News
When the solution defines the problem
How AI is reversing traditional problem-solving — and uncovering opportunities we never knew existed Continue reading on...
When Long Helps Short: How Context Length in Supervised Fine-tuning Affects Behavior of Large Language Models
arXiv:2509.18762v1 Announce Type: new Abstract: Large language models (LLMs) have achieved impressive performance across natural...
When Facts Change: Probing LLMs on Evolving Knowledge with evolveQA
arXiv:2510.19172v1 Announce Type: new Abstract: LLMs often fail to handle temporal knowledge conflicts–contradictions arising when...
When and How Long Did Therapy Happen? Soft-Supervising Temporal Localization Using Audio-Language Models
arXiv:2506.09707v3 Announce Type: replace-cross Abstract: Prolonged Exposure (PE) therapy is an effective treatment for post-traumatic...
What your tools miss at 2:13 AM: How gen AI attack chains exploit telemetry lag – Part 1
Explore a strategic 2025 roadmap for cybersecurity leaders to tackle gen AI, insider risks, and...
What Is Context Engineering in AI? Techniques, Use Cases, and Why It Matters
Introduction: What is Context Engineering? Context engineering refers to the discipline of designing, organizing, and...
What is AI Inference? A Technical Deep Dive and Top 9 AI Inference Providers (2025 Edition)
Artificial Intelligence (AI) has evolved rapidly—especially in how models are deployed and operated in real-world...
What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind Attacks
arXiv:2411.03343v2 Announce Type: replace-cross Abstract: Jailbreaks have been a central focus of research regarding the...
What Does Neuro Mean to Cardio? Investigating the Role of Clinical Specialty Data in Medical LLMs
arXiv:2505.10113v3 Announce Type: replace Abstract: In this paper, we introduce S-MedQA, an English medical question-answering...
What do Speech Foundation Models Learn? Analysis and Applications
arXiv:2508.12255v1 Announce Type: new Abstract: Speech foundation models (SFMs) are designed to serve as general-purpose...
WebThinker: Empowering Large Reasoning Models with Deep Research Capability
arXiv:2504.21776v1 Announce Type: new Abstract: Large reasoning models (LRMs), such as OpenAI-o1 and DeepSeek-R1, demonstrate...
Weak-for-Strong (W4S): A Novel Reinforcement Learning Algorithm that Trains a weak Meta Agent to Design Agentic Workflows with Stronger LLMs
Researchers from Stanford, EPFL, and UNC introduce Weak-for-Strong Harnessing, W4S, a new Reinforcement Learning RL...
