Search-Aware Reinforcement Learning for Multi-Component Query Understanding in Roblox Game Search
A search-aware reinforcement learning framework for query understanding in Roblox Game Search improves search quality by 8.9 points over SFT policy.
70
AI model
large language models (LLMs)
- Mentions · 7d0
- Mentions · 30d0
- All mentions2
- First seenSep 23, 2026
- Last mentionedSep 24, 2026
Timeline
2 articles · newest firstYour Model Is Leaking: Covert Information Transfer through LLM Residual Streams
A residual-stream covert-channel attack hides sensitive information in LLM intermediate activations, recoverable with a simple linear decoder without retraining or weight modification.
70
Appears with
- covert-channel attackmalware · 1
- privacy-sensitive organizationsorganization · 1
- LLMai model · 1
- large language models (LLMs)product · 1
- Robloxorganization · 1
- Roblox Game Searchproduct · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.