13 papers
Drag as Evidence: Motion-Grounded Latent Recomposition for Drag-Based Editing
Xinyu Pu, Hongsong Wang, Jie Gui +1
Modern image editors excel at semantic manipulation and visual synthesis, yet remain limited in precise spatial control, motivating the development of drag-based editing. However,…
ScenePilot: Grow-and-Repair Policy for Text-Driven 3D Indoor Scene Generation
Jiawei Zhang, Hongsong Wang, Pan Zhou
Text-driven 3D indoor scene generation has advanced from dataset-bound layout modeling to open-vocabulary synthesis with large language and vision-language models. Yet existing met…
PathRelax: Parallel-Path Relaxed Speculative Jacobi Decoding for Accelerating Auto-Regressive Text-to-Image Generation
Haodong Lei, Hongsong Wang, Bingxuan Dai +1
The growing need for high-resolution image generation in autoregressive text-to-image models has resulted in extended token sequences, significantly increasing computational costs…
Bilingual Text-to-Motion Generation: A New Benchmark and Baselines
Wanjiang Weng, Xiaofeng Tan, Xiangbo Shu +3
Text-to-motion generation holds significant potential for cross-linguistic applications, yet it is hindered by the lack of bilingual datasets and the poor cross-lingual semantic un…
Fast Inference of Visual Autoregressive Model with Adjacency-Adaptive Dynamical Draft Trees
Haodong Lei, Hongsong Wang, Xin Geng +2
Autoregressive (AR) image models achieve diffusion-level quality but suffer from sequential inference, requiring approximately 2,000 steps for a 576x576 image. Speculative decoding…
ReAlign: Text-to-Motion Generation via Step-Aware Reward-Guided Alignment
Wanjiang Weng, Xiaofeng Tan, Junbo Wang +3
Text-to-motion generation, which synthesizes 3D human motions from text inputs, holds immense potential for applications in gaming, film, and robotics. Recently, diffusion-based me…
IBNorm: Information-Bottleneck Inspired Normalization for Representation Learning
Xiandong Zou, Jia Li, Xiaotong Yuan +1
Normalization is fundamental to deep learning, but existing approaches such as BatchNorm, LayerNorm, and RMSNorm are variance-centric by enforcing zero mean and unit variance, stab…
Dragging with Geometry: From Pixels to Geometry-Guided Image Editing
Xinyu Pu, Hongsong Wang, Jie Gui +1
Interactive point-based image editing serves as a controllable editor, enabling precise and flexible manipulation of image content. However, most drag-based methods operate primari…
Benchmarking Gaslighting Attacks Against Speech Large Language Models
Jinyang Wu, Bin Zhu, Xiandong Zou +3
As Speech Large Language Models (Speech LLMs) become increasingly integrated into voice-based applications, ensuring their robustness against manipulative or adversarial input beco…
DreamCS: Geometry-Aware Text-to-3D Generation with Unpaired 3D Reward Supervision
Xiandong Zou, Ruihao Xia, Hongsong Wang +1
While text-to-3D generation has attracted growing interest, existing methods often struggle to produce 3D assets that align well with human preferences. Current preference alignmen…
ReAlign: Bilingual Text-to-Motion Generation via Step-Aware Reward-Guided Alignment
Wanjiang Weng, Xiaofeng Tan, Hongsong Wang +1
Bilingual text-to-motion generation, which synthesizes 3D human motions from bilingual text inputs, holds immense potential for cross-linguistic applications in gaming, film, and r…
HPS: Hard Preference Sampling for Human Preference Alignment
Xiandong Zou, Wanyu Lin, Yuchen Li +1
Aligning Large Language Model (LLM) responses with human preferences is vital for building safe and controllable AI systems. While preference optimization methods based on Plackett…
SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimization
Xiaofeng Tan, Hongsong Wang, Xin Geng +1
Text-to-motion generation is essential for advancing the creative industry but often presents challenges in producing consistent, realistic motions. To address this, we focus on fi…