4 citations · 10 across the 30 of their papers we have counts for
35 papers
RVG-Bench: A Benchmark for Reasoning-Driven Audio-Visual Temporal Grounding
Yue Feng, Boshen Xu, Zihao Yue +5
Existing temporal video grounding (TVG) benchmarks primarily focus on localizing target video segments according to descriptive text queries of the visual content. However, real-wo…
EventLens: Event-Structure Reinforcement Learning for Video Understanding
Guowen Zhang, Boshen Xu, Zihao Yue +6
Recent multimodal large language models (MLLMs) achieve strong results on video question answering, yet often fail to recover the temporal structure that makes a video coherent. Th…
ORCA: The Annealed Spectral Conditioning Optimizer for Faster, Better LLM Training
Yuanshi Liu, Boyuan Jiang, Liang Hou +4
Modern LLM optimizers such as Muon often produce weight matrices with higher effective rank than Adam, yet further spectral control has delivered only modest gains. We identify a t…
FlowCPO: A Unified Divergence View of Preference Alignment for Flow Models
Yansen Han, Shengyi Liao, Peng Sun +4
Preference alignment for flow and diffusion models now spans online reinforcement learning and offline preference optimization, but the relation between these methods remains uncle…
Manifold Drift in Flow Preference Optimization: A Root Cause of Reward Hacking
Yansen Han, Shengyi Liao, Yuanxing Zhang +2
Preference optimization is a standard alignment method for generative models, yet extending it to continuous-time dynamics remains non-trivial. In flow matching, reward-driven upda…
PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives
Kaixin Ding, Xi Chen, Minghong Cai +9
Video world models simulate future states conditioned on current observations and user actions. Recent systems have demonstrated impressive video consistency and action controllabi…
CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning
Xinyu Mao, Yuhui Zeng, Xiaokun Liu +6
Cinematographic captioning aims to describe how a video is filmed using professional film-language concepts such as camera movement, shot size, depth of field, composition, and sho…
Geometry-Instructed Video Editing
Chirui Chang, Xiaoyang Lyu, Yi-Hua Huang +7
Object-level geometric edits, including translating, rotating, scaling, duplicating, or removing an object, are routine operations in digital content creation (DCC) workflows, yet…
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…
UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating
Jiehui Huang, Yuechen Zhang, Bin Xia +7
Generating a coherent multi-shot video requires structured cross-shot memory. Subject appearance, scene context, and speaker identity must persist across cuts. Existing approaches…
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…
SRC-Flow: Compact Semantic Representations Enable Normalizing Flows for Image Generation
Longtao Jiang, Jianmin Bao, Zhendong Wang +4
Normalizing flows (NFs) provide exact likelihoods and deterministic invertible sampling, but have historically lagged behind diffusion models for large-scale image generation. We i…
Stable Velocity: A Variance Perspective on Flow Matching
Donglin Yang, Yongxing Zhang, Xin Yu +5
While flow matching is elegant, its reliance on single-sample conditional velocities leads to high-variance training targets that destabilize optimization and slow convergence. By…
Astra: General Interactive World Model with Autoregressive Denoising
Yixuan Zhu, Jiaqi Feng, Wenzhao Zheng +5
Recent advances in diffusion transformers have empowered video generation models to generate high-quality video clips from texts or images. However, world models with the ability t…
A Mechanistic View on Video Generation as World Models: State and Dynamics
Luozhou Wang, Zhifei Chen, Yihua Du +11
Large-scale video generation models have demonstrated emergent physical coherence, positioning them as potential world models. However, a gap remains between contemporary "stateles…
SALAD: Achieve High-Sparsity Attention via Efficient Linear Attention Tuning for Video Diffusion Transformer
Tongcheng Fang, Hanling Zhang, Ruiqi Xie +8
Diffusion Transformers have demonstrated remarkable performance in video generation. However, their long input sequences incur substantial latency due to the quadratic complexity o…
MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives
Sihui Ji, Xi Chen, Shuai Yang +3
The core challenge for streaming video generation is maintaining the content consistency in long context, which poses high requirement for the memory design. Most existing solution…
UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation
Jiehui Huang, Yuechen Zhang, Xu He +7
Recent video generation models demonstrate impressive synthesis capabilities but remain limited by single-modality conditioning, constraining their holistic world understanding. Th…
Decoupling Complexity from Scale in Latent Diffusion Model
Tianxiong Zhong, Xingye Tian, Xuebo Wang +3
Existing latent diffusion models typically couple scale with content complexity, using more latent tokens to represent higher-resolution images or higher-frame rate videos. However…
Terra: Explorable Native 3D World Model with Point Latents
Yuanhui Huang, Weiliang Chen, Wenzhao Zheng +4
World models have garnered increasing attention for comprehensive modeling of the real world. However, most existing methods still rely on pixel-aligned representations as the basi…
PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning
Sihui Ji, Xi Chen, Xin Tao +2
Video generation models nowadays are capable of generating visually realistic videos, but often fail to adhere to physical laws, limiting their ability to generate physically plaus…
Mitigating the Noise Shift for Denoising Generative Models via Noise Awareness Guidance
Jincheng Zhong, Boyuan Jiang, Xin Tao +3
Existing denoising generative models rely on solving discretized reverse-time SDEs or ODEs. In this paper, we identify a long-overlooked yet pervasive issue in this family of model…
Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?
Ouxiang Li, Yuan Wang, Xinting Hu +7
Text-to-image (T2I) generation aims to synthesize images from textual prompts, which jointly specify what must be shown and imply what can be inferred, which thus correspond to two…
MIDAS: Multimodal Interactive Digital-humAn Synthesis via Real-time Autoregressive Video Generation
Ming Chen, Liyuan Cui, Wenyuan Zhang +9
Recently, interactive digital human video generation has attracted widespread attention and achieved remarkable progress. However, building such a practical system that can interac…