C4G introduces timestamp-conditioned learnable Gaussian tokens with transformer decoding, enabling efficient 4D scene reconstruction from monocular video without scene-specific optimization, reducing Gaussian count by orders of magnitude.

Mungyeom Kim, Minkyeong Jeon, Honggyu An et al.

VideoMLA introduces low-rank latent KV cache, reducing memory by 92.7% for minute-scale video diffusion while maintaining high quality.

Hidir Yesiltepe, Jiazhen Hu, Tuna Han Salih Meral et al.

NeuROK employs a transformer-based encoder-decoder to learn a low-dimensional latent space for 4D object dynamics, trained on large-scale geometric trajectories, bypassing predefined physical models.

Chen Geng, Guangzhao He, Yue Gao et al.

YoCausal employs a two-level causality benchmark using real-world videos and natural reversal, evaluating 13 SOTA video diffusion models' causal understanding via RSI and CCI metrics.

You-Zhe Xie, Yu-Hsuan Li, Jie-Ying Lee et al.

Introduces GPIC, a 28 trillion-pixel large-scale image corpus with permissive licensing, to advance visual generative modeling.

Keshigeyan Chandrasegaran, Kyle Sargent, Suchir Agarwal et al.

NEO-ov, a fully native end-to-end vision-language model, supports multi-image and video understanding with superior fine-grained perception and spatial reasoning.

Haiwen Diao, Jiahao Wang, Penghao Wu et al.

VisualMem introduces a structured visual memory module integrated with text memory, achieving 95% accuracy in personal entity recall, surpassing caption-based methods by over 40%.

Viet Nguyen, Thao Nguyen, Vishal M. Patel et al.

LocateAnything uses Parallel Box Decoding and 138M samples to significantly boost visual grounding speed and accuracy.

Shihao Wang, Shilong Liu, Yuanguo Kuang et al.

Representation-conditioned diffusion models using DINO embeddings achieve high-quality, controllable image generation on LSUN and CelebA datasets.

Nithesh Chandher Karthikeyan, Jonas Unger, Gabriel Eilertsen

Proposed DeltaDirect with MoDirect dataset boosts motion direction accuracy from 25.9% to 85.4% on synthetic domain.

Jongseo Lee, Hyuntak Lee, Sunghun Kim et al.

MotiMotion integrates VLM-based reasoning and confidence-aware control for motion-controlled video generation, outperforming baselines on MotiBench.

Lee Hsin-Ying, Hanwen Jiang, Yiqun Mei et al.

DecQ introduces detail-condensing queries to RAEs, boosting reconstruction PSNR to 22.76dB and reducing generation FID to 1.41 with only 3.9% extra computation.

Tianhang Wang, Yitong Chen, Wei Song et al.

WorldKV enables efficient world memory via KV cache retrieval and compression, doubling throughput while maintaining revisit fidelity.

Jung Yi, Minjae Kim, Paul Hyunbin Cho et al.

AnyMo proposes geometry-aware setup-agnostic human motion modeling, achieving 11.7% zero-shot recognition and 28.6% cross-modal retrieval MRR improvements.

Baiyu Chen, Zechen Li, Wilson Wongso et al.

CUActSpot benchmark enhances GUI complex interaction performance via data synthesis and multimodal evaluation; Phi-Ground-Any-4B excels.

Miaosen Zhang, Xiaohan Zhao, Zhihong Tan et al.

SenseNova-U1 unifies multimodal understanding and generation via NEO-unify architecture, enhancing vision-language model performance.

Haiwen Diao, Penghao Wu, Hanming Deng et al.

CausalCine achieves real-time multi-shot video generation using a causal autoregressive framework, significantly enhancing cross-shot coherence and interactivity.

Yihao Meng, Zichen Liu, Hao Ouyang et al.

AlphaGRPO enhances UMMs' multimodal generation via Decompositional Verifiable Reward, significantly improving benchmarks like GenEval.

Runhui Huang, Jie Wu, Rui Yang et al.

OmniNFT enhances audio-video generation quality and synchronization through a modality-aware online diffusion RL framework.

Guohui Zhang, XiaoXiao Ma, Jie Huang et al.

FuTCR framework improves new-class panoptic quality by up to 28% in continual panoptic segmentation while enhancing base-class performance.

Nicholas Ikechukwu, Keanu Nichols, Deepti Ghadiyaram et al.