5 papers
Accurate Ensembles, Fragile Narratives: Multi-Scale Stacking and a Fidelity Audit of LLM-Generated Explanations for Credit Risk
Gregorius Reynaldi Pratama, Kuo-Kun Tseng
Credit scoring increasingly relies on models whose decision logic cannot be read off their parameters, in tension with supervisory expectations that adverse decisions be explainabl…
Linear-DPO: Linear Direct Preference Optimization for Diffusion and Flow-Matching Generative Models
Kesong Li, Yixuan Xu, Kuo-kun Tseng +3
Direct Preference Optimization (DPO) is successful for alignment in LLMs but still faces challenges in text-to-image generation. Existing studies are confined to denoising diffusio…
Fusion Matters: Length-Aware Analysis of Positional-Encoding Fusion in Transformers
Mohamed Amine Hallam, Kuo-Kun Tseng
Transformers require positional encodings to represent sequence order, yet most prior work focuses on designing new positional encodings rather than examining how positional inform…
RoboGSim: A Real2Sim2Real Robotic Gaussian Splatting Simulator
Xinhai Li, Jialin Li, Ziheng Zhang +6
Efficient acquisition of real-world embodied data has been increasingly critical. However, large-scale demonstrations captured by remote operation tend to take extremely high costs…
GaussianDiffusion: 3D Gaussian Splatting for Denoising Diffusion Probabilistic Models with Structured Noise
Xinhai Li, Huaibin Wang, Kuo-Kun Tseng
Text-to-3D, known for its efficient generation methods and expansive creative potential, has garnered significant attention in the AIGC domain. However, the pixel-wise rendering of…