Charles Packer
YOU?
Author Swipe
View article: Sleep-time Compute: Beyond Inference Scaling at Test-time
Sleep-time Compute: Beyond Inference Scaling at Test-time Open
Scaling test-time compute has emerged as a key ingredient for enabling large language models (LLMs) to solve difficult problems, but comes with high latency and inference cost. We introduce sleep-time compute, which allows models to "think…
View article: CARFF: Conditional Auto-encoded Radiance Field for 3D Scene Forecasting
CARFF: Conditional Auto-encoded Radiance Field for 3D Scene Forecasting Open
We propose CARFF, a method for predicting future 3D scenes given past observations. Our method maps 2D ego-centric images to a distribution over plausible 3D latent scene configurations and predicts the evolution of hypothesized scenes thr…
View article: MemGPT: Towards LLMs as Operating Systems
MemGPT: Towards LLMs as Operating Systems Open
Large language models (LLMs) have revolutionized AI, but are constrained by limited context windows, hindering their utility in tasks like extended conversations and document analysis. To enable using context beyond limited context windows…
View article: Hindsight Task Relabelling: Experience Replay for Sparse Reward Meta-RL
Hindsight Task Relabelling: Experience Replay for Sparse Reward Meta-RL Open
Meta-reinforcement learning (meta-RL) has proven to be a successful framework for leveraging experience from prior tasks to rapidly learn new related tasks, however, current meta-RL approaches struggle to learn in sparse reward environment…
View article: Contingencies from Observations: Tractable Contingency Planning with Learned Behavior Models
Contingencies from Observations: Tractable Contingency Planning with Learned Behavior Models Open
Humans have a remarkable ability to make decisions by accurately reasoning about future events, including the future behaviors and states of mind of other agents. Consider driving a car through a busy intersection: it is necessary to reaso…
View article: Contingencies from Observations: Tractable Contingency Planning with\n Learned Behavior Models
Contingencies from Observations: Tractable Contingency Planning with\n Learned Behavior Models Open
Humans have a remarkable ability to make decisions by accurately reasoning\nabout future events, including the future behaviors and states of mind of other\nagents. Consider driving a car through a busy intersection: it is necessary to\nre…
View article: Assessing Generalization in Deep Reinforcement Learning
Assessing Generalization in Deep Reinforcement Learning Open
Deep reinforcement learning (RL) has achieved breakthrough results on many tasks, but agents often fail to generalize beyond the environment they were trained in. As a result, deep RL algorithms that promote generalization are receiving in…
View article: Visually-Aware Personalized Recommendation using Interpretable Image Representations
Visually-Aware Personalized Recommendation using Interpretable Image Representations Open
Visually-aware recommender systems use visual signals present in the underlying data to model the visual characteristics of items and users' preferences towards them. In the domain of clothing recommendation, incorporating items' visual in…
View article: GraphZip: Dictionary-based Compression for Mining Graph Streams
GraphZip: Dictionary-based Compression for Mining Graph Streams Open
A massive amount of data generated today on platforms such as social networks, telecommunication networks, and the internet in general can be represented as graph streams. Activity in a network's underlying graph generates a sequence of ed…
View article: Monomer: Non-Metric Mixtures-of-Embeddings for Learning Visual Compatibility Across Categories.
Monomer: Non-Metric Mixtures-of-Embeddings for Learning Visual Compatibility Across Categories. Open
Identifying relationships between items is a key task of an online recommender system, in order to help users discover items that are functionally complementary or visually compatible. In domains like clothing recommendation, this task is …
View article: Learning Compatibility Across Categories for Heterogeneous Item Recommendation
Learning Compatibility Across Categories for Heterogeneous Item Recommendation Open
Identifying relationships between items is a key task of an online recommender system, in order to help users discover items that are functionally complementary or visually compatible. In domains like clothing recommendation, this task is …