8 papers
Entropy as a Structural Prior: How a Log-Barrier on DiT Belief Space Drives Musical Diversity and Development
Zixi Li, Youzhen Li
Confidence-based loss weighting is usually avoided in generative models because it accelerates errors when the model is confidently wrong, but this intuition breaks down in supervi…
A Closed-Form Upper Bound for Admissible Learning-Rate Steps in Belief-Space Dynamics
Zixi Li, Youzhen Li
Learning-rate steps are usually treated as hyperparameters. This paper isolates a local beliefspace calculation: when an update is modeled as a projected forward step on the probab…
Listwise Direct Preference Optimization with Multi-Dimensional Preference Mixing
Yuhui Sun, Xiyao Wang, Zixi Li +6
Recent alignment methods based on Direct Preference Optimization (DPO) reformulate preference learning as supervised optimization over pairwise comparisons, offering improved effic…
Reasoning: From Reflection to Solution
Zixi Li
What is reasoning? This question has driven centuries of philosophical inquiry, from Aristotle's syllogisms to modern computational complexity theory. In the age of large language…
Large Language Models for Pedestrian Safety: An Application to Predicting Driver Yielding Behavior at Unsignalized Intersections
Yicheng Yang, Zixian Li, Jean Paul Bizimana +3
Pedestrian safety is a critical component of urban mobility and is strongly influenced by the interactions between pedestrian decision-making and driver yielding behavior at crossw…
TreeGPT: Pure TreeFFN Encoder-Decoder Architecture for Structured Reasoning Without Attention Mechanisms
Zixi Li
We present TreeGPT, an attention-free neural architecture that explores the potential of pure TreeFFN encoder-decoder design for structured reasoning tasks. Unlike traditional tran…