Fast-ARDiff accelerates AR+diffusion generation using entropy-informed methods, achieving 4.3x speedup on ImageNet.

Zhen Zou, Xiaoxiao Ma, Jie Huang et al.

First comprehensive survey on body and face motion generation, covering datasets, evaluation metrics, and techniques like GANs and DDPMs for multimodal tasks.

Lownish Rai Sookha, Nikhil Pakhale, Mudasir Ganaie et al.

PAVAS integrates physical reasoning into video-to-audio synthesis, significantly enhancing physical consistency.

Oh Hyun-Bin, Yuhta Takida, Toshimitsu Uesaka et al.

OneStory uses adaptive memory for multi-shot video, reaching 0.5813 T2MSV coherence.

Zhaochong An, Menglin Jia, Haonan Qiu et al.

Introduced NPC to optimize text-image alignment via negative prompts, achieving a 54% improvement on GenEval++.

Sangha Park, Eunji Kim, Yeongtak Oh et al.

VulnLLM-R detects vulnerabilities through reasoning, outperforming SOTA models in parameter efficiency.

Yuzhou Nie, Hongwei Li, Chengquan Guo et al.

SJD++ accelerates AR text-to-image generation by 2-3x using multi-token prediction and high-confidence reuse.

Yao Teng, Zhihuan Jiang, Han Shi et al.

SAGE benchmark evaluates LLMs' cross-cultural understanding via 9 dimensions and 4,530 tasks, exposing systematic deficiencies.

Shiwei Guo, Sihang Jiang, Qianxi He et al.

AlignGemini achieves generalizable AI-generated image detection via task-model alignment, improving accuracy by 9.5%.

Ruoxin Chen, Jiahui Gao, Kaiqing Lin et al.

Data-driven functional observer framework estimates target states without system identification, suitable for complex networks.

Yuan Zhang, Ziyuan Luo, Wenxuan Xu et al.

Proposed Gaussian Quant (GQ), a training-free vector quantization method, outperforms VQGAN on ImageNet.

Tongda Xu, Wendi Zheng, Jiajun He et al.

Proposed a randomized greedy compression algorithm, proving the existence of pruned/quantized subnetworks in wide MLPs.

Houssam El Cheairi, David Gamarnik, Rahul Mazumder

Proposes RFET-based energy-efficient stochastic neural network accelerator, reducing area, latency, and energy consumption by ~40%.

Sheng Lu, Qianhou Qu, Sungyong Jung et al.

RefBench-PRO improves localization accuracy in referring expression comprehension using Ref-R1 with Dynamic IoU-based GRPO.

Tianyi Gao, Hao Li, Han Fang et al.

GraphDeT introduces edge denoising as an auxiliary task, boosting GNN domain adaptation performance by up to 21.83%.

Haiyang Yu, Meng-Chieh Lee, Xiang song et al.

WAM-Flow achieves parallel coarse-to-fine motion planning via discrete flow matching, reaching 89.1 PDMS with 1-step inference.

Yifang Xu, Jiahao Cui, Feipeng Cai et al.

PRiSM evaluates scientific reasoning via Python code with 24,750 physics and math problems.

Shima Imani, Seungwhan Moon, Adel Ahmadyan et al.

CARD combines noise whitening and diffusion updates to address correlated noise, achieving state-of-the-art results on the CIN-D dataset.

Niki Nezakati, Arnab Ghosh, Amit Roy-Chowdhury et al.

DraCo integrates low-res sketches and multi-modal reasoning, boosting rare concept generation with +8% on GenEval and +0.91 on Imagine-Bench.

Dongzhi Jiang, Renrui Zhang, Haodong Li et al.

BulletTime employs 4D positional encoding and adaptive normalization to decouple scene dynamics from camera pose, enabling precise 4D control in video diffusion models.

Yiming Wang, Qihang Zhang, Shengqu Cai et al.