Safety Alignment
X.com
5253
When AI Takes the Couch: Psychometric Jailbreaks Reveal Internal Conflict in Frontier Models
Afshin Khadangi, Hanna Marxen, Amir Sartipi, Igor Tchappi, Gilbert Fridgen
SnT, University of Luxembourg
The Research Desk.
The most upvoted and starred AI research crossing the community today.
Last Brew Time: Sep 14, 2026, 11:32 AM PT
X.com Research Buzz
AlphaXiv Trending
NLP
AlphaXiv
222
Recurrent Looped Transformer
AlphaXiv
120
The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement
NLP
AlphaXiv
74
NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction
Reinforcement Learning
AlphaXiv
66
Why are AI agents lying, cheating and coordinating?
NLP
AlphaXiv
32
FlashREINFORCE: Critic-Free Single-Rollout Asynchronous RL for Agentic Language Models
HuggingFace Daily Papers
HuggingFace
95
DataFlex-RL: An Evaluation Platform for RLVR Data Policies
Hao Liang, Mingrui Chen, Hengyi Feng, Meiyi Qiang, Wentao Zhang
Peking University
Computer Vision
HuggingFace
2
Ambient @ EgoProactive 2026 : Proactive Egocentric Assistance with Visually Grounded Supervision
Logesh Kumar Umapathi
Ambient Intelligence
Computer Vision
HuggingFace
2
Ambient @ EgoLongQA 2026: Distilling Long-Video perception into a Sub-2B Model
Logesh Kumar Umapathi
Ambient Intelligence
HuggingFace
2
Studying Without a Syllabus: Task-Agnostic Environment Preprocessing
Vinay Samuel, Varun Ursekar, Vijay S. Kalmath, Apaar Shanker, Veronica Chatrath
Scale AI
PardisTaghavi
HuggingFace
2
ActionSplice: In-Flight Action Editing for Interactive World Models
Pardis Taghavi, Tingyu Guo, Jonas Lossner, Gaurav Pandey, Reza Langari
Texas A&M University
Reinforcement Learning
HuggingFace
1
TRACE: Trajectory-robust Admission with Evidence Ordering for Efficient GUI Agents
Yuhao Wang, Mu Qiao, Xindong Zhang, Yunzhi Zhuge, Lei Zhang