Face-Feature Tuning is a label-free logit remapping method that reduces FPR/TPR gaps across groups in deepfake detection while preserving overall accuracy.
hub
Interactive language: Talking to robots in real time
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative citing papers
UniSim learns a universal real-world simulator from orchestrated diverse datasets, enabling zero-shot deployment of policies trained purely in simulation.
VoxPoser uses LLMs to compose 3D value maps via VLM interaction for model-based synthesis of robust robot trajectories on open-set language-specified manipulation tasks.
Chronos elevates full observation history to the policy's latent state via selective SSM tokens and a Schrödinger-inspired acceleration bridge, achieving large gains on memory-dependent robot tasks with fewer parameters.
This is the first survey on vision-language-action models, providing a taxonomy across three lines, plus summaries of datasets, simulators, benchmarks, challenges, and future directions in embodied AI.
A GPT-style model pre-trained on large video datasets achieves 94.9% success on CALVIN multi-task manipulation and 85.4% zero-shot generalization, outperforming prior baselines.
PaLM-E is a single 562B-parameter multimodal model that performs embodied reasoning tasks like robotic manipulation planning and visual question answering by interleaving vision, state, and text inputs with positive transfer from joint training on language and robotics data.
GROW decomposes trajectories into state-action samples to enable GRPO for multi-turn VLM agents and reports state-of-the-art results on more than 800 Minecraft tasks.
MimicGen creates over 50K robot demonstrations from roughly 200 human ones, allowing imitation learning to achieve strong performance on complex long-horizon tasks like assembly and coffee preparation.
No current AI systems exhibit the indicator properties derived from established scientific theories of consciousness, yet there appear to be no fundamental technical obstacles to implementing those properties in future systems.
The paper introduces World Action Models as a new paradigm unifying predictive world modeling with action generation in embodied foundation models and provides a taxonomy of existing approaches.
citing papers explorer
-
Learning Interactive Real-World Simulators
UniSim learns a universal real-world simulator from orchestrated diverse datasets, enabling zero-shot deployment of policies trained purely in simulation.
-
Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation
A GPT-style model pre-trained on large video datasets achieves 94.9% success on CALVIN multi-task manipulation and 85.4% zero-shot generalization, outperforming prior baselines.
-
PaLM-E: An Embodied Multimodal Language Model
PaLM-E is a single 562B-parameter multimodal model that performs embodied reasoning tasks like robotic manipulation planning and visual question answering by interleaving vision, state, and text inputs with positive transfer from joint training on language and robotics data.
-
Consciousness in Artificial Intelligence: Insights from the Science of Consciousness
No current AI systems exhibit the indicator properties derived from established scientific theories of consciousness, yet there appear to be no fundamental technical obstacles to implementing those properties in future systems.