Entropy

A 170M-parameter M2S model trained on about 262B OpenWebText token slots outperforms the evaluated pure-uniform SEDD, GIDD, and Neural CTMC checkpoints at every tested sampling budget, reaching generative PPL $143.3$ at 128 steps versus $183.6$ for the strongest pure-uniform baseline.

UNIFUSION: Adapting Autoregressive Language Models into Discrete Diffusion under a Unified Reverse-Rate Objective

This work proposes a simple continual pre-training approach for directly adapting pretrained GPT2 checkpoints to uniform-noise diffusion, and establishes connections among SEDD, MDLM/GIDD, M2S, and Neural CTMC by expressing their conditional losses as a single generalized Kullback--Leibler objective over model reverse...