16 papers
Regular integral models of Shimura varieties and a conjecture of Pappas
Jie Yang, Ioannis Zachos, Zhihao Zhao
We construct regular integral models for a class of Shimura varieties of symplectic and orthogonal type with maximal parahoric level at an odd prime . These models are defined o…
SafeStage: Evaluating Safety Before, During, and After Vision-Language-Conditioned Robot Manipulation
Jinzhu Luo, Qi Zhang, Wei Wang +1
Vision-language-conditioned robot policies integrate perception, language understanding, and control for general-purpose manipulation. However, existing evaluations often focus on…
COEC: Calibrated Orthogonal-Equivalence Compensation for Structured Pruning of Large Language Models
Peiqi Yu, Nam Ling, Wei Wang +1
Structured pruning reduces the size and inference cost of large language models (LLMs) by removing weight columns, but the resulting output error can degrade accuracy. Existing tra…
Role-Conditioned Sub-Token Routing for Efficient Vision-Language-Action Policies
Wei Jiang, Wei Wang
Vision-Language-Action (VLA) models process long multimodal token sequences, making inference expensive in both memory and computation. Existing efficiency methods mainly reduce vi…
CORAM: Coherent Orthogonal Rotation for Model Merging
Xinyi Sui, Ziran Liu, Nam Ling +2
Merging finetuned models combines specialized capabilities without joint training or access to the original data. Most methods operate by linear arithmetic in Euclidean weight spac…
CORA: Per-Slice Coherent Orthogonal Rotation for SVD-based Low-Rank Adaptation
Pengcheng Wang, Ziran Liu, Wei Wang +1
Parameter-Efficient Fine-Tuning (PEFT) commonly adapts pretrained weights through low-rank updates, and recent methods further exploit the singular value decomposition (SVD) of the…
Geometric and Spectral Alignment for Deep Neural Network II
Ziran Liu, Wei Wang, Jinhao Wang +5
This paper develops the angular and static-channel component of Geometric and Spectral Alignment for residual Jacobian chains. Starting from Cartan-coordinate rigidity and fitted e…
Geometric and Spectral Alignment for Deep Neural Network I
Ziran Liu, Wei Wang, Jinhao Wang +5
Deep residual architectures are modeled as products of near-identity Jacobians. This paper proves deterministic quotient-geometric estimates for singular spectra of Frobenius-norma…
PAT-VCM: Plug-and-Play Auxiliary Tokens for Video Coding for Machines
Wei Jiang, Wei Wang
Existing video coding for machines is often trained for a specific downstream task and model. As a result, the compressed representation becomes tightly coupled to the end task, ma…
From Pixels to Nucleotides: End-to-End Token-Based Video Compression for DNA Storage
Cihan Ruan, Lebin Zhou, Bingqing Zhao +8
DNA-based storage has emerged as a promising approach to the global data crisis, offering molecular-scale density and millennial-scale stability at low maintenance cost. Over the p…
Sub-Token Routing for KV Cache Compression
Wei Jiang, Wei Wang
Transformer inference often requires a large KV cache, especially for long-context language modeling and multimodal generation. Existing compression methods usually reduce cache co…
Analysis of Converged 3D Gaussian Splatting Solutions: Density Effects and Prediction Limit
Zhendong Wang, Cihan Ruan, Jingchuan Xiao +5
We investigate what structure emerges in 3D Gaussian Splatting (3DGS) solutions from standard multi-view optimization. We term these Rendering-Optimal References (RORs) and analyze…
Efficient Post-Training Pruning of Large Language Models with Statistical Correction
Peiqi Yu, Jinhao Wang, Xinyi Sui +3
Post-training pruning is an effective approach for reducing the size and inference cost of large language models (LLMs), but existing methods often face a trade-off between pruning…
SCONE: A Practical, Constraint-Aware Plug-in for Latent Encoding in Learned DNA Storage
Cihan Ruan, Lebin Zhou, Rongduo Han +6
DNA storage has matured from concept to practical stage, yet its integration with neural compression pipelines remains inefficient. Early DNA encoders applied redundancy-heavy cons…
LoD-Structured 3D Gaussian Splatting for Streaming Video Reconstruction
Xinhui Liu, Can Wang, Lei Liu +4
Free-Viewpoint Video (FVV) reconstruction enables photorealistic and interactive 3D scene visualization; however, real-time streaming is often bottlenecked by sparse-view inputs, p…
Collaborative Compression for Large-Scale MoE Deployment on Edge
Yixiao Chen, Yanyue Xie, Ruining Yang +6
The Mixture of Experts (MoE) architecture is an important method for scaling Large Language Models (LLMs). It increases model capacity while keeping computation cost low. However,…