9 papers
CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild
Jian Yang, Haau-Sing Li, Shawn Guo +10
As large language models (LLMs) continue to advance in coding capabilities, their potential in cybersecurity has drawn increasing research attention, with closed-source LLMs (e.g.,…
WebWorld: The Browser as a World Model for Self-Improving Web Code
Jiajun Wu, Jian Yang, Yaxin Du +7
VLM-driven self-improvement of web code has a structural flaw: the model that proposes the repair is the model that judges it, and visual plausibility under that judge is a poor pr…
MIRA: Mid-training Rubric Anchoring for Source-Aware Data Selection
Haowen Wang, Yaxin Du, Jian Yang +9
Mid-training has become an important stage in modern LLM development, using large-scale curated mixtures to strengthen capabilities before final post-training. Its data selection p…
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
Dongrui Liu, Yu Li, Zhonghao Yang +47
Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI mod…
HTMLCure: Turning Browser Experience into State Guided Repair for Interactive HTML
Jiajun Wu, Jian Yang, Tuney Zheng +4
LLMs can now produce full HTML pages, but many of those pages are only superficially correct: they render once, then fail under scroll, hover, click, resize, or gameplay. Evaluatio…
SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillation
Zhuguanyu Wu, Ruihao Gong, Yang Yong +5
Distribution Matching Distillation (DMD) is a widely used paradigm for accelerating inference in few-step video diffusion models. However, DMD-style video distillation faces two co…
Weak-Driven Learning: How Weak Agents make Strong Agents Stronger
Zehao Chen, Gongxun Li, Tianxiang Ai +9
As post-training optimization becomes central to improving large language models, we observe a persistent saturation bottleneck: once models grow highly confident, further training…
CodeChemist: Test-Time Scaling for Low-Resource Code Generation via Functional Knowledge Transfer
Kaixin Wang, Tianlin Li, Xiaoyu Zhang +6
Code Large Language Models (CodeLLMs) have been widely adopted for Natural Language to Programming Language code generation, powering applications with large user bases. Their perf…
RobustVLA: On Robustness of Vision-Language-Action Model against Multi-Modal Perturbations
Jianing Guo, Zhenhong Wu, Chang Tu +13
In Vision-Language-Actionf(VLA) models, robustness to real-world perturbations is critical for deployment. Existing methods target simple visual disturbances, overlooking the broad…