An attention-guided RL reward combined with diverse persuasion strategies produces higher attack success rates against large reasoning models than prior jailbreak methods.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
Fully aligned instructional videos for physical tasks yield 11.1% better completion quality and 15.5% faster times, with four decomposable visual attributes whose isolated misalignments degrade performance without users noticing.
Kumushi improves automated vulnerability repair by focusing LLM edits on root causes via dynamic localization and ranking, yielding more genuine fixes than prior agents on 178 C/C++ vulnerabilities.
ComPASS creates tool-augmented LLM agents for substantive social support, releases the first personalized benchmark ComPASS-Bench, and fine-tunes ComPASS-Qwen to outperform its base model while matching larger LLMs.
citing papers explorer
-
Attention-Guided Reward for Reinforcement Learning-based Jailbreak against Large Reasoning Models
An attention-guided RL reward combined with diverse persuasion strategies produces higher attack success rates against large reasoning models than prior jailbreak methods.
-
Substantial, Decomposable, and Invisible: Visual Context Misalignment in Instructional Videos for Physical Tasks
Fully aligned instructional videos for physical tasks yield 11.1% better completion quality and 15.5% faster times, with four decomposable visual attributes whose isolated misalignments degrade performance without users noticing.
-
Root-Cause-Driven Automated Vulnerability Repair
Kumushi improves automated vulnerability repair by focusing LLM edits on root causes via dynamic localization and ranking, yielding more genuine fixes than prior agents on 178 C/C++ vulnerabilities.
-
ComPASS: Towards Personalized Agentic Social Support via Tool-Augmented Companionship
ComPASS creates tool-augmented LLM agents for substantive social support, releases the first personalized benchmark ComPASS-Bench, and fine-tunes ComPASS-Qwen to outperform its base model while matching larger LLMs.