Wenwu Ou
2 papers · Latest:
Artificial Intelligence
IG-Search: Step-Level Information Gain Rewards for Search-Augmented Reasoning
IG-Search introduces a novel step-level Information Gain reward for RL-trained LLMs, significantly improving search-augmented reasoning performance and efficiency.
2604.15148
Machine LearningAlternating Multi-bit Quantization for Recurrent Neural Networks
This paper proposes an alternating multi-bit quantization method for RNNs that significantly reduces model size and speeds up inference with minimal accuracy loss.
1802.00150
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.