Zhiyuan Liu

30

Papers

2,430

Total Citations

1

Affiliations

Affiliations

National University of Singapore

Papers (30)

ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs

AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors

RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback

KoLA: Carefully Benchmarking World Knowledge of Large Language Models

Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages

Towards 3D Molecule-Text Interpretation in Language Models

RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness

Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance

Dataset Distillation with Neural Characteristic Function: A Minmax Perspective

Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis

Predicting Emergent Abilities with Infinite Resolution Evaluation

XLRS-Bench: Could Your Multimodal LLMs Understand Extremely Large Ultra-High-Resolution Remote Sensing Imagery?

AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation

WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language Models

A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules

Graph Coarsening via Supervised Granular-Ball for Scalable Graph Neural Network Training

Learning to Focus: Causal Attention Distillation via Gradient‐Guided Token Pruning

Rational Decision-Making Agent with Learning Internal Utility Judgment

Visual Distant Supervision for Scene Graph Generation

ULTRAFEEDBACK: Boosting Language Models with Scaled AI Feedback

Exploring the Benefit of Activation Sparsity in Pre-training

NExT-Chat: An LMM for Chat, Detection and Segmentation

Fine-Grained Scene Graph Generation with Data Transfer

Graph Policy Network for Transferable Active Learning on Graphs

Moderate-fitting as a Natural Backdoor Defender for Pre-trained Language Models

A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks

Sparse Structure Search for Delta Tuning

VPGTrans: Transfer Visual Prompt Generator across LLMs

H3T: Efficient Integration of Memory Optimization and Parallelism for Large-scale Transformer Training

Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evaluations