9 citations · 10 across the 8 of their papers we have counts for
9 papers
Causal Analysis and Mitigation of Spurious Onsets in Full-Duplex Speech LLMs
Kento Nishi
Speech-to-speech LLMs like Moshi, and its derivative PersonaPlex, can listen and speak concurrently through full-duplex generation. However, they can begin speaking inappropriately…
Governing AI Research Through Peer Review: A Mixed-Methods Study of the Longitudinal Effects of Ethics Flags Across Resubmissions
Kento Nishi, Alec Laprevotte, Isaiah Bullock +1
Selective AI conferences have recently begun enforcing ethics flags and related review requirements, with the goal being to steer research towards safer and more responsible practi…
Evolutionary Curriculum Learning Improves Biological Sequence Modeling
Richard Zhu, Kento Nishi
Variational autoencoders (VAEs) trained on multiple sequence alignments (MSAs) have emerged as powerful generative models for biological sequences, with applications ranging from d…
Mechanisms of Misgeneralization in Physical Sequence Modeling
Kento Nishi, Raphael Tang, Karun Kumar +2
Generative sequence models are often trained to plan motion in physical domains, from robotics to mechanical simulations. When constructing a dataset to train such a model, enginee…
ICLR: In-Context Learning of Representations
Core Francisco Park, Andrew Lee, Ekdeep Singh Lubana +5
Recent work has demonstrated that semantics specified by pretraining data influence how representations of different concepts are organized in a large language model (LLM). However…
Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing
Kento Nishi, Rahul Ramesh, Maya Okawa +3
Knowledge Editing (KE) algorithms alter models' weights to perform targeted updates to incorrect, outdated, or otherwise unwanted factual associations. However, recent work has sho…
Joint-Task Regularization for Partially Labeled Multi-Task Learning
Kento Nishi, Junsik Kim, Wanhua Li +1
Multi-task learning has become increasingly popular in the machine learning field, but its practicality is hindered by the need for large, labeled datasets. Most multi-task learnin…
Towards an Understanding of Stepwise Inference in Transformers: A Synthetic Graph Navigation Model
Mikail Khona, Maya Okawa, Jan Hula +5
Stepwise inference protocols, such as scratchpads and chain-of-thought, help language models solve complex problems by decomposing them into a sequence of simpler subproblems. Desp…
Augmentation Strategies for Learning with Noisy Labels
Kento Nishi, Yi Ding, Alex Rich +1
Imperfect labels are ubiquitous in real-world datasets. Several recent successful methods for training deep neural networks (DNNs) robust to label noise have used two primary techn…