0

Tong Zhu

Papers
19

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
19papers

Authored papers

19

Toward Efficient Agents: Memory, Tool learning, and Planning

arXiv 2026

2026

π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows

arXiv 2026

2026

Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs

arXiv 2026

2026

GEMS: Agent-Native Multimodal Generation with Memory and Skills

arXiv 2026

2026

Linear-MoE: Linear Sequence Modeling Meets Mixture-of-Experts

arXiv 2025

2025

DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models

arXiv 2025

2025

Speed Always Wins: A Survey on Efficient Architectures for Large Language Models

arXiv 2025

2025

Chain-of-Tools: Utilizing Massive Unseen Tools in the CoT Reasoning of Frozen Language Models

arXiv 2025

2025

LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training

arXiv 2024

2024

CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling

arXiv 2024

2024

LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training

arXiv 2024

2024

Timo: Towards Better Temporal Reasoning for Language Models

arXiv 2024

2024

NesTools: A Dataset for Evaluating Nested Tool Learning Abilities of Large Language Models

arXiv 2024

2024

ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLM

arXiv 2024

2024

Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed Benchmark

arXiv 2024

2024

Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts

arXiv 2024

2024

Learning to Refuse: Towards Mitigating Privacy Risks in LLMs

arXiv 2024

2024

Mirror: A Universal Framework for Various Information Extraction Tasks

arXiv 2023

2023

Closed-loop Error Correction Learning Accelerates Experimental Discovery of Thermoelectric Materials

arXiv 2023

2023

Affiliations

No known affiliations.

Frequent co-authors

10

from 19 papers