DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search Paper โข 2509.25454 โข Published Sep 29 โข 136
WideSearch: Benchmarking Agentic Broad Info-Seeking Paper โข 2508.07999 โข Published Aug 11 โข 109
Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks Paper โข 2504.01308 โข Published Apr 2 โข 14
Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks Paper โข 2504.01308 โข Published Apr 2 โข 14