Papers
Deep, long-form breakdowns of recent research in AI, machine learning, security & programming languages.
SciExam for ENSO: Can AI Agents Build Climate Models?
by Yinling Zhang, Langchen Liu, Dongbin Xiu, Xueyan Zou, Xu Kuang, Mengdi Wang, Shilong Liu
Your Prompt Should Do More: Effects of Retrieval Instructions in Embedding Models
by Amanda Myntti, Jenna Kanerva, Veronika Laippala, Filip Ginter
RECAST: Learning to Compute the Right Context through Adaptive Evidence Routing
by Yilun Hao, Krishna Sayana, Isabella Ye, James S Ren, Sukhdeep Sodhi, Craig Boutilier, Chuchu Fan
Validity Without Ground Truth: What Stated-Preference Economics Offers the Evaluation of Language Models
by Daniel Robert Kling Alexander, Catherine Louise Kling
EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution
by Python Song, Zhixuan Liang, Kelsey Fu, Mengdi Wang, Junfeng Yang, Shilong Liu
Conformal Prediction Sets Quantify Information Gain: A Theoretical Perspective
by Kevin Zhang, Stephen Bates
IdeaAnchor: Teaching LLMs to Turn Literature into Research Ideas
by Ziyu Chen, Yilun Zhao, Jiashuo Sun, Yiling Ma, Manasi Patwardhan, Arman Cohan
Sherpa: Teaching LLMs to Teach Adaptively
by Weixian Xu, Yanzhe Zhang, Zora Zhiruo Wang, Changyu Chen, Diyi Yang
Agent in a Bottle: Can LLM Agents Turn Their Capabilities Into Cheap, Scalable Artifacts?
by Ankit Sonthalia, Haritz Puerto, Alexander Rubinstein, Martin Gubri, Seong Joon Oh
AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model
by Sarim Hashmi, Mukul Ranjan, Kshitij Mishra, Mikhail Kuznetsov, Praneeth Vepakomma, Nils Lukas