32 citations · 51 across the 12 of their papers we have counts for
14 papers
How Far Can Coding Agents Go in Visual Generation?
Hengguang Zhou, Yuanhao Ban, Jiaqi Feng +3
Modern image generation largely relies on specialized generative models that leave the process of image construction implicit in learned parameters. We explore an alternative: gene…
SlackDrive: Reclaiming Runtime Slack for Adaptive Driving Inference
Xiaohuan Pei, Hengguang Zhou, Yuanhao Ban +7
Driving world-action models improve planning by coupling multimodal reasoning with future prediction, but their growing inference cost increasingly conflicts with the real-time lat…
Region-Level Policy Optimization for Fine-grained MLLM Perception
Yuheng Shi, Xiaohuan Pei, Minjing Dong +1
Fine-grained visual perception in MLLMs is commonly improved by raising the resolution, but the added visual tokens inflate vision-encoding and language-model prefilling costs. We…
Stream4D: 4D-Consistency for Streaming Autoregressive Diffusion Video Models
Yuanhao Ban, Jiaqi Feng, Hengguang Zhou +3
Streaming autoregressive diffusion models enable real-time, long-horizon video generation, but their training objectives optimize local frame prediction rather than the geometry an…
Differentiable Efficient Operator Search
Xiaohuan Pei, Jiyuan Zhang, Yuanfan Guo +4
Efficient multimodal foundation models often rely on manually designed token-reduction operators, such as pruning, merging, pooling, and adaptive reweighting. Although these operat…
Q-Zoom: Query-Aware Adaptive Perception for Efficient Multimodal Large Language Models
Yuheng Shi, Xiaohuan Pei, Linfeng Wen +2
MLLMs require high-resolution visual inputs for fine-grained tasks like document understanding and dense scene perception. However, current global resolution scaling paradigms indi…
Action-aware Dynamic Pruning for Efficient Vision-Language-Action Manipulation
Xiaohuan Pei, Yuxing Chen, Siyu Xu +3
Robotic manipulation with Vision-Language-Action models requires efficient inference over long-horizon multi-modal context, where attention to dense visual tokens dominates computa…
Catching the Details: Self-Distilled RoI Predictors for Fine-Grained MLLM Perception
Yuheng Shi, Xiaohuan Pei, Minjing Dong +1
Multimodal Large Language Models (MLLMs) require high-resolution visual information to perform fine-grained perception, yet processing entire high-resolution images is computationa…
Rethinking Causal Mask Attention for Vision-Language Inference
Xiaohuan Pei, Tao Huang, YanXiang Ma +1
Causal attention has become a foundational mechanism in autoregressive vision-language models (VLMs), unifying textual and visual inputs under a single generative framework. Howeve…
Cross-Self KV Cache Pruning for Efficient Vision-Language Inference
Xiaohuan Pei, Tao Huang, Chang Xu
KV cache pruning has emerged as a promising technique for reducing memory and computation costs in long-context auto-regressive generation. Existing methods for vision-language mod…
EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba
Xiaohuan Pei, Tao Huang, Chang Xu
Prior efforts in light-weight model development mainly centered on CNN and Transformer-based designs yet faced persistent challenges. CNNs adept at local feature extraction comprom…
LocalMamba: Visual State Space Model with Windowed Selective Scan
Tao Huang, Xiaohuan Pei, Shan You +3
Recent advancements in state space models, notably Mamba, have demonstrated significant progress in modeling long sequences for tasks like language understanding. Yet, their applic…
Neural Architecture Retrieval
Xiaohuan Pei, Yanxi Li, Minjing Dong +1
With the increasing number of new neural architecture designs and substantial existing neural architectures, it becomes difficult for the researchers to situate their contributions…
GPT Self-Supervision for a Better Data Annotator
Xiaohuan Pei, Yanxi Li, Chang Xu
The task of annotating data into concise summaries poses a significant challenge across various domains, frequently requiring the allocation of significant time and specialized kno…