20 papers
TwinPrune: Density-Aware Two-Phase Token Pruning for Vision-Language Models
Kai Liu, Anqi Li, Junxian Li +4
We propose a unified spatial-density signal to score token importance for both inference phases: bipartite merge for prefill and KV eviction for decode, yielding measurable gains i…
VenusRL: A Fully Disaggregated Agentic RL System with Priority Scheduling and Scalable Interaction
Mingjun Zhang, Yucheng Li, Menghao Zhang +15
Agentic Reinforcement Learning (RL) trains LLM agents through multi-turn interactions with external tool environments. Its multi-turn nature exposes two system-level bottlenecks un…
InstanceControl: Controllable Complex Image Generation without Instance Labeling
Xiaoyu Liu, Huan Wang, Fan Li +4
Controllable image generation methods, such as ControlNet, have demonstrated a remarkable capacity to introduce visual conditions(e.g., depth maps) to guide image generation. Howev…
Illuminating Unified Multimodal Model for Free-form Interleaved Text-Image Generation
Chonghuinan Wang, Zhikai Chen, Chunwei Wang +9
The advancement of generative AI models capable of producing text and image marks a critical step forward in the realm of multimodal intelligence, particularly for tasks involving…
ShotCrop: Cropping Human-Centric Images into Cinematic Triple-Shot Compositions
Dehong Kong, Lina Lei, Lingtao Zheng +10
Prior work on aesthetic composition typically produces a single aesthetically pleasing crop, overlooking the narrative value of composing multiple shots from one scene. In practice…
Fast Image Super-Resolution via Consistency Rectified Flow
Jiaqi Xu, Wenbo Li, Haoze Sun +8
Diffusion models (DMs) have demonstrated remarkable success in real-world image super-resolution (SR), yet their reliance on time-consuming multi-step sampling largely hinders thei…
PermuQuant: Lowering Per-Group Quantization Error by Reordering Channels for Diffusion Models
Yongsen Cheng, Kai Liu, Kaiwen Tao +5
Large-scale visual generative models have achieved remarkable performance. However, their high computational and memory costs make deployment challenging in resource-constrained sc…
Accelerating Rectified Flow Models via Trajectory-Aware Caching
Xiao Liu, Kai Liu, Naiyang Guan +5
Diffusion and rectified flow (RF) models generate high-fidelity images and videos, but their iterative velocity-field evaluations are computationally expensive. Existing caching me…
GTR: Generation-Guided Visual Token Reduction for Separate-Encoder Unified Multimodal Models
Junxian Li, Kai Liu, Zizhong Ding +4
The development of separate-encoder Unified multimodal models (UMMs) comes with a rapidly growing inference cost due to dense visual token processing. In this paper, we focus on un…
How Much is Brain Data Worth for Machine Learning?
Lane Lewis, Zhixin Wang, David Schwab +1
If a person can solve a task, can measuring their brain make it easier to train a model to solve that task too? Recent NeuroAI work suggests that supplementing task training with n…
YOSE: You Only Select Essential Tokens for Efficient DiT-based Video Object Removal
Chenyang Wu, Lina Lei, Fan Li +6
Recent advances in Diffusion Transformer (DiT)-based video generation technologies have shown impressive results for video object removal. However, these methods still suffer from…
HP-Edit: A Human-Preference Post-Training Framework for Image Editing
Fan Li, Chonghuinan Wang, Lina Lei +9
Common image editing tasks typically adopt powerful generative diffusion models as the leading paradigm for real-world content editing. Meanwhile, although reinforcement learning (…
ColorFLUX: A Structure-Color Decoupling Framework for Old Photo Colorization
Bingchen Li, Zhixin Wang, Fan Li +5
Old photos preserve invaluable historical memories, making their restoration and colorization highly desirable. While existing restoration models can address some degradation issue…
PlanViz: Evaluating Planning-Oriented Image Generation and Editing for Computer-Use Tasks
Junxian Li, Kai Liu, Leyang Chen +7
Unified multimodal models (UMMs) have shown impressive capabilities in complex natural image generation. However, their potential in computer-use planning tasks, which are closely…
UmniBench: Unified Understand and Generation Model Oriented Omni-dimensional Benchmark
Kai Liu, Leyang Chen, Wenbo Li +5
Unifying multimodal understanding and generation has shown impressive capabilities in cutting-edge proprietary systems. However, evaluations of unified multimodal models (UMMs) rem…
PocketSR: The Super-Resolution Expert in Your Pocket Mobiles
Haoze Sun, Linfeng Jiang, Fan Li +9
Real-world image super-resolution (RealSR) aims to enhance the visual quality of in-the-wild images, such as those captured by mobile phones. While existing methods leveraging larg…
Visual Programmability: A Guide for Code-as-Thought in Chart Understanding
Bohao Tang, Yan Ma, Fei Zhang +6
Chart understanding presents a critical test to the reasoning capabilities of Vision-Language Models (VLMs). Prior approaches face critical limitations: some rely on external tools…
RefSTAR: Blind Facial Image Restoration with Reference Selection, Transfer, and Reconstruction
Zhicun Yin, Junjie Chen, Ming Liu +6
Blind facial image restoration is highly challenging due to unknown complex degradations and the sensitivity of humans to faces. Although existing methods introduce auxiliary infor…
DistFlow: A Fully Distributed RL Framework for Scalable and Efficient LLM Post-Training
Zhixin Wang, Jiaming Xu, Tianyi Zhou +10
Effectively scaling Reinforcement Learning (RL) is crucial for enhancing the reasoning and alignment of Large Language Models. The massive data and complex execution flows inherent…
Dual Prompting Image Restoration with Diffusion Transformers
Dehong Kong, Fan Li, Zhixin Wang +4
Recent state-of-the-art image restoration methods mostly adopt latent diffusion models with U-Net backbones, yet still facing challenges in achieving high-quality restoration due t…