Lidong Bing

11

Papers

638

Total Citations

Papers (11)

Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding

Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources

VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM

MOOSE-Chem2: Exploring LLM Limits in Fine-Grained Scientific Hypothesis Discovery via Hierarchical Search

Evolving Prompts In-Context: An Open-ended, Self-replicating Perspective

ECBench: Can Multi-modal Foundation Models Understand the Egocentric World? A Holistic Embodied Cognition Benchmark

Breaking the Memory Barrier of Contrastive Loss via Tile-Based Strategy

2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining

Semi-Supervised Learning with Declaratively Specified Entropy Constraints

M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models

From Cloze to Comprehension: Retrofitting Pre-trained Masked Language Models to Pre-trained Machine Reader