ServiceNow IA recherche

9

DoomArena: A framework for Testing AI Agents Against Evolving Security Threats
DoomArena: A framework for Testing AI Agents Against Evolving Security Threats
We present DoomArena, a security evaluation framework for AI agents. DoomArena is designed on three principles: 1) It is a …
Workshop at the International Conference of Machine Learning (ICML),  2025.
Article Citation Code
How to Train Your LLM Web Agent: A Statistical Diagnosis (Oral)
How to Train Your LLM Web Agent: A Statistical Diagnosis (Oral)

Large language model (LLM) agents for web interfaces have advanced rapidly, yet open-source systems still lag behind proprietary …

Workshop at the International Conference of Machine Learning (ICML),  2025.
Article Citation
Silent Sabotage: Injecting Backdoors into AI Agents Through Fine-Tuning
Silent Sabotage: Injecting Backdoors into AI Agents Through Fine-Tuning
The rise of AI agents that can use tools, browse the web and interact with computers on behalf of a user, has sparked strong interest …
Workshop at the International Conference of Machine Learning (ICML),  2025.
Article Citation
WebMMU: A Benchmark for Multimodal Multilingual Website Understanding and Code Generation
WebMMU: A Benchmark for Multimodal Multilingual Website Understanding and Code Generation
Understanding diverse web data and automating web development presents an exciting challenge for agentic AI. While existing benchmarks …
Workshop at the Computer Vision and Pattern Recognition Conference (CVPR),  2025.
Article Citation
Backpropagating from Customer Success
Backpropagating from Customer Success
How do we measure the real performance of AI in enterprise—beyond just model performance? This work introduces a research project …
Conference on Human Factors in Computing Systems (ACM-CHI),  2025.
Citation Vidéo
AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Understanding
AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Understanding
Aligning visual features with language embeddings is a key challenge in vision-language models (VLMs). The performance of such models …
Workshop at the International Conference of Learning Representation (ICLR),  2025.
Article Citation Code
Learning to Defer for Causal Discovery with Imperfect Experts
Learning to Defer for Causal Discovery with Imperfect Experts
Integrating expert knowledge, e.g. from large language models, into causal discovery algorithms can be challenging when the knowledge …
Workshop at the International Conference of Learning Representation (ICLR),  2025.
Article Citation
No, of course I can! Refusal Mechanisms Can Be Exploited Using Harmless Fine-Tuning Data
No, of course I can! Refusal Mechanisms Can Be Exploited Using Harmless Fine-Tuning Data
Leading language model (LM) providers like OpenAI and Google offer fine-tuning APIs that allow customers to adapt LMs for specific use …
Workshop at the International Conference of Learning Representation (ICLR),  2025.
Article Citation Vidéo
Societal Alignment Frameworks Can Improve LLM Alignment
Societal Alignment Frameworks Can Improve LLM Alignment
Recent progress in large language models (LLMs) has focused on producing responses that meet human expectations and align with shared …
Workshop at the International Conference of Learning Representation (ICLR),  2025.
Article Citation
The Landscape of Causal Discovery Data: Grounding Causal Discovery in Real-World Applications
The Landscape of Causal Discovery Data: Grounding Causal Discovery in Real-World Applications
Causal discovery aims to automatically uncover causal relationships from data, a capability with significant potential across many …
Workshop at the International Conference of Learning Representation (ICLR),  2025.
Article Citation Code