papers

Publications (9)

cs.CL2020

Asking Questions the Human Way: Scalable Question-Answer Generation from Text Corpus

Bang Liu, Haojie Wei, Di Niu +2

The ability to ask questions is important in both human and machine intelligence. Learning to ask questions helps knowledge acquisition, improves question-answering and machine rea…

cs.SD2025

UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity MoE

Zhenyu Liu, Yunxin Li, Xuanyu Zhang +13

Recent advances in unified multimodal models indicate a clear trend towards comprehensive content generation. However, the auditory domain remains a significant challenge, with mus…

cs.CV2024

CasSR: Activating Image Power for Real-World Image Super-Resolution

Haolan Chen, Jinhua Hao, Kai Zhao +4

The objective of image super-resolution is to generate clean and high-resolution images from degraded versions. Recent advancements in diffusion modeling have led to the emergence…

cs.CL2026

Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs

Zhenyu Liu, Xuanyu Zhang, Yunxin Li +10

The paper identifies gradient conflicts between acoustic and semantic modeling as the cause of modality interference in full-duplex spoken language models and proposes Lychee-FD, a…

#full-duplex spoken language models#modality interference#hierarchical parameter separation#semantic alignment
cs.CV2023

AdSEE: Investigating the Impact of Image Style Editing on Advertisement Attractiveness

Liyao Jiang, Chenglin Li, Haolan Chen +5

Online advertisements are important elements in e-commerce sites, social media platforms, and search engines. With the increasing popularity of mobile browsing, many online ads are…

cs.LG2025

Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing

Kunfeng Lai, Zhenheng Tang, Xinglin Pan +7

Model merging aggregates Large Language Models (LLMs) finetuned on different tasks into a stronger one. However, parameter conflicts between models leads to performance degradation…

cs.CV2026

SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation

Jiaming Zhang, Shengming Cao, Rui Li +8

Preserving first-frame identity while ensuring precise motion control is a fundamental challenge in human image animation. The Image-to-Motion Binding process of the dominant Refer…

cs.AI2020

QBSUM: a Large-Scale Query-Based Document Summarization Dataset from Real-world Applications

Mingjun Zhao, Shengli Yan, Bang Liu +6

Query-based document summarization aims to extract or generate a summary of a document which directly answers or is relevant to the search query. It is an important technique that…

cs.CV2021

Deep Point Set Resampling via Gradient Fields

Haolan Chen, Bi'an Du, Shitong Luo +1

3D point clouds acquired by scanning real-world objects or scenes have found a wide range of applications including immersive telepresence, autonomous driving, surveillance, etc. T…