15 papers
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…
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…
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…
Adaptive Fused Prior Transfer for Controllable Generative Image Compression
Yifei Pei, Ying Liu, Nam Ling
At very low bitrates, image compression discards fine textures and local structures, while distortion-oriented reconstruction often produces over-smoothed images. Generative codecs…
What Did They Mean? How LLMs Resolve Ambiguous Social Situations across Perspectives and Roles
Qiming Yuan, Linyi Han, Nam Ling +1
People increasingly turn to large language models (LLMs) to interpret ambiguous social situations: a delayed text reply, an unusually cold supervisor, a teacher's mixed signals, or…
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…
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…
Thinking Like Van Gogh: Structure-Aware Style Transfer via Flow-Guided 3D Gaussian Splatting
Lebin Zhou, Jingchuan Xiao, Zhendong Wang +4
In 1888, Vincent van Gogh wrote, "I am seeking exaggeration in the essential." This principle, amplifying structural form while suppressing photographic detail, lies at the core of…
: A Large-Scale Multi-Modality Multi-View Synthesized Benchmark Dataset for Image Restoration and Content Creation
Yuanzhi Li, Lebin Zhou, Nam Ling +3
The gaming and entertainment industry is rapidly evolving, driven by immersive experiences and the integration of generative AI (GAI) technologies. Training such models effectively…
ISCS: Parameter-Guided Feature Pruning for Resource-Constrained Embodied Perception
Jinhao Wang, Nam Ling, Wei Wang +1
Prior studies in embodied AI consistently show that robust perception is critical for human-robot interaction, yet deploying high-fidelity visual models on resource-constrained age…
TVC: Tokenized Video Compression with Ultra-Low Bit Rate
Lebin Zhou, Cihan Ruan, Nam Ling +3
Tokenized visual representations have shown promise in image compression, yet their extension to video remains underexplored due to the challenges posed by complex temporal dynamic…
GameIR: A Large-Scale Synthesized Ground-Truth Dataset for Image Restoration over Gaming Content
Lebin Zhou, Kun Han, Nam Ling +2
Image restoration methods like super-resolution and image synthesis have been successfully used in commercial cloud gaming products like NVIDIA's DLSS. However, restoration over ga…