LLMpeople
Public Atlas People first, reports as evidence, organizations as context.

Atlas / People / Detail

Wei Shen

Public OpenReview and personal homepage/blog for Wei Shen show work on reinforcement learning from human feedback, adaptive chain-of-thought control, long-context behavior, and LLM data-scaling analysis.

Researcher focused on large language model alignment, RLHF, and reasoning.1 organizations1 reports

Profile status: updated

updated 2 public sources
large language modelsRLHFreasoningalignment

Current frame

Researcher focused on large language model alignment, RLHF, and reasoning.

Extended note

Wei Shen is publicly associated with large language model research through an OpenReview profile and a personal LLM blog. Publicly listed work includes research on RLHF policy filtration, adaptive reasoning-step control, long-sequence behavior under RoPE, and data-scaling effects in preference learning, indicating a focus on alignment, reasoning, and training methodology for LLMs.

Public links

website Wei Shen's LLM Blog google_scholar Google Scholar openreview OpenReview

Organizations

core ByteDance Seed

Reports

Report Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning

Official and primary sources

Wei Shen’s LLM Blog Official source · homepage · Notion Wei Shen | OpenReview Official source · openreview · OpenReview