4 papers
TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning
Heming Zou, Qi Wang, Yun Qu +9
Reinforcement learning with verifiable rewards (RLVR) is a promising approach for enhancing reasoning and agentic behavior in large language models. However, rollout-intensive poli…
Kwai Keye-VL-2.0 Technical Report
Kwai Keye Team, Bin Wen, Changyi Liu +50
We introduce Kwai Keye-VL-2.0-30B-A3B, an open-source Mixture-of-Experts (MoE) multimodal foundation model designed to advance long-video understanding and agentic intelligence. To…
ElectriQ: A Benchmark for Assessing the Response Capability of Large Language Models in Power Marketing
Jinzhi Wang, Qingke Peng, Haozhou Li +7
As power systems decarbonise and digitalise, high penetrations of distributed energy resources and flexible tariffs make electric power marketing (EPM) a key interface between regu…
LumiCRS: Asymmetric Contrastive Prototype Learning for Long-Tail Conversational Recommender Systems
Jinzhi Wang, Bin Li, Qingke Peng +7
Conversational recommender systems (CRSs) often suffer from an extreme long-tail distribution of dialogue data, causing a strong bias toward head-frequency blockbusters that sacrif…