AI
Benchmarking Document Parsers on Mathematical Formula Extraction from PDFs
Researchers have developed a new framework to evaluate the performance of document parsers in extrac...
AI
An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift
Researchers conducted an empirical study to investigate how well preference tuning works when applie...
AI
LLM-Based Adversarial Persuasion Attacks on Fact-Checking Systems
Researchers have developed a new type of attack on fact-checking systems that use artificial intelli...
AI
PEAfowl: Perception-Enhanced Multi-View Vision-Language-Action for Bimanual Manipulation
Researchers have developed a new AI model called PEAfowl that can improve the performance of robots ...
AI
Dynamic Cogeneration of Bug Reproduction Test in Agentic Program Repair
Researchers propose a method for automatically generating both fixes and bug rep...
AI
Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks
Researchers have proposed a new method for approximating complex functions in co...
AI
Procedural Knowledge Extraction from Industrial Troubleshooting Guides Using Vision Language Models
Researchers have developed a method to extract procedural knowledge from industr...
AI
Backdoor Sentinel: Detecting and Detoxifying Backdoors in Diffusion Models via Temporal Noise Consistency
Researchers have developed a method to detect and remove backdoors in diffusion ...