影响力指数

55.74/100

前 6.2%

全站排名 #3,987

发表论文16 篇

平均评分5.0

年均产出5.3 篇/年

Pascal Poupart

Full Professor@University of Waterloo·加拿大·OpenReview

研究方向

reinforcement learning · Markov decision processes · federated learning · inverse constraint reinforcement learning · large language model alignment

Image-POSER: Reflective RL for Multi-Expert Image Generation and Editing

ICLR 2026Rejected

Counterfactual Residual Data Augmentation for Regression

ICLR 2026Desk Rejected

Talk, Judge, Cooperate: Gossip-Driven Indirect Reciprocity in Self-Interested LLM Agents

ICLR 2026Rejected

Unconstrained Models as Constrained Problem Solvers: Duality-Driven Adaptation without Retraining

ICLR 2026Withdrawn

Agent-Chained Policy Optimization

ICLR 2026Rejected

Information Bargaining: Bilateral Commitment in Bayesian Persuasion

ICLR 2026Rejected

Towards Cost-Effective Reward Guided Text Generation

ICML 2025Poster

A Critical Look At Tokenwise Reward-Guided Text Generation

COLM 2025Poster

Uncertainty-Guided Optimization on Large Language Model Search Trees

ICLR 2025Rejected

Reflect-then-Plan: Offline Model-Based Planning through a Doubly Bayesian Lens

ICML 2025Poster

Understanding Constraint Inference in Safety-Critical Inverse Reinforcement Learning

ICLR 2025Poster

A Critical Look At Tokenwise Reward-Guided Text Generation

ICLR 2025Rejected

Reflect-then-Plan: Offline Model-Based Planning through a Doubly Bayesian Lens

ICLR 2025Rejected

FAACL: Federated Adaptive Asymmetric Clustered Learning

ICLR 2025Rejected

Bayesian Persuasion Is a Bargaining Game

ICLR 2025Rejected

合作者 (20)

Agustinus Kristiadi