2 citations · 2 across the 11 of their papers we have counts for
13 papers
Learning to Be Monitored: Causal Bounds and Intervention-Aware Post-Training Recipes for Chain-of-Thought Monitorability
Qiang Fu, Xinyue Li, Andre Wibisono +1
Chain-of-thought (CoT) monitoring aims to detect potentially harmful behaviors in large language models (LLMs) from their CoTs. Intervention-based evaluations measure this property…
Kimi K3: Open Frontier Intelligence
Kimi Team, Tongtong Bai, Yifan Bai +398
We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision capabilities, and a 1-million-token context window. Kimi K3 is…
Deep (Predictive) Discounted Counterfactual Regret Minimization
Hang Xu, Kai Li, Haobo Fu +3
Counterfactual regret minimization (CFR) is a family of algorithms for effectively solving imperfect-information games. To enhance CFR's applicability in large games, researchers u…
Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning
Jinmin He, Kai Li, Yifan Zang +4
Offline multi-task reinforcement learning aims to learn a unified policy capable of solving multiple tasks using only pre-collected task-mixed datasets, without requiring any onlin…
Efficient Multi-Task Reinforcement Learning with Cross-Task Policy Guidance
Jinmin He, Kai Li, Yifan Zang +4
Multi-task reinforcement learning endeavors to efficiently leverage shared information across various tasks, facilitating the simultaneous learning of multiple tasks. Existing appr…
Hamiltonian Descent Algorithms for Optimization: Accelerated Rates via Randomized Integration Time
Qiang Fu, Andre Wibisono
We study the Hamiltonian flow for optimization (HF-opt), which simulates the Hamiltonian dynamics for some integration time and resets the velocity to to decrease the objective…
Preference Goal Tuning: Post-Training as Latent Control for Frozen Policies
Guangyu Zhao, Kewei Lian, Haoxuan Ru +8
Goal-conditioned policies enable decision-making models to execute diverse behaviors based on specified goals, yet their downstream performance is often highly sensitive to the cho…
Diverse Policies Recovering via Pointwise Mutual Information Weighted Imitation Learning
Hanlin Yang, Jian Yao, Weiming Liu +13
Recovering a spectrum of diverse policies from a set of expert trajectories is an important research topic in imitation learning. After determining a latent style for a trajectory,…
Minimizing Weighted Counterfactual Regret with Optimistic Online Mirror Descent
Hang Xu, Kai Li, Bingyun Liu +4
Counterfactual regret minimization (CFR) is a family of algorithms for effectively solving imperfect-information games. It decomposes the total regret into counterfactual regrets,…
Enhance Reasoning for Large Language Models in the Game Werewolf
Shuang Wu, Liwen Zhu, Tao Yang +4
This paper presents an innovative framework that integrates Large Language Models (LLMs) with an external Thinker module to enhance the reasoning capabilities of LLM-based agents.…
Not All Tasks Are Equally Difficult: Multi-Task Deep Reinforcement Learning with Dynamic Depth Routing
Jinmin He, Kai Li, Yifan Zang +4
Multi-task reinforcement learning endeavors to accomplish a set of different tasks with a single policy. To enhance data efficiency by sharing parameters across multiple tasks, a c…
Mean-field underdamped Langevin dynamics and its spacetime discretization
Qiang Fu, Ashia Wilson
We propose a new method called the N-particle underdamped Langevin algorithm for optimizing a special class of non-linear functionals defined over the space of probability measures…
Diversity from Human Feedback
Ren-Jian Wang, Ke Xue, Yutong Wang +4
Diversity plays a significant role in many problems, such as ensemble learning, reinforcement learning, and combinatorial optimization. How to define the diversity measure is a lon…