Showing 2026Show all
2 papers · 1 filter
cs.LG2026
ERR+: Sequential Entropy Resolution for Efficient and Decisive LLM Reasoning
Xin Jiang, Minhao Wang, Wen Wu +4
Large reasoning models achieve strong performance on complex tasks by generating extended chain-of-thought (CoT) traces via reinforcement learning with verifiable rewards (RLVR). W…
cs.LG2026
Learning Variable-Length Tokenization for Generative Recommendation
Minhao Wang, Bowen Wu, Wei Zhang
Generative recommendation reformulates recommendation as next-token prediction over discrete semantic identifiers (IDs). A fundamental yet unexplored design choice is that existing…