Appears on
Articles5
T
Contextual Rollout Bandits: A Neural Scheduling Framework for Efficient Reinforcement Learning with Verifiable Rewards
Insight
Shared by @ai-firehose.column.social on Bluesky ↗
arxiv.org4d ago
RICP: A Teacher-Student Framework for Retrieved In-Context Principles from Mistakes in LLMs
Insight
Shared by @ai-firehose.column.social on Bluesky ↗arxiv.org4d ago
Open-Weight AI Video Models Enable Non-Consensual Deepfake Imagery, Study Finds
Insight
Shared by @ai-firehose.column.social on Bluesky ↗arxiv.org4d ago
Eureka: An LLM-Driven Framework for Automated Feature Engineering in Enterprise AI
Insight
Shared by @ai-firehose.column.social on Bluesky ↗arxiv.org4d ago
HSIR: New Method Improves Self-Improvement Training for Large Reasoning Models
Insight
Shared by @ai-firehose.column.social on Bluesky ↗arxiv.org5d ago