Princeton University

university

Verified

https://www.princeton.edu

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

narutatsuri submitted a paper about 1 hour ago

Do Thinking Tokens Help with Safety?

Lingaaaaaaa authored a paper 2 days ago

OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured Recalibration

Lingaaaaaaa authored a paper 2 days ago

PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models

View all activity

Papers

Do Thinking Tokens Help with Safety?

Context-Aware RL for Agentic and Multimodal LLMs

View all Papers

princetonu 's papers 18

Submitted by

Narutatsu Ri

Do Thinking Tokens Help with Safety?

princetonu

Princeton University

Submitted by

py xu

Context-Aware RL for Agentic and Multimodal LLMs

princetonu

Princeton University

Submitted by

Seth Karten

Agent Bazaar: Enabling Economic Alignment in Multi-Agent Marketplaces

princetonu

Princeton University

2

Submitted by

Tao Zhong

HodgeCover: Higher-Order Topological Coverage Drives Compression of Sparse Mixture-of-Experts

princetonu

Princeton University

2

Submitted by

Tao Zhong

Topology-Preserving Neural Operator Learning via Hodge Decomposition

princetonu

Princeton University

Submitted by

XYX

Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training

princetonu

Princeton University

Submitted by

Seth Karten

Continual Harness: Online Adaptation for Self-Improving Foundation Agents

princetonu

Princeton University

Submitted by

Yixuan Huang

KinDER: A Physical Reasoning Benchmark for Robot Learning and Planning

princetonu

Princeton University

Submitted by

XYX

TIP: Token Importance in On-Policy Distillation

princetonu

Princeton University

Submitted by

Yinghui He

Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision

princetonu

Princeton University

Submitted by

Julian Ost

WorldFlow3D: Flowing Through 3D Distributions for Unbounded World Generation

princetonu

Princeton University

3

Submitted by

Tyler Zhu

Video Models Reason Early: Exploiting Plan Commitment for Maze Solving

princetonu

Princeton University

Submitted by

Seth Karten

The PokeAgent Challenge: Competitive and Long-Context Learning at Scale

princetonu

Princeton University

2

Submitted by

Seth Karten

Automatic Generation of High-Performance RL Environments

princetonu

Princeton University

2

Submitted by

Tao Zhong

Neural Field Thermal Tomography: A Differentiable Physics Framework for Non-Destructive Evaluation

princetonu

Princeton University

2

Submitted by

taesiri

Towards a Science of AI Agent Reliability

princetonu

Princeton University

Submitted by

taesiri

GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators

princetonu

Princeton University

LSD-3D: Large-Scale 3D Driving Scene Generation with Geometry Grounding

princetonu

Princeton University