Search Results for author:
Found 27 papers, 12 papers with code
Embodied LLM Agents Learn to Cooperate in Organized Teams
Large Language Models (LLMs) have emerged as integral tools for reasoning, planning, and decision-making, drawing upon their extensive world knowledge and proficiency in language-related tasks.
StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows
In StateFlow, we distinguish between "process grounding" (via state and state transitions) and "sub-task solving" (through actions within a state), enhancing control and interpretability of the task-solving procedure.
AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
Through conducting extensive experiments on a large scale of harmful and safe prompts, we validate the effectiveness of the proposed AutoDefense in improving the robustness against jailbreak attacks, while maintaining the performance at normal user request.
Training Language Model Agents without Modifying Language Models
Researchers and practitioners have recently reframed powerful Large Language Models (LLMs) as agents, enabling them to automate complex tasks largely via the use of specialized functions.
Towards better Human-Agent Alignment: Assessing Task Utility in LLM-Powered Applications
The rapid development in the field of Large Language Models (LLMs) has led to a surge in applications that facilitate collaboration among multiple agents to assist humans in their daily tasks.
Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraints
Coreset selection is powerful in reducing computational costs and accelerating data processing for deep learning algorithms.
IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models
However, since the prompts need to be sampled from a large volume of annotated examples, finding the right prompt may result in high annotation costs.
Adversarial Attacks on Combinatorial Multi-Armed Bandits
Contrary to prior understanding of multi-armed bandits, our work reveals a surprising fact that the attackability of a specific CMAB instance also depends on whether the bandit instance is known or unknown to the adversary.
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
AutoGen is an open-source framework that allows developers to build LLM applications via multiple agents that can converse with each other to accomplish tasks.
Unified Off-Policy Learning to Rank: a Reinforcement Learning Perspective
Building upon this, we leverage offline RL techniques for off-policy LTR and propose the Click Model-Agnostic Unified Off-policy Learning to Rank (CUOLR) method, which could be easily applied to a wide range of click models.
An Empirical Study on Challenging Math Problem Solving with GPT-4
Employing Large Language Models (LLMs) to address mathematical problems is an intriguing research endeavor, considering the abundance of math problems expressed in natural language across numerous science and engineering fields.
HyperTime: Hyperparameter Optimization for Combating Temporal Distribution Shifts
In this work, we propose a hyperparameter optimization method named \emph{HyperTime} to find hyperparameters robust to potential temporal distribution shifts in the unseen test data.
Provably Efficient Reinforcement Learning for Online Adaptive Influence Maximization
Online influence maximization aims to maximize the influence spread of a content in a social network with unknown network model by selecting a few seed nodes.
Model-based Reinforcement Learning
reinforcement-learning
+1
FairAutoML: Embracing Unfairness Mitigation in AutoML
In this work, we propose an Automated Machine Learning (AutoML) system to search for models not only with good prediction accuracy but also fair.
ChaCha for Online AutoML
We propose the ChaCha (Champion-Challengers) algorithm for making an online choice of hyperparameters in online learning settings.
When and Whom to Collaborate with in a Changing Environment: A Collaborative Dynamic Bandit Solution
However, all existing collaborative bandit learning solutions impose a stationary assumption about the environment, i. e., both user preferences and the dependency among users are assumed static over time.
ECONOMIC HYPERPARAMETER OPTIMIZATION WITH BLENDED SEARCH STRATEGY
We study the problem of using low cost to search for hyperparameter configurations in a large search space with heterogeneous evaluation cost and model quality.
Unifying Clustered and Non-stationary Bandits
Non-stationary bandits and online clustering of bandits lift the restrictive assumptions in contextual bandits and provide solutions to many important real-world scenarios.
Fast Distributed Bandits for Online Recommendation Systems
This algorithm lazily creates clusters in a distributed manner, and dramatically reduces the network data sharing requirement, achieving high scalability.
Seamlessly Unifying Attributes and Items: Conversational Recommendation for Cold-Start Users
In this work, we consider the conversational recommendation for cold-start users, where a system can both ask the attributes from and recommend items to a user interactively.
Frugal Optimization for Cost-related Hyperparameters
To address this problem, we develop a new cost-frugal HPO solution.
Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems
Recommender systems are embracing conversational technologies to obtain user preferences dynamically, and to overcome inherent limitations of their static models.
FLAML: A Fast and Lightweight AutoML Library
We study the problem of using low computational cost to automate the choices of learners and hyperparameters for an ad-hoc training dataset and error metric, by conducting trials of different configurations on the given training data.
Variance Reduction in Gradient Exploration for Online Learning to Rank
We prove that the projected gradient is an unbiased estimation of the true gradient, and show that this lower-variance gradient estimation results in significant regret reduction.
Factorization Bandits for Online Influence Maximization
We capitalize on an important property of the influence maximization problem named network assortativity, which is ignored by most existing works in online influence maximization.
Bandit Learning with Implicit Feedback
Implicit feedback, such as user clicks, although abundant in online information service systems, does not provide substantial evidence on users' evaluation of system's output.
Learning Contextual Bandits in a Non-stationary Environment
Multi-armed bandit algorithms have become a reference solution for handling the explore/exploit dilemma in recommender systems, and many other important real-world problems, such as display advertisement.
