arXiv
What Do Safety-Aligned LLMs Learn From Mixed Compliance Demonstrations?
Prior work has shown that in-context demonstrations can jailbreak language models, but it remains unclear how models ...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
Efficient and Sound Probabilistic Verification for AI Agents
Securing AI agents that operate in complex digital environments has become a critical need, and runtime monitoring ap...
arXiv
Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages
LiveCodeBench (LCB) has recently become a widely adopted benchmark for evaluating large language models (LLMs) on cod...
arXiv
FlowEdit: Associative Memory for Lifelong Pronunciation Adaptation in Flow-Matching TTS
Flow-matching text-to-speech systems achieve remarkable zero-shot quality but remain static after deployment: pronunc...
arXiv
Sovereign Execution Brokers: Enforcing Certificate-Bound Authority in Agentic Control Planes
Autonomous agents are increasingly connected to cloud, deployment, and data-control workflows, but production mutatio...
arXiv
SARLO-80: Worldwide Slant SAR Language Optic Dataset 80cm
Multimodal foundation models have advanced rapidly thanks to large optical benchmarks, but comparable resources for s...
arXiv
DeepSWIP: Quotient-WMC Counterfactuals for Neural Probabilistic Logic Programs
Neurosymbolic systems such as DeepProbLog combine neural perception with probabilistic logic, but standard inference ...
arXiv
LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents
Policy-adherent tool-calling agents in customer-service domains must maintain task states across turns while calling ...
arXiv
How Do Instructions Shape Speech? Cross-Attention Attribution for Style-Captioned Text-to-Speech
Style-captioned text-to-speech systems use natural language to control voice characteristics, but how individual word...
arXiv
Toward Calibrated Mixture-of-Experts Under Distribution Shift
Calibration aligns a model's predictive uncertainty with the frequencies of its empirical outcomes and is important f...
arXiv
Structuring and Tokenizing Distributed User Interest Context for Generative Recommendation
Generative recommendation is an emerging paradigm that has shown promise in industrial recommendation systems, aiming...
arXiv
How Transparent is DiffusionGemma?
LLM reasoning transparency is a critical affordance for understanding model decisions, mitigating misuse and misalign...