pith. sign in

Hong Peng

Identifiers

  • name variant Hong Peng 0.60 · backfill

Papers (2)

  1. On the Implicit Reward Overfitting and the Low-rank Dynamics in RLVR cs.LG · 2026 · author #8
  2. Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning cs.CV · 2026 · author #16

Mentions

  • 2601.06943 #16 · arxiv_oai · confidence 0.70 Hong Peng

Frequent Coauthors