collaborators

21 papers

stat.ML2026

Symmetric Divergence and Normalized Similarity: A Unified Topological Framework for Representation Analysis

Yan Wang, Tianyang Hu

Topological Data Analysis (TDA) offers a principled, intrinsic lens for comparing neural representations. However, existing paired topological divergences (e.g., RTD) are limited b…

cs.CV2026

Autoregressive Visual Generation Needs a Prologue

Bowen Zheng, Weijian Luo, Guang Yang +2

In this work, we propose Prologue, an approach to bridging the reconstruction-generation gap in autoregressive (AR) image generation. Instead of modifying visual tokens to satisfy…

cs.LG2026

The Structural Origin of Attention Sink: Variance Discrepancy, Super Neurons, and Dimension Disparity

Siquan Li, Kaiqi Jiang, Jiacheng Sun +1

Despite the prevalence of the attention sink phenomenon in Large Language Models (LLMs), where initial tokens disproportionately monopolize attention scores, its structural origins…

cs.CV2026

Taming the Entropy Cliff: Variable Codebook Size Quantization for Autoregressive Visual Generation

Bowen Zheng, Weijian Luo, Guang Yang +2

Most discrete visual tokenizers rely on a default design: every position in the sequence shares the same codebook. Researchers try to scale the codebook size to get better reco…

cs.CV2026

Learning Discrete Autoregressive Priors with Wasserstein Gradient Flow

Bowen Zheng, Yihong Luo, Tianyang Hu

Discrete image tokenizers are commonly trained in two stages: first for reconstruction, and then with a prior model fitted to the frozen token sequences. This decoupling leaves the…

cs.CL2026

PrefixMemory-Tuning: Modernizing Prefix-Tuning by Decoupling the Prefix from Attention

Haonan Wang, Brian Chen, Siquan Li +4

Parameter-Efficient Fine-Tuning (PEFT) methods have become crucial for rapidly adapting large language models (LLMs) to downstream tasks. Prefix-Tuning, an early and effective PEFT…