activity
20232026
most citedTowards Empirical Interpretation of Internal Circuits and Properties in Grokked Transformers on Modular Polynomials

1 citations · 1 across the 18 of their papers we have counts for

collaborators

19 papers

cs.AI2026

Few-Shot Demonstrations Elicit the Use of In-Context World Representations in LLMs

Kohsei Matsutani, Gouki Minegishi, Core Francisco Park +3

Large language models (LLMs), when acting as agents, are expected to take observed data in context, infer the latent state space underlying the world, and leverage it for downstrea…

cs.AI2026

In-Context Neurofeedback: Can LLMs Control Their Internal Representations through Privileged Access?

Koshiro Aoki, Ryota Takatsuki, Gouki Minegishi +2

Whether large language models (LLMs) can control their own internal representations matters for both machine metacognition and AI safety. A recent study applied neurofeedback to LL…

cs.AI2026

Visual Access Boundaries in Vision-Language Model Reasoning

Hiroto Osaka, Shohei Taniguchi, Gouki Minegishi +3

Chain-of-Thought (CoT) prompting is widely used as a test-time scaling strategy for Vision-Language Models (VLMs), but it remains unclear what is extended when VLMs generate longer…

cs.LG2026

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…

cs.AI2026

Zipping the Thought: When and How Compressed Reasoning Data Works in LLM Post-Training

Kohsei Matsutani, Gouki Minegishi, Takeshi Kojima +2

Large language models (LLMs) can now solve complex problems through long chain-of-thought (CoT) reasoning, but the trade-off between performance and token cost remains a central ch…

cs.CL2026

LIT-RAGBench: Benchmarking Generator Capabilities of Large Language Models in Retrieval-Augmented Generation

Koki Itai, Shunichi Hasegawa, Yuta Yamamoto +2

Retrieval-Augmented Generation (RAG) is a framework in which a Generator, such as a Large Language Model (LLM), produces answers by retrieving documents from an external collection…