From Requirements to Attack Trees: Grounded LLM Agents for Design-Time Security Review
Research
Research News
New papers, breakthroughs and academic AI research
Beware EviLLM: Enabling Vulnerability Injection via Large Language Models
Research
GOTT: Object-centric Dexterous Manipulation with a Reusable Cross-Embodiment Primitive
Research
ROT: Rotating Hidden States towards Contextual Vectors for Hallucination Mitigation in LVLMs
Research
JLD: Perceptual Distance Through A Jacobian Lens
Research
ProsaBuddy: Assisting Mechanized Real-Time Schedulability Analysis with LLM-based Agents
Research
Distribution Matching Evolutionary Algorithms for Rare Event Sampling
Research
An Executable Benchmark for LLM-Based HLS Repair:Design Complexity and Repair Underconstraint
Research
ReMem: Streaming Video Understanding With Long Context Retention
Research
Learning without Overwriting: A Theory of Self-Distillation and Supervised Fine-Tuning in Continual Reasoning
Research
SALUS: Automated Auditing of NL-to-SQL Benchmarks through Weak Supervision of Multi-Agent Output
Research
Loopy: Low-Bit Quantization Framework for Looped Language Models
Research