Papers
Deep, long-form breakdowns of recent research in AI, machine learning, security & programming languages.
Looped Diffusion Transformer
by Yong Xien Chng, Tianyi Chen, Wenwen Tong, Haiwen Diao, Zhongang Cai, Lei Yang, Ziwei Liu, Lewei Lu, Dahua Lin, Gao Huang
Cropland PAtteRNS: Parallel Dimensional Attention Networks and Attention to Dataset Disparity for Crop Segmentation in Satellite Imagery Time Series Data
by Joseph Metcalfe, Sara Sharifzadeh, Fabio Caraffini
A Spectral Theory of Distortion in LLM Graph Reconstruction: Sharp Bounds and Empirical Characterization
by Jianru Shen
Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering
by Jaewoo Jung, Hyeonseo Yu, Honggyu An, Jisang Han, Mungyeom Kim, Minkyeong Jeon, Heeseong Shin, Wonjun Moon, Federico Tombari, Daniel Barath, Marc Pollefeys, Seungryong Kim, Sunghwan Hong
Breakdown of Local Denoising as Semantic Speciation
by Guangkuo Liu, Mert Okyay, Yifan F. Zhang, Fangjun Hu, Rahul Nandkishore, Xun Gao
LeapQuant: Efficient Linear Attention with Accurate Recurrent State Quantization
by Yi Pan, Haocheng Xi, Kan Zhu, Xingyang Li, Yibo Wu, Mayank Mishra, Hongtao Zhang, William X.Zheng, Baris Kasikci, Song Han, Kurt Keutzer, Rishabh Iyer, Ion Stoica
Pretraining Latent Information Feedback Transformers with Teacher Supervision
by Dor Tirosh, Ido Amos, Mor Geva
Thinking Before Thinking: Scaling Agentic Inference Through Meta-Reasoning
by Paras Dahal, Anton Bakhtin, Taco Cohen, Zhengxing Chen, Carole-Jean Wu, Rob Fergus, Scott Yih, Gabriel Synnaeve, Ruslan Salakhutdinov, Sanjeev Arora, Jason Weston, Anirudh Goyal
Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI
by Cheng Qian, Kunlun Zhu, Beibin Li, Zhenhailong Wang, Heng Ji
Breaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE
by Yu Xu, Yuxin Zhang, Xiao Yang, Haotian Yang, Yizhi Wang, Xinwei Huang, Minxuan Lin, Angtian Wang, Chongyang Ma, Fan Tang