17 citations · 56 across the 57 of their papers we have counts for
59 papers
Evidence-RL: Towards Evidence-intensive Visual Reasoning
Haojie Huang, Xinlei Yu, Chengming Xu +6
Vision-Language Models (VLMs) should answer from concrete image evidence rather than language priors, dataset shortcuts, or irrelevant visual context. Existing perception-aware pos…
In-Context Forcing: Uncovering Context Effects in Autoregressive Video Diffusion
Lingxiao Yang, Liu Liu, Moran Li +4
Current few-step autoregressive video diffusion models depend on previous fully denoised clean frames as context for all denoising steps of the current frame. However, these clean…
MambaADv2: Evolving Duality-enhanced State Space Model for Unsupervised Anomaly Detection
Xiaobin Hu, Haoyang He, Bo Yin +5
While recent advancements in anomaly detection have demonstrated the efficacy of CNN- and Transformer-based approaches, these architectures face inherent limitations: CNNs struggle…
Dual Latent Memory for Visual Multi-agent System
Xinlei Yu, Chengming Xu, Zhangquan Chen +8
While Visual Multi-Agent Systems (VMAS) promise to enhance comprehensive abilities through inter-agent collaboration, empirical evidence reveals a counter-intuitive "scaling wall":…
FFP-300K: Scaling First-Frame Propagation for Generalizable Video Editing
Xijie Huang, Chengming Xu, Donghao Luo +6
First-Frame Propagation (FFP) offers a promising paradigm for controllable video editing, but existing methods are hampered by a reliance on cumbersome run-time guidance. We identi…
Towards Generalized Multi-Image Editing for Unified Multimodal Models
Pengcheng Xu, Peng Tang, Donghao Luo +7
Unified Multimodal Models (UMMs) integrate multimodal understanding and generation, yet they are limited to maintaining visual consistency and disambiguating visual cues when refer…
Soul: Breathe Life into Digital Human for High-fidelity Long-term Multimodal Animation
Jiangning Zhang, Junwei Zhu, Zhenye Gan +14
We propose a multimodal-driven framework for high-fidelity long-term digital human animation termed , which generates semantically coherent videos from a single-fram…
Transform Trained Transformer for Accelerating Native 4K Video Generation
Jiangning Zhang, Junwei Zhu, Teng Hu +9
Native 4K (21763840) video generation remains a critical challenge due to the quadratic computational explosion of full-attention as spatiotemporal resolution increases, ma…
RoleRMBench & RoleRM: Towards Reward Modeling for Profile-Based Role Play in Dialogue Systems
Hang Ding, Qiming Feng, Dongqi Liu +9
Reward modeling has become a cornerstone of aligning large language models (LLMs) with human preferences. Yet, when extended to subjective and open-ended domains such as role play,…
Med-CMR: A Fine-Grained Benchmark Integrating Visual Evidence and Clinical Logic for Medical Complex Multimodal Reasoning
Haozhen Gong, Xiaozhong Ji, Yuansen Liu +9
MLLMs MLLMs are beginning to appear in clinical workflows, but their ability to perform complex medical reasoning remains unclear. We present Med-CMR, a fine-grained Medical Comple…
Boosting Reasoning in Large Multimodal Models via Activation Replay
Yun Xing, Xiaobin Hu, Qingdong He +4
Recently, Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective approach to incentivizing reasoning capability in Large Multimodal Models (LMMs), while…
DiP: Taming Diffusion Models in Pixel Space
Zhennan Chen, Junwei Zhu, Xu Chen +6
Diffusion models face a fundamental trade-off between generation quality and computational efficiency. Latent Diffusion Models (LDMs) offer an efficient solution but suffer from po…
FeRA: Frequency-Energy Constrained Routing for Effective Diffusion Adaptation Fine-Tuning
Bo Yin, Xiaobin Hu, Xingyu Zhou +7
Diffusion models have achieved remarkable success in generative modeling, yet how to effectively adapt large pretrained models to new tasks remains challenging. We revisit the reco…
VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models
Xinlei Yu, Chengming Xu, Guibin Zhang +7
Despite the remarkable success of Vision-Language Models (VLMs), their performance on a range of complex visual tasks is often hindered by a "visual processing bottleneck": a prope…
Towards One-step Causal Video Generation via Adversarial Self-Distillation
Yongqi Yang, Huayang Huang, Xu Peng +5
Recent hybrid video generation models combine autoregressive temporal dynamics with diffusion-based spatial denoising, but their sequential, iterative nature leads to error accumul…
Real-IAD Variety: Pushing Industrial Anomaly Detection Dataset to a Modern Era
Wenbing Zhu, Chengjie Wang, Bin-Bin Gao +12
Industrial Anomaly Detection (IAD) is a cornerstone for ensuring operational safety, maintaining product quality, and optimizing manufacturing efficiency. However, the advancement…
TokenAR: Multiple Subject Generation via Autoregressive Token-level enhancement
Haiyue Sun, Qingdong He, Jinlong Peng +5
Autoregressive Model (AR) has shown remarkable success in conditional image generation. However, these approaches for multiple reference generation struggle with decoupling differe…
Human-MME: A Holistic Evaluation Benchmark for Human-Centric Multimodal Large Language Models
Yuansen Liu, Haiming Tang, Jinlong Peng +12
Multimodal Large Language Models (MLLMs) have demonstrated significant advances in visual understanding tasks. However, their capacity to comprehend human-centric scenes has rarely…
StrandDesigner: Towards Practical Strand Generation with Sketch Guidance
Na Zhang, Moran Li, Chengming Xu +6
Realistic hair strand generation is crucial for applications like computer graphics and virtual reality. While diffusion models can generate hairstyles from text or images, these i…
Collaborative Face Experts Fusion in Video Generation: Boosting Identity Consistency Across Large Face Poses
Yuji Wang, Moran Li, Xiaobin Hu +7
Current video generation models struggle with identity preservation under large face poses, primarily facing two challenges: the difficulty in exploring an effective mechanism to i…
Visual Document Understanding and Reasoning: A Multi-Agent Collaboration Framework with Agent-Wise Adaptive Test-Time Scaling
Xinlei Yu, Chengming Xu, Zhangquan Chen +6
The dominant paradigm of monolithic scaling in Vision-Language Models (VLMs) is failing for understanding and reasoning in documents, yielding diminishing returns as it struggles w…
Semantic Frame Interpolation
Yijia Hong, Jiangning Zhang, Ran Yi +4
Generating intermediate video content of varying lengths based on given first and last frames, along with text prompt information, offers significant research and application poten…
HumanVideo-MME: Benchmarking MLLMs for Human-Centric Video Understanding
Yuxuan Cai, Jiangning Zhang, Zhenye Gan +9
Multimodal Large Language Models (MLLMs) have demonstrated significant advances in visual understanding tasks involving both images and videos. However, their capacity to comprehen…
Identity-Preserving Text-to-Video Generation Guided by Simple yet Effective Spatial-Temporal Decoupled Representations
Yuji Wang, Moran Li, Xiaobin Hu +7
Identity-preserving text-to-video (IPT2V) generation, which aims to create high-fidelity videos with consistent human identity, has become crucial for downstream applications. Howe…