Search Results for author:
Found 28 papers, 14 papers with code
MineStudio: A Streamlined Package for Minecraft AI Agent Development
Minecraft has emerged as a valuable testbed for embodied intelligence and sequential decision-making research, yet the development and validation of novel agents remains hindered by significant engineering challenges.
GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents
Developing agents that can follow multimodal instructions remains a fundamental challenge in robotics and AI.
ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting
Using this approach, we train ROCKET-1, a low-level policy that predicts actions based on concatenated visual observations and segmentation masks, supported by real-time object tracking from SAM-2.
Discrete Copula Diffusion
When we apply this approach to autoregressive copula models, the combined model outperforms both models individually in unconditional and conditional text generation.
OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents
First, we introduce a self-supervised approach to learn a behavior encoder that produces discretized tokens for behavior trajectories $\tau = \{o_0, a_0, \dots\}$ and an imitation learning policy decoder conditioned on these tokens.
Combining Supervised Learning and Reinforcement Learning for Multi-Label Classification Tasks with Partial Labels
Traditional supervised learning heavily relies on human-annotated datasets, especially in data-hungry neural approaches.
Document-level Relation Extraction
Multi-Label Classification
+3
Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planning
To address these issues, we propose Hierarchical Opponent modeling and Planning (HOP), a novel multi-agent decision-making algorithm that enables few-shot adaptation to unseen policies in mixed-motive environments.
Learning to Discretize Denoising Diffusion ODEs
We achieve FIDs of 2. 38 (10 NFE), and 2. 27 (10 NFE) on unconditional CIFAR10 and AFHQv2 in 5-10 minutes of training.
Smart Help: Strategic Opponent Modeling for Proactive and Adaptive Robot Assistance in Households
Our findings illustrate the potential of AI-imbued assistive robots in improving the well-being of vulnerable groups.
RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation
We explore how iterative revising a chain of thoughts with the help of information retrieval significantly improves large language models' reasoning and generation ability in long-horizon generation tasks, while hugely mitigating hallucination.
Image Inpainting via Tractable Steering of Diffusion Models
Further, with the help of an image encoder and decoder, our method can readily accept semantic constraints on specific regions of the image, which opens up the potential for more controlled image generation tasks.
JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models
Achieving human-like planning and control with multimodal observations in an open world is a key milestone for more functional generalist agents.
A Tractable Inference Perspective of Offline RL
A popular paradigm for offline Reinforcement Learning (RL) tasks is to first fit the offline trajectories to a sequence model, and then prompt the model for actions that lead to high expected return.
GROOT: Learning to Follow Instructions by Watching Gameplay Videos
We propose to follow reference videos as instructions, which offer expressive goal specifications while eliminating the need for expensive text-gameplay annotations.
ProAgent: Building Proactive Cooperative Agents with Large Language Models
Building agents with adaptive behavior in cooperative tasks stands as a paramount goal in the realm of multi-agent systems.
Understanding the Distillation Process from Deep Generative Models to Tractable Probabilistic Circuits
In this paper, we theoretically and empirically discover that the performance of a PC can exceed that of its teacher model.
Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents
We investigate the challenge of task planning for multi-task embodied agents in open-world environments.
Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction
We study the problem of learning goal-conditioned policies in Minecraft, a popular, widely accessible yet challenging open-ended environment for developing human-level multi-task agents.
Sparse Probabilistic Circuits via Pruning and Growing
The growing operation increases model capacity by increasing the size of the latent space.
Efficient Meta Reinforcement Learning for Preference-based Fast Adaptation
To bridge this gap, we study the problem of few-shot adaptation in the context of human-in-the-loop reinforcement learning.
Scaling Up Probabilistic Circuits by Latent Variable Distillation
We propose to overcome such bottleneck by latent variable distillation: we leverage the less tractable but more expressive deep generative models to provide extra supervision over the latent variables of PCs.
Lossless Compression with Probabilistic Circuits
To overcome such problems, we establish a new class of tractable lossless compression models that permit efficient encoding and decoding: Probabilistic Circuits (PCs).
Tractable Regularization of Probabilistic Circuits
Instead, we re-think regularization for PCs and propose two intuitive techniques, data softening and entropy regularization, that both take advantage of PCs' tractability and still have an efficient implementation as a computation graph.
A Compositional Atlas of Tractable Circuit Operations for Probabilistic Inference
Circuit representations are becoming the lingua franca to express and reason about tractable generative and discriminative models.
A Compositional Atlas of Tractable Circuit Operations: From Simple Transformations to Complex Information-Theoretic Queries
Circuit representations are becoming the lingua franca to express and reason about tractable generative and discriminative models.
On Effective Parallelization of Monte Carlo Tree Search
Second, and more importantly, we demonstrate how the proposed necessary conditions can be adopted to design more effective parallel MCTS algorithms.
Off-Policy Deep Reinforcement Learning with Analogous Disentangled Exploration
Off-policy reinforcement learning (RL) is concerned with learning a rewarding policy by executing another policy that gathers samples of experience.
Watch the Unobserved: A Simple Approach to Parallelizing Monte Carlo Tree Search
Monte Carlo Tree Search (MCTS) algorithms have achieved great success on many challenging benchmarks (e. g., Computer Go).
