Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data.
VLDB 2026 Research / reviewers in the wild / expert

Charles Sun

dblp:66/9626 · DBLP profile ↗
← Back
2ranked-venue papers
0as first author
1since 2021 · last 2025
—ORCID · none

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 1 · 1 since 2021Applied, interdisciplinary, general and emerging computing · 1

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Artificial intelligence
1 paper
Reinforcement learning · 59% Language models and text generation · 20% Question answering and dialogue systems · 20%

Topics — the 7 heaviest of 7, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Natural language and speech › Language models and text generation
LLM agents		 0.912025
LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models · ICML 2025
Natural language and speech › Question answering and dialogue systems
multi-turn interaction		 0.912025
LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models · ICML 2025
Machine learning › Reinforcement learning
multi-turn reinforcement learning		 0.912025
LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models · ICML 2025
Machine learning › Reinforcement learning
reinforcement learning from human feedback		 0.912025
LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models · ICML 2025
Machine learning › Reinforcement learning
offline reinforcement learning		 0.312025
LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models · ICML 2025
Machine learning › Reinforcement learning › online decision making
online reinforcement learning		 0.312025
LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models · ICML 2025
Machine learning › Reinforcement learning
value-based reinforcement learning		 0.312025
LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models · ICML 2025

Methods — techniques the papers use, named apart from their topics

online policy-based RL · 0.9offline value-based RL · 0.9
YearPublicationVenuePosition
2025 LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models
abstract
Large language models (LLMs) provide excellent text-generation capabilities, but standard prompting and generation methods generally do not lead to intentional or goal-directed agents and might necessitate considerable prompt tuning. Even the best current LLMs rarely ask clarifying questions, engage in explicit information gathering, or take actions that lead to better decisions after multiple turns. Reinforcement learning has the potential to leverage the powerful modeling capabilities of LLMs, as well as their internal representation of textual interactions, to create capable goal-directed language agents. This can enable intentional and temporally extended interactions, such as with humans, the emergence of complex skills such as persuasion, and long-horizon strategic behavior, such as in the context of games. Enabling this requires the community to develop reliable reinforcement learning algorithms for training LLMs. Developing such algorithms requires tasks that can gauge progress on algorithm design, provide accessible and reproducible evaluations for multi-turn interactions, and cover a range of task properties and challenges in improving reinforcement learning algorithms. Our paper introduces the LMRL-Gym benchmark for evaluating multi-turn RL for LLMs, together with an open-source research framework for getting started on multi-turn RL with offline value-based and online policy-based RL methods. Our benchmark consists of 3 Interactive Dialogue tasks and 5 RL Capability tests for a total of 8 tasks, which require multiple rounds of language interaction and cover a range of tasks in open-ended dialogue and text games.
Marwa Abdulhai, Isadora White, Charlie Snell, Charles Sun, Joey Hong, Yuexiang Zhai, Kelvin Xu, Sergey Levine
 ICML4
2008 Variability in the Atlantic Meridional Overturning Circulation and Heat Transport Detected Remotely from Argo Floats
abstract
Available data for ocean temperature, salinity, and current at the present time do not have sufficient resolution to describe the variability in Atlantic Meridional Overturning Circulation (AMOC). To fill the gap, we are working on near real-time 3D synoptic temperature, salinity, and velocity (STSV) datasets from remotely sensed Argo profiling and trajectory data together with the Global Temperature-Salinity Profile Program (GTSPP), Navy's MOODS, and the OSCAR data using the optimal spectral decomposition (OSD) method. With establishment of the STSV dataset, the AMOC variability can be effectively detected and predicted.
Peter C. Chu, Charles Sun, Oleg V. Melnichenko
 IGARSS (3)2