5 papers
Batch-wise Adaptive Pruning: Periodic Neuron Activation-Aware Weight Pruning for Language Reasoning Model
Yongmin Kim, Shota Takashiro, Yusuke Iwasawa +2
Large Reasoning Models (LRMs) achieve strong performance on complex tasks through extended chain-of-thought generation, but incur substantial computational costs during inference.…
OrderGrad: Optimizing Beyond the Mean with Order-Statistic Policy Gradient Estimation
Paavo Parmas, Yongmin Kim, Kohsei Matsutani +5
Policy-gradient methods usually optimize expected return, but many real world applications care about distributional properties of returns: tail risk, outlier robustness, or best-o…
On Advantage Estimates for Max@K Policy Gradients
Shota Takashiro, Soichiro Nishimori, Paavo Parmas +6
Reinforcement learning with verifiable rewards is widely used for post-training reasoning models, but sparse outcome rewards make exploration difficult. A complementary approach is…
-MoE: Generalizing Mixture of Experts to Infinite Experts
Shota Takashiro, Takeshi Kojima, Shohei Taniguchi +2
The Mixture of Experts (MoE) selects a few feed-forward networks (FFNs) per token, achieving an effective trade-off between computational cost and performance. In conventional MoE,…
Answer When Needed, Forget When Not: Language Models Pretend to Forget via In-Context Knowledge Unlearning
Shota Takashiro, Takeshi Kojima, Andrew Gambardella +3
As large language models (LLMs) are applied across diverse domains, the ability to selectively unlearn specific information is becoming increasingly essential. For instance, LLMs a…