Paper Archive

Qiuxuan Feng, Jiale Yu, Jiaming Liu, Yueru Jia, Zhuangzhe Wu, Hao Chen, Zezhong Qian, Shuo Gu, Peng Jia, Siwei Ma, Shanghang Zhang 5/11/2026 arxiv

World Action Models (WAMs) have emerged as a promising paradigm for robot control by modeling physical dynamics. Current WAMs generally follow two paradigms: the "Imagine-then-Execute" approach, which uses video prediction to infer actions via inverse dynamics, and the "Joint Modeling" approach, whi...

Keya Hu, Linlu Qiu, Yiyang Lu, Hanhong Zhao, Tianhong Li, Yoon Kim, Jacob Andreas, Kaiming He 5/11/2026 arxiv

Diffusion and flow-based models have become the de facto approaches for generating continuous data, e.g., in domains such as images and videos. Their success has attracted growing interest in applying them to language modeling. Unlike their image-domain counterparts, today's leading diffusion langua...

Haoyuan Sun, Jing Wang, Yuxin Song, Yu Lu, Bo Fang, Yifu Luo, Jun Yin, Pengyu Zeng, Miao Zhang, Tiantian Zhang, Xueqian Wang, Shijian Lu 5/11/2026 arxiv

Recently, post-training methods based on reinforcement learning, with a particular focus on Group Relative Policy Optimization (GRPO), have emerged as the robust paradigm for further advancement of text-to-image (T2I) models. However, these methods are often prone to reward hacking, wherein models e...

Zihui Xue, Ami Baid, Sangho Kim, Mi Luo, Kristen Grauman 5/11/2026 arxiv

As wearable devices like smart glasses integrate Large Multimodal Models (LMMs) into the continuous first-person visual streams of individual users, the evolution of these models into true personal assistants hinges on visual personalization: the ability to reason over visual information unique to t...

Yaman Kindap, Manfred Opper, Benjamin Dupuis, Umut Simsekli, Tolga Birdal 5/11/2026 arxiv

Modelling extreme events and heavy-tailed phenomena is central to building reliable predictive systems in domains such as finance, climate science, and safety-critical AI. While Lévy processes provide a natural mathematical framework for capturing jumps and heavy tails, Bayesian inference for Lévy-d...

Chenyang Song, Weilin Zhao, Xu Han, Chaojun Xiao, Yingfa Chen, Zhiyuan Liu 5/11/2026 arxiv

While Mixture-of-Experts (MoE) scales model capacity without proportionally increasing computation, its massive total parameter footprint creates significant storage and memory-access bottlenecks, which hinder efficient end-side deployment that simultaneously requires high performance, low computati...

Albert Alcalde, Leon Bungert, Konstantin Riedl, Tim Roith 5/11/2026 arxiv

Transformers with self-attention modules as their core components have become an integral architecture in modern large language and foundation models. In this paper, we study the evolution of tokens in deep encoder-only transformers at inference time which is described in the large-token limit by a ...

Xinyu Guo, Bin Xie, Wei Chai, Xianchi Deng, Tiancai Wang, Zhengxing Wu, Xingyu Chen 5/11/2026 arxiv

Large-scale pretraining has made Vision-Language-Action (VLA) models promising foundations for generalist robot manipulation, yet adapting them to downstream tasks remains necessary. However, the common practice of full fine-tuning treats pretraining as initialization and can shift broad priors towa...

Junhao Shen, Teng Zhang, Xiaoyan Zhao, Hong Cheng 5/11/2026 arxiv

Large language model agents increasingly rely on external skills to solve complex tasks, where skills act as modular units that extend their capabilities beyond what parametric memory alone supports. Existing methods assume external skills either accumulate as persistent guidance or internalized int...

Dong-Yang Li, Wang Zhao, Yuxin Chen, Wenbo Hu, Meng-Hao Guo, Fang-Lue Zhang, Ying Shan, Shi-Min Hu 5/11/2026 arxiv

Recent advances in 3D generative models have rapidly improved image-to-3D synthesis quality, enabling higher-resolution geometry and more realistic appearance. Yet fidelity, which measures pixel-level faithfulness of the generated 3D asset to the input image, still remains a central bottleneck. We a...