103 citations · 120 across the 63 of their papers we have counts for
71 papers
Who Is the Influencer? Consensus Dynamics in Multi-Agent Systems
Gouki Minegishi, Jingyuan Feng, Hiroki Furuta +3
Multi-agent LLM systems are increasingly used in practice, but their behavior is complex and hard to understand. We design a simple task to ask which model has the most influence o…
Neural Dimensional Analysis: Foundations of Dimensionless and Scale-Consistent Computation
Bum Jun Kim, Makoto Kawano, Yusuke Iwasawa +1
Modern Transformers rely on many scale-control mechanisms, including normalization, residual scaling, attention temperatures, loss weighting, and adaptive updates. To explain how t…
Matching Object or Relation? Tracing Abstract Reasoning Inside VLMs
Gouki Minegishi, Hiroki Furuta, Takeshi Kojima +2
Vision Language Models (VLMs) excel on visual benchmarks but fail systematically on tasks requiring abstract reasoning. Existing benchmarks document this failure but cannot say \em…
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…
Steering Recurrent Reasoners at Inference Time with Readout Feedback
Shunsuke Kamiya, Masanori Koyama, Seongcheol Jeong +5
Recurrent models, which repeatedly update latent states with shared computation blocks, have emerged as powerful architectures for solving complex reasoning tasks. Existing inferen…
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.…
Bootstrapping Niche Multilingual Code Translation via Reinforcement Learning with Execution-Based Verifiable Supervision
Kouki Yuki, Jie Zeng, Kyoko Ogawa +6
Code translation must preserve executable behavior across many programming languages, yet neural code translation has largely focused on a few popular languages such as C++, Java,…
Auditing Instruction-Trajectory Mismatches in Multimodal Robot Demonstrations
Simon Holk, Ryosuke Takanami, Tatsuya Matsushima +4
Robot demonstration datasets used to train vision-language-action policies can contain a subtle but harmful failure mode: trajectories that are behaviorally correct but paired with…
Looped Transformers with Source-Centered State Evolution
Bum Jun Kim, Kohei Hayashi, Shunsuke Kamiya +3
Looped Transformers create a useful train- and test-time compute axis by reusing the same Transformer block over recurrent depth, increasing effective depth at a fixed parameter co…
CHASE: Cache-Hole-Adapted Skip Exit for Looped State-Space Language Models
Zhenxuan Yu, Takeshi Kojima, Yutaka Matsuo +1
Recent work on looped language models suggests that many reasoning problems benefit from greater computational depth rather than from additional independent parameters. Existing st…
SMC-ITA: Sequential Monte Carlo Inference-Time Alignment for Video-to-Audio Generation
Haoyu Zhang, Yuta Oshima, Xingjian Du +4
Video-to-audio (V2A) generation must jointly satisfy audiovisual alignment, semantic consistency, temporal synchronization, and perceptual quality. While prior work has mainly focu…
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…
Clustered Self-Assessment: A Simple yet Effective Method for Uncertainty Quantification in Large Language Models
Qi Cao, Takeshi Kojima, Andrew Gambardella +3
Large language models (LLMs) demonstrate remarkable performance across diverse tasks, but they often generate responses that appear plausible while being factually incorrect. This…
JMed48k: A Multi-Profession Japanese Medical Licensing Benchmark for Vision-Language Model Evaluation
Yue Xun, Junyu Liu, Qian Niu +10
We introduce JMed48k, a multi-profession Japanese healthcare licensing benchmark for evaluating vision-language models. Built from official PDF materials released by the Japanese M…
QuadNorm: Resolution-Robust Normalization for Neural Operators
Bum Jun Kim, Makoto Kawano, Yusuke Iwasawa +1
Normalization layers in neural operators usually compute statistics by uniformly averaging discrete grid values, making the normalization itself discretization-dependent and thereb…
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…
Does "Do Differentiable Simulators Give Better Policy Gradients?" Give Better Policy Gradients?
Ku Onoda, Paavo Parmas, Manato Yaguchi +1
In policy gradient reinforcement learning, access to a differentiable model enables 1st-order gradient estimation that accelerates learning compared to relying solely on derivative…
C-voting: Confidence-Based Test-Time Voting without Explicit Energy Functions
Kenji Kubo, Shunsuke Kamiya, Masanori Koyama +3
Neural network models with latent recurrent processing, where identical layers are recursively applied to the latent state, have gained attention as promising models for performing…
Understanding Emergent Misalignment via Feature Superposition Geometry
Gouki Minegishi, Hiroki Furuta, Takeshi Kojima +2
Emergent misalignment, where fine-tuning on narrow, non-harmful tasks induces harmful behaviors, poses a key challenge for AI safety in LLMs. Despite growing empirical evidence, it…
E3VS-Bench: A Benchmark for Viewpoint-Dependent Active Perception in 3D Gaussian Splatting Scenes
Koya Sakamoto, Taiki Miyanishi, Daichi Azuma +6
Visual search in 3D environments requires embodied agents to actively explore their surroundings and acquire task-relevant evidence. However, existing visual search and embodied AI…
Exploration of Fast-Slow Latent Recurrence for Train-Short, Test-Long Generalization
Shota Takashiro, Masanori Koyama, Takeru Miyato +3
We study out of distribution generalization in streaming tasks where models are trained on short sequences but must operate over much longer, unknown horizons under bounded memory.…
Semantic Token Clustering for Efficient Uncertainty Quantification in Large Language Models
Qi Cao, Andrew Gambardella, Takeshi Kojima +2
Large language models (LLMs) have demonstrated remarkable capabilities across diverse tasks. However, the truthfulness of their outputs is not guaranteed, and their tendency toward…
Towards High-resolution and Disentangled Reference-based Sketch Colorization
Dingkun Yan, Xinrui Wang, Ru Wang +5
Sketch colorization is a critical task for automating and assisting in the creation of animations and digital illustrations. Previous research identified the primary difficulty as…