Wei Li
7 papers · Latest:
ConsisVLA-4D: Advancing Spatiotemporal Consistency in Efficient 3D-Perception and 4D-Reasoning for Robotic Manipulation
ConsisVLA-4D enhances robotic manipulation by improving spatiotemporal consistency in 3D perception and 4D reasoning, achieving significant speedups.
GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
GLM-5V-Turbo is a new foundation model integrating multimodal perception natively for enhanced agent reasoning, planning, and tool use across diverse contexts.
Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models
Prefill-Time Intervention (PTI) reduces hallucinations in LVLMs by correcting errors in the KV cache during the prefill stage, before accumulation.
Physics-Informed Neural Networks for Methane Sorption: Cross-Gas Transfer Learning, Ensemble Collapse Under Physics Constraints, and Monte Carlo Dropout Uncertainty Quantification
A PINN framework uses transfer learning from hydrogen to accurately predict methane sorption in coal, identifying Monte Carlo Dropout as the best UQ method.
V2E: Validating Smart Contract Vulnerabilities through Profit-driven Exploit Generation and Execution
V2E validates smart contract vulnerabilities by generating and refining profit-driven exploits, confirming real-world exploitability and financial loss.
The Llama 3 Herd of Models
Llama 3 is a new family of large multilingual foundation models excelling in language, coding, reasoning, and multimodal tasks, rivaling GPT-4 in quality and offering extensive public releases.
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
This paper introduces a unified text-to-text framework for transfer learning in NLP, achieving state-of-the-art results across diverse language tasks by systematically exploring pre-training and fine-tuning strategies.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.