The Research Desk.

Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians

Kartik Chandra, Max Kleiman-Weiner, Jonathan Ragan-Kelley, Joshua B. Tenenbaum

MIT CSAIL, University of Washington, Seattle, MIT Department of Brain & Cognitive Sciences

The Pain Axis: LLMs Represent Self-Directed Harm and Act to Relieve It

Cameron Berg, Valen Tagliabue

Financing the AI Buildout

Stijn Van Nieuwerburgh

Columbia Business School

Tokenization: A Survey for Modern NLP

Invent a Dataset: Measuring Dataset Generation Abilities with Zero Seed Data

4k, views

ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research

1k, views

Affiliation: Stanford University Seoul National University University of Washington, Affiliation: Carnegie Mellon University Allen Institute for AI MIT, Retrieving Papers that Inspire New Research, Stanford University Seoul National University University of Washington, Carnegie Mellon University Allen Institute for AI MIT

Looped Diffusion Transformer

SenseTime Research, LeapLab, Tsinghua University

Sharpening Tax in Post-Training

views

Affiliation: Meta Superintelligence Labs, Affiliation: University of Wisconsin–Madison, Affiliation: Stanford University, Meta Superintelligence Labs, University of Wisconsin–Madison

SkillRefiner: Offline Skill Refinement from Historical Agent Traces

views

OpenTumorBoard: A Real-World Benchmark of Multidisciplinary Tumor Board Discussion Trajectories

Anqi Li, Zhixuan Ge, Yixuan Duan, Jiarong Qian, Chi-Yu Chen

X-Tree: Tokenizing Reusable Experience for Efficient Agent Generalization

Sitao Cheng, Xunjian Yin, Zhiyuan Sun, Yuxuan Li, Ruiwen Zhou

University of Waterloo

Honeycomb: Constant-Size Scene Memory Representation for Video World Models

Jack Wei Lun Shi, Kaichen Zhou, Haoyu Chen, Yufeng Weng, Keane Ong