activity
20242026
collaborators

5 papers

cs.CL2026

RCPU: Rotation-Constrained Error Compensation for Structured Pruning of Large Language Models

Shuichiro Haruta, Kazunori Matsumoto, Zhi Li +2

In this paper, we propose a rotation-constrained compensation method to address the errors introduced by structured pruning of large language models (LLMs). LLMs are trained on mas…

cs.CV2025

CoTasks: Chain-of-Thought based Video Instruction Tuning Tasks

Yanan Wang, Julio Vizcarra, Zhi Li +2

Despite recent progress in video large language models (VideoLLMs), a key open challenge remains: how to equip models with chain-of-thought (CoT) reasoning abilities grounded in fi…

cs.CV2024

Top-down Activity Representation Learning for Video Question Answering

Yanan Wang, Shuichiro Haruta, Donghuo Zeng +2

Capturing complex hierarchical human activities, from atomic actions (e.g., picking up one present, moving to the sofa, unwrapping the present) to contextual events (e.g., celebrat…

cs.CV2024

Multi-object event graph representation learning for Video Question Answering

Yanan Wang, Shuichiro Haruta, Donghuo Zeng +2

Video question answering (VideoQA) is a task to predict the correct answer to questions posed about a given video. The system must comprehend spatial and temporal relationships amo…

quant-ph2024

QWalkVec: Node Embedding by Quantum Walk

Rei Sato, Shuichiro Haruta, Kazuhiro Saito +1

In this paper, we propose QWalkVec, a quantum walk-based node embedding method. A quantum walk is a quantum version of a random walk that demonstrates a faster propagation than a r…