activity
20242026
collaborators

9 papers

cs.CL2026

Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation

Zhuolin Yang, Zihan Liu, Yang Chen +14

We introduce Nemotron-Cascade 2, an open 30B MoE model with 3B activated parameters that delivers best-in-class reasoning and strong agentic capabilities. Despite its compact size,…

cs.LG2025

Nearly Optimal Algorithms for Contextual Dueling Bandits from Adversarial Feedback

Qiwei Di, Jiafan He, Quanquan Gu

Learning from human feedback plays an important role in aligning generative models, such as large language models (LLM). However, the effectiveness of this approach can be influenc…

cs.LG2025

A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation

Heyang Zhao, Jiafan He, Quanquan Gu

The exploration-exploitation dilemma has been a central challenge in reinforcement learning (RL) with complex model classes. In this paper, we propose a new algorithm, Monotonic Q-…

cs.LG2025

Variance-Dependent Regret Lower Bounds for Contextual Bandits

Jiafan He, Quanquan Gu

Variance-dependent regret bounds for linear contextual bandits, which improve upon the classical regret bound to , whe…

cs.LG2025

Reinforcement Learning from Human Feedback with Active Queries

Kaixuan Ji, Jiafan He, Quanquan Gu

Aligning large language models (LLM) with human preference plays a key role in building modern generative models and can be achieved by reinforcement learning from human feedback (…

cs.LG2024

Achieving Constant Regret in Linear Markov Decision Processes

Weitong Zhang, Zhiyuan Fan, Jiafan He +1

We study the constant regret guarantees in reinforcement learning (RL). Our objective is to design an algorithm that incurs only finite regret over infinite episodes with high prob…