collaborators

7 papers

cs.CV2026

AV-SyncBench: Decoupled Benchmarking of Temporal and Semantic Audio-Visual Synchronization

Tianhong Zhou, Mingyang Han, Boyu Li +8

Audio-visual feature extraction is a fundamental component of multimodal understanding and generation tasks. However, existing evaluation protocols for feature extraction models ex…

cs.SD2026

FreeSonic: Training-Free Temporal-Aware Decoupled Attention for Precise Audio Editing

Yuxuan Jiang, Mingyang Han, Yusheng Dai +12

Text-to-audio (TTA) generation has made significant strides, yet achieving precise and consistent audio editing remains a major challenge. However, existing methods struggle to bal…

cs.CL2026

The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models

Zanlin Ni, Shenzhi Wang, Yang Yue +8

Diffusion Large Language Models (dLLMs) break the rigid left-to-right constraint of traditional LLMs, enabling token generation in arbitrary orders. Intuitively, this flexibility i…

cs.LG2026

SpiralFormer: Looped Transformers Can Learn Hierarchical Dependencies via Multi-Resolution Recursion

Chengting Yu, Xiaobo Shu, Yadao Wang +8

Recursive (looped) Transformers decouple computational depth from parameter depth by repeatedly applying shared layers, providing an explicit architectural primitive for iterative…

cs.LG2026

MeSH: Memory-as-State-Highways for Recursive Transformers

Chengting Yu, Xiaobo Shu, Yadao Wang +8

Recursive transformers reuse parameters and iterate over hidden states multiple times, decoupling compute depth from parameter depth. However, under matched compute, recursive mode…

cs.CL2026

YOCO++: Enhancing YOCO with KV Residual Connections for Efficient LLM Inference

You Wu, Ziheng Chen, Yizhen Zhang +6

Cross-layer key-value (KV) compression has been found to be effective in efficient inference of large language models (LLMs). Although they reduce the memory consumption of the KV…