arXiv
Corrupt Plans, Clean Traces: Evading Chain-of-Thought Monitoring with Plan Injection
Chain-of-thought (CoT) monitoring is a safety strategy where the reasoning of a large language model "actor" is inspe...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Discovery Foundation Models: Toward Open-Ended Discovery Intelligence
Foundation models have progressed from learning and reasoning over existing knowledge, to increasingly learning throu...
HuggingFace
Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation
We present Vidu S2, which comprises Vidu S2-Avatar, a real-time interactive digital-character model, and Vidu S2-Edit...
HuggingFace
Not All Prompts Are Equal: Exploration-Guided Prompt Scaffolding for Multimodal Reinforcement Post-Training
Training prompts in online reinforcement learning (RL) differ substantially in how informative they are for the curre...
HuggingFace
PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models
We present PhysBrain 1.5, a unified model for understanding physical environments, generating actions, and predicting...
HuggingFace
ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search
In this work, we present ZGCM-1, a fully open 7B dense foundation model trained from scratch with extreme data, syste...
HuggingFace
Kaininja: Extending Native 3D Generators to the Part Level
Native 3D generators turn one image into a single mesh. TRELLIS.2 and its peers deliver high-fidelity non-watertight ...
HuggingFace
Atria Dawn: The Dawn of Agentic Superintelligence
As AI agents become participants in the development of their successors, they reshape both the production of intellig...
HuggingFace
When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis
Large language model (LLM) agents allocate test-time compute adaptively as they revise solutions, use tools, explore ...
HuggingFace
Enabling Creative Exploration for Vibe Design Agents
Vibe design agents turn natural-language briefs into rendered interfaces and frontend code. Yet a useful design agent...
HuggingFace
Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks
Backdoor poisoning attacks add poisoned examples to otherwise-clean finetuning data, pairing a trigger with a target ...
HuggingFace
Agent as Policy for Robotic Manipulation
We demonstrate that a general-purpose agent can directly drive a physical robot throughout task execution without any...