10 papers
PETS: A Principled Framework Towards Optimal Trajectory Allocation for Efficient Test-Time Self-Consistency
Zhangyi Liu, Huaizhi Qu, Xiaowei Yin +4
Test-time scaling can improve model performance by aggregating stochastic reasoning trajectories. However, achieving sample-efficient test-time self-consistency under a limited bud…
Multi-Agent Debate for LLM Judges with Adaptive Stability Detection
Tianyu Hu, Zhen Tan, Song Wang +2
With advancements in reasoning capabilities, Large Language Models (LLMs) are increasingly employed for automated judgment tasks. While LLMs-as-Judges offer promise in automating e…
EditCast3D: Single-Frame-Guided 3D Editing with Video Propagation and View Selection
Huaizhi Qu, Ruichen Zhang, Shuqing Luo +5
Recent advances in foundation models have driven remarkable progress in image editing, yet their extension to 3D editing remains underexplored. A natural approach is to replace the…
RTGS: Real-Time 3D Gaussian Splatting SLAM via Multi-Level Redundancy Reduction
Leshu Li, Jiayin Qin, Jie Peng +8
3D Gaussian Splatting (3DGS) based Simultaneous Localization and Mapping (SLAM) systems can largely benefit from 3DGS's state-of-the-art rendering efficiency and accuracy, but have…
GEM: 3D Gaussian Splatting for Efficient and Accurate Cryo-EM Reconstruction
Huaizhi Qu, Xiao Wang, Gengwei Zhang +2
Cryo-electron microscopy (cryo-EM) has become a central tool for high-resolution structural biology, yet the massive scale of datasets (often exceeding 100k particle images) render…
VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction
Zhiwen Fan, Jian Zhang, Renjie Li +15
The rapid advancement of Large Multimodal Models (LMMs) for 2D images and videos has motivated extending these models to understand 3D scenes, aiming for human-like visual-spatial…
DOGe: Defensive Output Generation for LLM Protection Against Knowledge Distillation
Pingzhi Li, Zhen Tan, Mohan Zhang +3
Large Language Models (LLMs) represent substantial intellectual and economic investments, yet their effectiveness can inadvertently facilitate model imitation via knowledge distill…
Efficient MAP Estimation of LLM Judgment Performance with Prior Transfer
Huaizhi Qu, Inyoung Choi, Zhen Tan +6
LLM ensembles are widely used for LLM judges. However, how to estimate their accuracy, especially in an efficient way, is unknown. In this paper, we present a principled maximum a…
LucidAtlas: Learning Uncertainty-Aware, Covariate-Disentangled, Individualized Atlas Representations
Yining Jiao, Sreekalyani Bhamidi, Huaizhi Qu +11
The goal of this work is to develop principled techniques to extract information from high dimensional data sets with complex dependencies in areas such as medicine that can provid…
Harnessing Your DRAM and SSD for Sustainable and Accessible LLM Inference with Mixed-Precision and Multi-level Caching
Jie Peng, Zhang Cao, Huaizhi Qu +5
Although Large Language Models (LLMs) have demonstrated remarkable capabilities, their massive parameter counts and associated extensive computing make LLMs' deployment the main pa…