Related papers: Efficient Many-Shot In-Context Learning with Dynam…

One-shot imitation is to learn a new task from a single demonstration, yet it is a challenging problem to adopt it for complex tasks with the high domain diversity inherent in a non-stationary environment. To tackle the problem, we explore…

Diffusion Probabilistic Models (DPMs) have achieved great success in image generation but suffer from high inference latency due to their iterative denoising nature. Motivated by the evolving feature dynamics across the denoising…

Large language models adapt to new tasks through in-context learning (ICL) without parameter updates. Current theoretical explanations for this capability assume test tasks are drawn from a distribution similar to that seen during…

Current hierarchical attention methods, such as NSA and InfLLMv2, select the top-k relevant key-value (KV) blocks based on coarse attention scores and subsequently apply fine-grained softmax attention on the selected tokens. However, the…

Attention guidance is an approach to addressing dataset bias in deep learning, where the model relies on incorrect features to make decisions. Focusing on image classification tasks, we propose an efficient human-in-the-loop system to…

Long-context supervised fine-tuning (Long-SFT) plays a vital role in enhancing the performance of large language models (LLMs) on long-context tasks. To smoothly adapt LLMs to long-context scenarios, this process typically entails training…

Supervised fine-tuning (SFT), supervised instruction tuning (SIT) and in-context learning (ICL) are three alternative, de facto standard approaches to few-shot learning. ICL has gained popularity recently with the advent of LLMs due to its…

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…

In multiple instance multiple label learning, each sample, a bag, consists of multiple instances. To alleviate labeling complexity, each sample is associated with a set of bag-level labels leaving instances within the bag unlabeled. This…

The ability to train complex and highly effective models often requires an abundance of training data, which can easily become a bottleneck in cost, time, and computational resources. Batch active learning, which adaptively issues batched…

In-Context Learning (ICL) allows Large Language Models (LLMs) to adapt to new tasks with just a few examples, but their predictions often suffer from systematic biases, leading to unstable performance in classification. While calibration…

We study the phenomenon of \textit{in-context learning} (ICL) exhibited by large language models, where they can adapt to a new learning task, given a handful of labeled examples, without any explicit parameter optimization. Our goal is to…

Multitask learning is a common approach in machine learning, which allows to train multiple objectives with a shared architecture. It has been shown that by training multiple tasks together inference time and compute resources can be saved,…

Large language models (LLMs) possess broad world knowledge and strong general-purpose reasoning ability, yet they struggle to learn from many in-context examples on standard machine learning (ML) tasks, that is, to leverage many-shot…

Recent advances in large language and vision-language models have enabled zero-shot inference, allowing models to solve new tasks without task-specific training. Various adaptation techniques such as prompt engineering, In-Context Learning…

Transformer-based large language models have displayed impressive in-context learning capabilities, where a pre-trained model can handle new tasks without fine-tuning by simply augmenting the query with some input-output examples from that…

In-Context Learning (ICL) has gained prominence due to its ability to perform tasks without requiring extensive training data and its robustness to noisy labels. A typical ICL workflow involves selecting localized examples relevant to a…

Diffusion large language models (dLLMs) have emerged as a promising alternative for text generation, distinguished by their native support for parallel decoding. In practice, block inference is crucial for avoiding order misalignment in…

Multi-scale inference is commonly used to improve the results of semantic segmentation. Multiple images scales are passed through a network and then the results are combined with averaging or max pooling. In this work, we present an…

The increasing demand for long-context modeling in large language models (LLMs) is bottlenecked by the quadratic complexity of the standard self-attention mechanism. The community has proposed sparse attention to mitigate this issue.…