23 papers
FrameLite: Decision-Oriented Aesthetic Cropping with a Compact Vision-Language Model
Jianze Li, Kai Liu, Ziqing Zhang +4
Aesthetic image cropping improves composition by balancing subjects, context, and image boundaries. Large vision-language models bring semantic knowledge to this task, but their sc…
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…
ET-Prune: Evidence-Aware Dynamic Budgeting for Visual Token Pruning in Text-Rich MLLMs
Zizhong Ding, Junxian Li, Kai Liu +4
Visual token pruning reduces the inference cost of multimodal large language models, but a fixed token ratio is poorly matched to text-rich inputs. In OCR-centric tasks, decisive e…
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA
Mind Lab, :, Vin Bo +80
Macaron-V1 is an open agent-model family for experiential intelligence: learning from experience in real environments and continuing to learn after deployment. It is organized arou…
On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters
Mind Lab, :, Vin Bo +64
Parameter-efficient fine-tuning (PEFT) is usually treated as a cheaper alternative to full fine-tuning. We study a broader role: small trainable adapters as persistent local state…
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…
MinT: Managed Infrastructure for Training and Serving Millions of LLMs
Mind Lab, :, Song Cao +60
We present MindLab Toolkit (MinT), a managed infrastructure system for Low-Rank Adaptation (LoRA) post-training and online serving. MinT targets a setting where many trained polici…
DRScaffold: Boosting Dense-Scene Reasoning in Lightweight Vision Language Models
Xinrui Shi, Kai Liu, Ziqing Zhang +3
Lightweight vision-language models perform competitively on standard benchmarks yet fail systematically in dense-scene reasoning, where multiple objects, attributes, and relations…
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…
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…
Fose: Fusion of One-Step Diffusion and End-to-End Network for Pansharpening
Kai Liu, Zeli Lin, Weibo Wang +2
Pansharpening is a significant image fusion task that fuses low-resolution multispectral images (LRMSI) and high-resolution panchromatic images (PAN) to obtain high-resolution mult…
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…
InfVSR: Toward Consistency-Driven Streaming Generative Video Super-Resolution
Ziqing Zhang, Kai Liu, Zheng Chen +5
Real-world videos often extend over thousands of frames. Existing generative video super-resolution (VSR) approaches, however, face two persistent challenges when processing long s…
CLQ: Cross-Layer Guided Orthogonal-based Quantization for Diffusion Transformers
Kai Liu, Shaoqiu Zhang, Linghe Kong +1
Visual generation quality has been greatly promoted with the rapid advances in diffusion transformers (DiTs), which is attributed to the scaling of model size and complexity. Howev…
Low-bit Model Quantization for Deep Neural Networks: A Survey
Kai Liu, Qian Zheng, Kaiwen Tao +9
With unprecedented rapid development, deep neural networks (DNNs) have deeply influenced almost all fields. However, their heavy computation costs and model sizes are usually unacc…
Freqformer: Image-Demoiréing Transformer via Effective Frequency Decomposition
Xiaoyang Liu, Bolin Qiu, Zheng Chen +5
Image demoiréing remains a challenging task due to the complex interplay between texture corruption and color distortions caused by moiré patterns. Existing methods, especially tho…
DVD-Quant: Data-free Video Diffusion Transformers Quantization
Zhiteng Li, Hanxuan Li, Junyi Wu +6
Diffusion Transformers (DiTs) have emerged as the state-of-the-art architecture for video generation, yet their computational and memory demands hinder practical deployment. While…
OSCAR: One-Step Diffusion Codec Across Multiple Bit-rates
Jinpei Guo, Yifei Ji, Zheng Chen +6
Pretrained latent diffusion models have shown strong potential for lossy image compression, owing to their powerful generative priors. Most existing diffusion-based methods reconst…
CondiQuant: Condition Number Based Low-Bit Quantization for Image Super-Resolution
Kai Liu, Dehui Wang, Zhiteng Li +5
Low-bit model quantization for image super-resolution (SR) is a longstanding task that is renowned for its surprising compression and acceleration ability. However, accuracy degrad…
BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution
Kai Liu, Kaicheng Yang, Zheng Chen +5
While super-resolution (SR) methods based on diffusion models (DM) have demonstrated inspiring performance, their deployment is impeded due to the heavy request of memory and compu…
Dog-IQA: Standard-guided Zero-shot MLLM for Mix-grained Image Quality Assessment
Kai Liu, Ziqing Zhang, Wenbo Li +5
Image quality assessment (IQA) serves as the golden standard for all models' performance in nearly all computer vision fields. However, it still suffers from poor out-of-distributi…
2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution
Kai Liu, Haotong Qin, Yong Guo +4
Low-bit quantization has become widespread for compressing image super-resolution (SR) models for edge deployment, which allows advanced SR models to enjoy compact low-bit paramete…