Actualités
From Perception to Action: The Role of World Models in Embodied AI Systems
Introduction to Embodied AI Agents Embodied AI agents are systems that exist in physical or...
From Individuals to Interactions: Benchmarking Gender Bias in Multimodal Large Language Models from the Lens of Social Relationship
arXiv:2506.23101v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have shown impressive capabilities across...
From hallucinations to hardware: Lessons from a real-world computer vision project gone sideways
What we tried, what didn’t work and how a combination of approaches eventually helped us...
From disruption to reinvention: How knowledge workers can thrive after AI
We are beginning a cognitive migration: Away from what AI now does well, and toward...
From Clicking to Reasoning: WebChoreArena Benchmark Challenges Agents with Memory-Heavy and Multi-Page Tasks
Web automation agents have become a growing focus in artificial intelligence, particularly due to their...
FRIDA to the Rescue! Analyzing Synthetic Data Effectiveness in Object-Based Common Sense Reasoning for Disaster Response
arXiv:2502.18452v3 Announce Type: replace Abstract: During Human Robot Interactions in disaster relief scenarios, Large Language...
Foxconn builds AI factory in partnership with Taiwan and Nvidia
Nvidia and Foxconn announced they are working with the Taiwan government to build an AI...
Four reasons to be optimistic about AI’s energy usage
The day after his inauguration in January, President Donald Trump announced Stargate, a $500 billion...
Format-Adapter: Improving Reasoning Capability of LLMs by Adapting Suitable Format
arXiv:2506.23133v1 Announce Type: new Abstract: Generating and voting multiple answers is an effective method to...
Forget the hype — real AI agents solve bounded problems, not open-world fantasies
Event-driven multi-agent systems are a practical architecture for working with imperfect tools in a structured...
Forensic deepfake audio detection using segmental speech features
arXiv:2505.13847v1 Announce Type: cross Abstract: This study explores the potential of using acoustic features of...
Forcing LLMs to be evil during training can make them nicer in the long run
A new study from Anthropic suggests that traits such as sycophancy or evilness are associated...
