3 papers
cs.AI2026
Shape of Thought: When Distribution Matters More than Correctness in Reasoning Tasks
Abhranil Chandra, Ayush Agrawal, Arian Hosseini +4
We present the surprising finding that a language model's reasoning capabilities can be improved by training on synthetic datasets of chain-of-thought (CoT) traces from more capabl…
cs.CR2025
STAF: Leveraging LLMs for Automated Attack Tree-Based Security Test Generation
Tanmay Khule, Stefan Marksteiner, Jose Alguindigue +3
In modern automotive development, security testing is critical for safeguarding systems against increasingly advanced threats. Attack trees are widely used to systematically repres…
cs.AI2024
VideoAgent: Self-Improving Video Generation
Achint Soni, Sreyas Venkataraman, Abhranil Chandra +4
Video generation has been used to generate visual plans for controlling robotic systems. Given an image observation and a language instruction, previous work has generated video pl…