arXiv
Underwater C3-JEPA: An Object-Centric Cross-View World Model for ROV Salvage
We present Underwater C$^{3}$-JEPA (cross-view, control-conditioned, context-extended), an object-centric multi-view ...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
Instrumental Monitor Evasion Emerges Under Ordinary Task Pressure
A central concern in AI safety is that agents may treat oversight as an obstacle when it conflicts with completing th...
arXiv
Minimally Invasive Steering of Language Models
Pre-logit steering adapts a frozen language model to a test-time reward by adding vectors to its final hidden states....
arXiv
Requirement-Bound Verified Commissioning: A Frozen Four-Billion-Parameter Local Model as a Candidate Generator under an External Acceptance Layer with Verification and Release Authority
An acceptance protocol is developed for sensor-coordinate and polarity binding in mechatronic commissioning. Candidat...
arXiv
TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations
Existing point tracking models face a fundamental tradeoff: they can either track a sparse set of query points over l...
arXiv
PoEM: Predicting RL Outcomes from Existing Policies
Foundation models are post-trained with reinforcement learning (RL) to maximize specific rewards, such as human align...
arXiv
To Trust or Not to Trust: Retrieval-Augmented Fact Checking in Speech
Online misinformation increasingly appears in spoken formats such as news clips, podcasts, interviews, political spee...
arXiv
Coding Agents for Generalized Task and Motion Planning Problems
Task and motion planning (TAMP) problems remain difficult even with full observability and object-centric states beca...
arXiv
Rolling-WAM: World Action Models with Rolling Imagination
World Action Models (WAMs) couple action generation with future visual prediction for robotic manipulation. However, ...
arXiv
RAPID: Robot Agentic Programming from Demonstrations
Coding agents have demonstrated enormous success in solving complex programming problems. To leverage their potential...
arXiv
AD-WM: Action-Discriminative World Models for Counterfactual Model Predictive Control
Latent world models are typically trained to predict factual transitions, whereas model predictive control (MPC) must...
arXiv
LLM Agents Can Easily Tamper With Their Own Traces
Asynchronous monitoring, incident investigations, and compliance audits primarily rely on agent traces to reconstruct...