Picture for Yuan Lin

Yuan Lin

StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identification

Add code
Nov 11, 2024
Figure 1 for StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identification
Figure 2 for StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identification
Figure 3 for StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identification
Figure 4 for StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identification
Viaarxiv icon

IPEval: A Bilingual Intellectual Property Agency Consultation Evaluation Benchmark for Large Language Models

Add code
Jun 18, 2024
Figure 1 for IPEval: A Bilingual Intellectual Property Agency Consultation Evaluation Benchmark for Large Language Models
Figure 2 for IPEval: A Bilingual Intellectual Property Agency Consultation Evaluation Benchmark for Large Language Models
Figure 3 for IPEval: A Bilingual Intellectual Property Agency Consultation Evaluation Benchmark for Large Language Models
Figure 4 for IPEval: A Bilingual Intellectual Property Agency Consultation Evaluation Benchmark for Large Language Models
Viaarxiv icon

AGILE: A Novel Framework of LLM Agents

Add code
May 23, 2024
Viaarxiv icon

Autonomous vehicle decision and control through reinforcement learning with traffic flow randomization

Add code
Mar 05, 2024
Viaarxiv icon

Safe Hybrid-Action Reinforcement Learning-Based Decision and Control for Discretionary Lane Change

Add code
Mar 01, 2024
Viaarxiv icon

Discretionary Lane-Change Decision and Control via Parameterized Soft Actor-Critic for Hybrid Action Space

Add code
Feb 24, 2024
Viaarxiv icon

Steady-State Error Compensation for Reinforcement Learning with Quadratic Rewards

Add code
Feb 14, 2024
Viaarxiv icon

AutoEval-Video: An Automatic Benchmark for Assessing Large Vision Language Models in Open-Ended Video Question Answering

Add code
Nov 25, 2023
Viaarxiv icon

Bi-Preference Learning Heterogeneous Hypergraph Networks for Session-based Recommendation

Add code
Nov 02, 2023
Viaarxiv icon

Mixed-Integer Optimal Control via Reinforcement Learning: A Case Study on Hybrid Vehicle Energy Management

Add code
May 02, 2023
Viaarxiv icon