Related papers: GRaSp: Automatic Example Optimization for In-Conte…

In real-world applications, data do not reflect the ones commonly used for neural networks training, since they are usually few, unlabeled and can be available as a stream. Hence many existing deep learning solutions suffer from a limited…

Improving Large Language Model (LLM) agents for sequential decision-making tasks typically requires extensive task-specific knowledge engineering--custom prompts, curated examples, and specialized observation/action spaces. We investigate a…

Recent studies show that, both explicit deep feature matching as well as large-scale and diverse training data can significantly improve the generalization of person re-identification. However, the efficiency of learning deep matchers on…

We consider a simulation optimization problem for a context-dependent decision-making. A Gaussian mixture model is proposed to capture the performance clustering phenomena of context-dependent designs. Under a Bayesian framework, we develop…

Neural models for amortized probabilistic clustering yield samples of cluster labels given a set-structured input, while avoiding lengthy Markov chain runs and the need for explicit data likelihoods. Existing methods which label each data…

Multi-label classification problems with thousands of classes are hard to solve with in-context learning alone, as language models (LMs) might lack prior knowledge about the precise classes or how to assign them, and it is generally…

World models simulate environment dynamics from raw sensory inputs like video. However, using them for planning can be challenging due to the vast and unstructured search space. We propose a robust and highly parallelizable planner that…

In-context learning can help Large Language Models (LLMs) to adapt new tasks without additional training. However, this performance heavily depends on the quality of the demonstrations, driving research into effective demonstration…

Large-scale pretrained language models have led to dramatic improvements in text generation. Impressive performance can be achieved by finetuning only on a small number of instances (few-shot setting). Nonetheless, almost all previous work…

Gradient-based meta-learning techniques aim to distill useful prior knowledge from a set of training tasks such that new tasks can be learned more efficiently with gradient descent. While these methods have achieved successes in various…

The remarkable advancements in large language models (LLMs) have significantly enhanced the performance in few-shot learning settings. By using only a small number of labeled examples, referred to as demonstrations, LLMs can effectively…

Training models to high-end performance requires availability of large labeled datasets, which are expensive to get. The goal of our work is to automatically synthesize labeled datasets that are relevant for a downstream task. We propose…

Large-scale models trained on broad data have recently become the mainstream architecture in computer vision due to their strong generalization performance. In this paper, the main focus is on an emergent ability in large vision models,…

Graph classification aims to extract accurate information from graph-structured data for classification and is becoming more and more important in graph learning community. Although Graph Neural Networks (GNNs) have been successfully…

Recent advances in flow matching models, particularly with reinforcement learning (RL), have significantly enhanced human preference alignment in few step text to image generators. However, existing RL based approaches for flow matching…

In this work, we present GraspFlow, a refinement approach for generating context-specific grasps. We formulate the problem of grasp synthesis as a sampling problem: we seek to sample from a context-conditioned probability distribution of…

In-context learning has recently been linked to implicit gradient descent in linear self-attention models, suggesting that context can induce a forward-pass update. Retrieval-augmented generation (RAG) also relies on context, but retrieved…

Meta learning methods have found success when applied to few shot classification problems, in which they quickly adapt to a small number of labeled examples. Prototypical representations, each representing a particular class, have been of…

In recent years, several frameworks and systems have been proposed that extend Inductive Logic Programming (ILP) to the Answer Set Programming (ASP) paradigm. In ILP, examples must all be explained by a hypothesis together with a given…

Continual learning (CL) in deep neural networks (DNNs) involves incrementally accumulating knowledge in a DNN from a growing data stream. A major challenge in CL is that non-stationary data streams cause catastrophic forgetting of…