74 citations · 153 across the 40 of their papers we have counts for
42 papers
LoOPSD: On-Policy Self-Distillation with Looped Teachers
Wei Fan, Qingyue Yang, Chao-Hong Tan +6
On-policy self-distillation improves a model using guidance from the model itself, but it still requires a teacher that provides more useful predictions than the student. Existing…
Breadcrumbing Search Agents
Xuebin Li, Hanqing Zhao, Siyuan Liang +4
LLM-based search agents are widely used for information-seeking tasks, but their reliance on external tool returns introduces a critical security risk: web content retrieved during…
Beyond the Text: Verifying That Agent-Written Papers Are Backed by Their Artifacts
Qiuhong Shen, Benlong Wu, Hanjin Liu +2
Large language model agents are increasingly capable of conducting research autonomously, producing research documents alongside the code and experiments that ostensibly support th…
Between Safe Boundaries: Exploiting Temporal Consistency for Jailbreaking Text-To-Video Generation Models
Xingkai Peng, Jun Jiang, Jiayang Liu +2
Recently, text-to-video (T2V) models have been widely deployed, sparking growing concerns over their robustness against jailbreak attacks. Existing jailbreak methods, mostly adapte…
Cosmos 3: Omnimodal World Models for Physical AI
NVIDIA, :, Aditi +293
We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-t…
Provably Secure Agent Guardrail
Benlong Wu, Weiming Zhang, Kejiang Chen +2
As large language models transition from bounded generative engines to agents with expansive execution privileges, AI going out of control precipitates a fundamental crisis in arti…