16 citations · 24 across the 23 of their papers we have counts for
25 papers
FlashPrefill V2: Block-Sparse Prefill Attention for Long-Context LLM Serving
Qihang Fan, Huaibo Huang, Zhiying Wu +2
Long-context modeling is a pivotal capability for Large Language Models, yet the quadratic complexity of attention remains a critical bottleneck, particularly during the compute-in…
TIP: Token Importance in On-Policy Distillation
Yuanda Xu, Hejian Sang, Zhengze Zhou +3
On-policy knowledge distillation (OPD) trains a student on its own rollouts under token-level supervision from a teacher. Not all token positions matter equally, but existing views…
UniPrefill: Universal Long-Context Prefill Acceleration via Block-wise Dynamic Sparsification
Qihang Fan, Huaibo Huang, Zhiying Wu +2
As large language models (LLMs) continue to advance rapidly, they are becoming increasingly capable while simultaneously demanding ever-longer context lengths. To improve the infer…
Advancing Vision Transformer with Enhanced Spatial Priors
Qihang Fan, Huaibo Huang, Mingrui Chen +2
In recent years, the Vision Transformer (ViT) has garnered significant attention within the computer vision community. However, the core component of ViT, Self-Attention, lacks exp…
HalluClear: Diagnosing, Evaluating and Mitigating Hallucinations in GUI Agents
Chao Jin, Wenkui Yang, Hao Sun +6
While progress in GUI agents has been largely driven by industrial-scale training, ungrounded hallucinations often trigger cascading failures in real-world deployments.Unlike gener…
MVPBench: A Multi-Video Perception Evaluation Benchmark for Multi-Modal Video Understanding
Purui Bai, Tao Wu, Jiayang Sun +3
The rapid progress of Large Language Models (LLMs) has spurred growing interest in Multi-modal LLMs (MLLMs) and motivated the development of benchmarks to evaluate their perceptual…
Think 360°: Evaluating the Width-centric Reasoning Capability of MLLMs Beyond Depth
Mingrui Chen, Hexiong Yang, Haogeng Liu +2
In this paper, we present a holistic multimodal benchmark that evaluates the reasoning capabilities of MLLMs with an explicit focus on reasoning width, a complementary dimension to…
FlashPrefill: Instantaneous Pattern Discovery and Thresholding for Ultra-Fast Long-Context Prefilling
Qihang Fan, Huaibo Huang, Zhiying Wu +3
Long-context modeling is a pivotal capability for Large Language Models, yet the quadratic complexity of attention remains a critical bottleneck, particularly during the compute-in…
Random Wins All: Rethinking Grouping Strategies for Vision Tokens
Qihang Fan, Yuang Ai, Huaibo Huang +1
Since Transformers are introduced into vision architectures, their quadratic complexity has always been a significant issue that many research efforts aim to address. A representat…
Expand and Prune: Maximizing Trajectory Diversity for Effective GRPO in Generative Models
Shiran Ge, Chenyi Huang, Yuang Ai +3
Group Relative Policy Optimization (GRPO) is a powerful technique for aligning generative models, but its effectiveness is bottlenecked by the conflict between large group sizes an…
Rectifying Magnitude Neglect in Linear Attention
Qihang Fan, Huaibo Huang, Yuang Ai +1
As the core operator of Transformers, Softmax Attention exhibits excellent global modeling capabilities. However, its quadratic complexity limits its applicability to vision tasks.…
NOFT: Test-Time Noise Finetune via Information Bottleneck for Highly Correlated Asset Creation
Jia Li, Nan Gao, Huaibo Huang +1
The diffusion model has provided a strong tool for implementing text-to-image (T2I) and image-to-image (I2I) generation. Recently, topology and texture control are popular explorat…
Unlocking the Potential of Difficulty Prior in RL-based Multimodal Reasoning
Mingrui Chen, Haogeng Liu, Hao Liang +3
In this work, we investigate how explicitly modeling problem's difficulty prior information shapes the effectiveness of reinforcement learning based fine-tuning for multimodal reas…
DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modeling
Yuang Ai, Qihang Fan, Xuefeng Hu +3
Diffusion Transformer (DiT), a promising diffusion model for visual generation, demonstrates impressive performance but incurs significant computational overhead. Intriguingly, ana…
Breaking the Low-Rank Dilemma of Linear Attention
Qihang Fan, Huaibo Huang, Ran He
The Softmax attention mechanism in Transformer models is notoriously computationally expensive, particularly due to its quadratic complexity, posing significant challenges in visio…
InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning
Xiaotian Han, Yiren Jian, Xuefeng Hu +8
Pre-training on large-scale, high-quality datasets is crucial for enhancing the reasoning capabilities of Large Language Models (LLMs), especially in specialized domains such as ma…
Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model
Haogeng Liu, Quanzeng You, Xiaotian Han +4
In the realm of Multimodal Large Language Models (MLLMs), vision-language connector plays a crucial role to link the pre-trained vision encoders with Large Language Models (LLMs).…
Semantic Equitable Clustering: A Simple and Effective Strategy for Clustering Vision Tokens
Qihang Fan, Huaibo Huang, Mingrui Chen +1
The Vision Transformer (ViT) has gained prominence for its superior relational modeling prowess. However, its global attention mechanism's quadratic complexity poses substantial co…
Vision Transformer with Sparse Scan Prior
Yuguang Zhang, Qihang Fan, Huaibo Huang
In recent years, Transformers have achieved remarkable progress in computer vision tasks. However, their global modeling often comes with substantial computational overhead, in sta…
Band-Attention Modulation Network for Robust Face Forgery Detection
Zhida Zhang, Jie Cao, Wenkui Yang +4
Face forgery detection faces critical challenges in generalizing to unseen manipulation techniques and remaining robust under image compression, which often obscures subtle artifac…
ViTAR: Vision Transformer with Any Resolution
Qihang Fan, Quanzeng You, Xiaotian Han +5
This paper tackles a significant challenge faced by Vision Transformers (ViTs): their constrained scalability across different image resolutions. Typically, ViTs experience a perfo…
InfiMM-HD: A Leap Forward in High-Resolution Multimodal Understanding
Haogeng Liu, Quanzeng You, Xiaotian Han +7
Multimodal Large Language Models (MLLMs) have experienced significant advancements recently. Nevertheless, challenges persist in the accurate recognition and comprehension of intri…
Video-Teller: Enhancing Cross-Modal Generation with Fusion and Decoupling
Haogeng Liu, Qihang Fan, Tingkai Liu +5
This paper proposes Video-Teller, a video-language foundation model that leverages multi-modal fusion and fine-grained modality alignment to significantly enhance the video-to-text…
DeVAn: Dense Video Annotation for Video-Language Models
Tingkai Liu, Yunzhe Tao, Haogeng Liu +5
We present a novel human annotated dataset for evaluating the ability for visual-language models to generate both short and long descriptions for real-world video clips, termed DeV…