papers

Publications (7)

physics.soc-ph2018

Examining effect of architectural adjustment on pedestrian crowd flow at bottleneck

Xiaomeng Shi, Zhirui Ye, Nirajan Shiwakoti +2

Recent advances in bottleneck studies have highlighted that different architectural adjustments at the exit may reduce the probability of clogging at the exit thereby enhancing the…

cs.CL2026

Large Language Model as Token Compressor and Decompressor

Wenbing Li, Yiran Wang, Zikai Song +4

In this paper, we study whether an off-the-shelf LLM can be adapted into a discrete, variable-length token compressor and decompressor for long-context processing. To this end, we…

cs.GR2026

LATO.2: Factorized 3D Mesh Generation with Vertex and Topology Flow

Hang Long, Tianhao Zhao, Junkai Lin +8

Flow matching over carefully designed latent representations has recently emerged as a powerful paradigm for topology-aware mesh generation. Existing approaches, however, model ver…

cs.AI2026

Toward Fine-Grained Forgetting:Attribute Unlearning for Multimodal Large Language Models

Junkai Lin, Junkai Chen, Siqi Hou +5

Multimodal large language models (MLLMs) exhibit strong vision--language capabilities but may also memorize and disclose sensitive information. Machine unlearning seeks to remove d…

cs.CV2025

MeshRipple: Structured Autoregressive Generation of Artist-Meshes

Junkai Lin, Hang Long, Huipeng Guo +8

Meshes serve as a primary representation for 3D assets. Autoregressive mesh generators serialize faces into sequences and train on truncated segments with sliding-window inference…

cs.CV2026

SubdivAR: Autoregressive Next-Scale Prediction for Neural Mesh Subdivision

Huipeng Guo, Zikai Song, Hang Long +7

Mesh subdivision is a fundamental operation for converting coarse, editable meshes into high-resolution surfaces, with broad applications in digital asset creation. Classical rule-…

cs.AI2026

QFCQT: A Chaotically Gated Quantformer Framework for Volatile Time-Series Forecasting

Junkai Lin, Siqi Hou, Raymond Lee

Forecasting non-stationary time series remains difficult due to long-range dependencies, local volatility bursts, structural shifts, and nonlinear oscillatory behaviors. Although T…