20 papers
PIGEONS: Incremental Long-Video Captioning with Persistent Identity Gallery and Evolving Overarching Narrative Summary
Xinlong Chen, Weihong Lin, Yuanxing Zhang +9
Detailed video captioning has become an essential semantic interface for multi-modal understanding and generation. While existing methods mainly target short videos, extending them…
Human-Centric Image Captioning with Subject-Centered Spatial Understanding
Bozhou Li, Jiahang Zhang, Yue Ding +11
While multimodal large language models (MLLMs) achieve remarkable performance on generic image captioning, they frequently suffer from structural hallucinations in human-centric sc…
Flux-OPD: On-Policy Distillation with Evolving Contexts
Yuran Wang, Zekun Wang, Bohan Zeng +10
Large language model training in open-ended domains lacks verifiable rewards, making task preferences difficult to formalize as effective supervision. Contexts derived from task fe…
KeyFrame-Compass: Towards Comprehensive Evaluation of Keyframe-Conditioned Video Generation
Yuqi Tang, Tengfei Liu, Yizheng Lai +18
Video generation increasingly relies on keyframe-based workflows, where creators specify a sequence of reference images to guide generation. Although recent models support multi-ke…
CapRiCorn-1K: A Comprehensive Benchmark for Video Captioning and Subject Referential Consistency Across Temporal Scales
Xinlong Chen, Jiafu Tang, Yue Ding +12
Accurate and comprehensive video captions with consistent subject references are critical for downstream understanding and generation tasks. However, few existing benchmarks can ob…
LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV
Tengfei Liu, Yang Shi, Xuanyu Zhu +17
Audio-visual generation is rapidly advancing from short clips to minute-long content, while existing evaluation protocols remain largely confined to short-form settings. Existing b…
LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning
Yifan Dai, Zhenhua Wu, Bohan Zeng +18
Joint audio-visual reasoning is essential for omnimodal understanding, yet current multimodal large language models (MLLMs) still struggle when reasoning requires fine-grained evid…
Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos
Yuqi Tang, Yang Shi, Zhuoran Zhang +21
Recent video generative models have greatly improved the realism of AI-generated videos, yet their outputs still exhibit artifacts such as temporal inconsistencies, structural dist…
Semantic Routing: Exploring Multi-Layer LLM Feature Weighting for Diffusion Transformers
Bozhou Li, Yushuo Guan, Haolin Li +7
Recent DiT-based text-to-image models increasingly adopt LLMs as text encoders, yet text conditioning remains largely static and often utilizes only a single LLM layer, despite pro…
Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks
Bohan Zeng, Kaixin Zhu, Daili Hua +24
World models have emerged as a critical frontier in AI research, aiming to enhance large models by infusing them with physical dynamics and world knowledge. The core objective is t…
OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models
Yue Ding, Yiyan Ji, Jungang Li +12
Omni-modal Large Language Models (Omni-LLMs) have demonstrated strong capabilities in audio-video understanding tasks. However, their reliance on long multimodal token sequences le…
DiaDem: Advancing Dialogue Descriptions in Audiovisual Video Captioning for Multimodal Large Language Models
Xinlong Chen, Weihong Lin, Jingyun Hua +10
Accurate dialogue description in audiovisual video captioning is crucial for downstream understanding and generation tasks. However, existing models generally struggle to produce f…
CoF-T2I: Video Models as Pure Visual Reasoners for Text-to-Image Generation
Chengzhuo Tong, Mingkun Chang, Shenglong Zhang +12
Recent video generation models have revealed the emergence of Chain-of-Frame (CoF) reasoning, enabling frame-by-frame visual inference. With this capability, video models have been…
SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder
Minglei Shi, Haolin Wang, Borui Zhang +11
Visual generation grounded in Visual Foundation Model (VFM) representations offers a highly promising unified pathway for integrating visual understanding, perception, and generati…
Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling
Yuran Wang, Bohan Zeng, Chengzhuo Tong +6
Subject-driven image generation has advanced from single- to multi-subject composition, while neglecting distinction, the ability to distinguish and generate the correct subject wh…
VABench: A Comprehensive Benchmark for Audio-Video Generation
Daili Hua, Xizhi Wang, Bohan Zeng +6
Recent advances in video generation have been remarkable, enabling models to produce visually compelling videos with synchronized audio. While existing video generation benchmarks…
MorphoBench: A Benchmark with Difficulty Adaptive to Model Reasoning
Xukai Wang, Xuanbo Liu, Mingrui Chen +16
With the advancement of powerful large-scale reasoning models, effectively evaluating the reasoning capabilities of these models has become increasingly important. However, existin…
RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark
Yang Shi, Yuhao Dong, Yue Ding +22
The integration of visual understanding and generation into unified multimodal models represents a significant stride toward general-purpose AI. However, a fundamental question rem…
VidBridge-R1: Bridging QA and Captioning for RL-based Video Understanding Models with Intermediate Proxy Tasks
Xinlong Chen, Yuanxing Zhang, Yushuo Guan +9
The "Reason-Then-Respond" paradigm, enhanced by Reinforcement Learning, has shown great promise in advancing Multimodal Large Language Models. However, its application to the video…
MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios
Yang Shi, Huanqian Wang, Wulin Xie +20
Multimodal Large Language Models (MLLMs) have achieved considerable accuracy in Optical Character Recognition (OCR) from static images. However, their efficacy in video OCR is sign…