WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory
We present WorldDirector, a highly controllable video world model framework designed for persistent dynamic object memory and unrestricted viewpoint exploration.
Distributed Attacks in Persistent-State AI Control
As AI coding agents become more autonomous, they increasingly ship code iteratively, with the codebase persisting across sessions.
LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning
LLMs memorize sensitive training data, including personally identifiable information (PII), creating a pressing need for reliable post hoc removal methods.
Online Safety Monitoring for LLMs
Despite alignment training, LLMs remain prone to generating unsafe outputs at deployment time.
ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
Understanding and reasoning over long contexts has become a key requirement for deploying large language models (LLMs) in realistic applications.
What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates
LLM agents will increasingly act in socially structured settings where role, audience, and relational context can shape what is advantageous or costly to say.
Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas
Long-form TV dramas present a formidable challenge for comprehensive video understanding, where deciphering complex storyline relies on speaker recognition.
DemoPSD: Disagreement-Modulated Policy Self-Distillation
On-policy self-distillation (OPSD) has emerged as a practical method for training large language models (LLMs) to reason.
Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots
Embodied AI models now span vision-language-action (VLA) models and world-action models (WAMs), but practical deployment remains fragmented.
Beyond Adam: SOAP and Muon for Faster, Label-Efficient Training of Machine Learning Interatomic Potentials
Machine learning interatomic potentials (MLIPs) have become a hallmark of AI for scientific simulation.