4 citations · 9 across the 20 of their papers we have counts for
25 papers
OmniCoT: A Benchmark for Global and Multi-Step Panoramic Reasoning
Haocong He, Chenfei Liao, Zichen Wen +13
Multimodal Large Language Models (MLLMs) have demonstrated promising spatial reasoning capabilities, while these abilities remain underexplored in the emerging visual modality of p…
StruVis: Enhancing Reasoning-based Text-to-Image Generation via Thinking with Structured Vision
Yuanhuiyi Lyu, Kaiyu Lei, Ziqiao Weng +7
Reasoning-based text-to-image (T2I) generation requires models to interpret complex prompts accurately. Existing reasoning frameworks can be broadly categorized into two types: (1)…
Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks
Xu Zheng, Zihao Dongfang, Lutao Jiang +17
Humans possess spatial reasoning abilities that enable them to understand spaces through multimodal observations, such as vision and sound. Large multimodal reasoning models extend…
AI for Service: Proactive Assistance with AI Glasses
Zichen Wen, Yiyu Wang, Chenfei Liao +10
In an era where AI is evolving from a passive tool into an active and adaptive companion, we introduce AI for Service (AI4Service), a new paradigm that enables proactive and real-t…
Don't Just Chase "Highlighted Tokens" in MLLMs: Revisiting Visual Holistic Context Retention
Xin Zou, Di Lu, Yizhou Wang +5
Despite their powerful capabilities, Multimodal Large Language Models (MLLMs) suffer from considerable computational overhead due to their reliance on massive visual tokens. Recent…
Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods
Chenfei Liao, Wensong Wang, Zichen Wen +10
Recent efforts to accelerate inference in Multimodal Large Language Models (MLLMs) have largely focused on visual token compression. The effectiveness of these methods is commonly…
Understanding-in-Generation: Reinforcing Generative Capability of Unified Model via Infusing Understanding into Generation
Yuanhuiyi Lyu, Chi Kit Wong, Chenfei Liao +5
Recent works have made notable advancements in enhancing unified models for text-to-image generation through the Chain-of-Thought (CoT). However, these reasoning methods separate t…
PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era
Xu Zheng, Chenfei Liao, Ziqiao Weng +12
Omnidirectional vision, using 360-degree vision to understand the environment, has become increasingly critical across domains like robotics, industrial inspection, and environment…
Unlocking Speech Instruction Data Potential with Query Rewriting
Yonghua Hei, Yibo Yan, Shuliang Liu +3
End-to-end Large Speech Language Models~(\textbf{LSLMs}) demonstrate strong potential in response latency and speech comprehension capabilities, showcasing general intelligence acr…
MLLMs are Deeply Affected by Modality Bias
Xu Zheng, Chenfei Liao, Yuqian Fu +15
Recent advances in Multimodal Large Language Models (MLLMs) have shown promising results in integrating diverse modalities such as texts and images. MLLMs are heavily influenced by…
Shifting AI Efficiency From Model-Centric to Data-Centric Compression
Xuyang Liu, Zichen Wen, Shaobo Wang +14
The advancement of large language models (LLMs) and multi-modal LLMs (MLLMs) has historically relied on scaling model parameters. However, as hardware limits constrain further mode…
LazyMAR: Accelerating Masked Autoregressive Models via Feature Caching
Feihong Yan, Qingyan Wei, Jiayi Tang +5
Masked Autoregressive (MAR) models have emerged as a promising approach in image generation, expected to surpass traditional autoregressive models in computational efficiency by le…
EEdit: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing
Zexuan Yan, Yue Ma, Chang Zou +3
Inversion-based image editing is rapidly gaining momentum while suffering from significant computation overhead, hindering its application in real-time interactive scenarios. In th…
OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentation
Ding Zhong, Xu Zheng, Chenfei Liao +5
Segment Anything Model 2 (SAM2) has emerged as a strong base model in various pinhole imaging segmentation tasks. However, when applying it to domain, the significant f…
From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers
Jiacheng Liu, Chang Zou, Yuanhuiyi Lyu +2
Diffusion Transformers (DiT) have revolutionized high-fidelity image and video synthesis, yet their computational demands remain prohibitive for real-time applications. To solve th…
Dataset Distillation with Neural Characteristic Function: A Minmax Perspective
Shaobo Wang, Yicun Yang, Zhiyuan Liu +4
Dataset distillation has emerged as a powerful approach for reducing data requirements in deep learning. Among various methods, distribution matching-based approaches stand out for…
RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning
Yuanhuiyi Lyu, Xu Zheng, Lutao Jiang +5
Recent text-to-image generative models, e.g., Stable Diffusion V3 and Flux, have achieved notable progress. However, these models are strongly restricted to their limited knowledge…
Token Pruning for Caching Better: 9 Times Acceleration on Stable Diffusion for Free
Evelyn Zhang, Bang Xiao, Jiayi Tang +5
Stable Diffusion has achieved remarkable success in the field of text-to-image generation, with its powerful generative capabilities and diverse generation results making a lasting…
SAVEn-Vid: Synergistic Audio-Visual Integration for Enhanced Understanding in Long Video Context
Jungang Li, Sicheng Tao, Yibo Yan +6
Endeavors have been made to explore Large Language Models for video analysis (Video-LLMs), particularly in understanding and interpreting long videos. However, existing Video-LLMs…
Rethinking Token-wise Feature Caching: Accelerating Diffusion Transformers with Dual Feature Caching
Chang Zou, Shikang Zheng, Evelyn Zhang +6
Diffusion Transformers (DiT) have become the dominant methods in image and video generation yet still suffer substantial computational costs. As an effective approach for DiT accel…
ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models
Junzhe Chen, Tianshu Zhang, Shiyu Huang +4
Despite the recent breakthroughs achieved by Large Vision Language Models (LVLMs) in understanding and responding to complex visual-textual contexts, their inherent hallucination t…
Learning Robust Anymodal Segmentor with Unimodal and Cross-modal Distillation
Xu Zheng, Haiwei Xue, Jialei Chen +6
Simultaneously using multimodal inputs from multiple sensors to train segmentors is intuitively advantageous but practically challenging. A key challenge is unimodal bias, where mu…
Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformers
Shaobo Wang, Hongxuan Tang, Mingyang Wang +5
The debate between self-interpretable models and post-hoc explanations for black-box models is central to Explainable AI (XAI). Self-interpretable models, such as concept-based net…
Accelerating Diffusion Transformers with Token-wise Feature Caching
Chang Zou, Xuyang Liu, Ting Liu +2
Diffusion transformers have shown significant effectiveness in both image and video synthesis at the expense of huge computation costs. To address this problem, feature caching met…