Papers
Deep, long-form breakdowns of recent research in AI, machine learning, security & programming languages.
Mission-Aware Attestation Envelopes for Time-Critical Autonomous Action: A Hardware-in-the-Loop V2I Study
by Dimitrios Nikou, Nikolaos Kekatos, Sophia Petridou, Stylianos Basagiannis
The Missing Minimal Pair: Stereotype Evaluation in LLMs
by Nataliya Stepanova, Ivan Titov, Emily Allaway, Björn Ross
One Figure, Every Canvas: Editable Flowchart Relayout via Agentic Pipeline
by Shih-Chen Tseng, Chih-Hsuan Chen, Ryan Yang, Hsi-An Chen, Chun-Wei Tuan Mu, Yu-Lun Liu
Base Models Can Reason By Taking a Cue From Training Data
by Sophie L. Wang, Amil Dravid, Rulin Shao, Kevin Farhat, Sewon Min, Alexei A. Efros
TranScope: What the Software Hides About LLM Training Data, the Hardware Reveals at Scale, and Accelerators Magnify
by Joshua Kalyanapu, Darsh Asher, Kaushal Mhapsekar, Bita Aslrousta, Rushiraj Chaitanyakumar Sheth, Maharshi Mukeshkumar Oza, Achyuta Kannan, Samira Mirbagher Ajorpaz
BiasFlow: Geometric Monitoring and Backbone Regularization for Spurious Feature Reliance
by Haojin Deng, Zhiping Lin, Yimin Yang
Learning to Read the Contextual Tokens in Diffusion Transformers
by Omer Dahary, Etai Sella, Hadar Averbuch-Elor, Daniel Cohen-Or, Or Patashnik
Recursive Video In-Context Learning for Agentic Robot
by Wenrui Bao, Xinxin Liu, Bingxin Xu, Yuzhang Shang
Anatomy-aware Fine-grained Multimodal Fusion for Laryngopharyngeal Cancer T-Staging Prediction Using CT and Radiology Report
by Xingyue Zhao, Yanzhou Su, Fang Zhang, Zhanghexuan Ji, Yirui Wang, Dazhou Guo, Sibo Ju, Yuehua Cheng, Yuzhen Chen, Ming Feng, Le Lu, Tsung-Ying Ho, Jian Wang, Dakai Jin, Na Shen
MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM Agents
by Haozhen Zhang, Haodong Yue, Quanyu Long, Jianzhu Bao, Qingyuan Liu, Tao Feng, Bohan Liu, Weida Liang, Wenya Wang