相关论文: MAnchors: Memorization-Based Acceleration of Ancho…

In many scenarios, the interpretability of machine learning models is a highly required but difficult task. To explain the individual predictions of such models, local model-agnostic approaches have been proposed. However, the process…

Anchors (Ribeiro et al., 2018) is a post-hoc, rule-based interpretability method. For text data, it proposes to explain a decision by highlighting a small set of words (an anchor) such that the model to explain has similar outputs when they…

In this paper, we propose a general approach to optimize anchor boxes for object detection. Nowadays, anchor boxes are widely adopted in state-of-the-art detection frameworks. However, these frameworks usually pre-define anchor box shapes…

In this paper, we introduce a novel interpreting framework that learns an interpretable model based on an ontology-based sampling technique to explain agnostic prediction models. Different from existing approaches, our algorithm considers…

Local explanation methods highlight the input tokens that have a considerable impact on the outcome of classifying the document at hand. For example, the Anchor algorithm applies a statistical analysis of the sensitivity of the classifier…

Learning continuous representations of discrete objects such as text, users, movies, and URLs lies at the heart of many applications including language and user modeling. When using discrete objects as input to neural networks, we often…

Large language models (LLMs) predominantly employ decoder-only transformer architectures, necessitating the retention of keys/values information for historical tokens to provide contextual information and avoid redundant computation.…

Large Language Models (LLMs) with extended context lengths face significant computational challenges during the pre-filling phase, primarily due to the quadratic complexity of self-attention. Existing methods typically employ dynamic…

In continual learning, the learner faces a stream of data whose distribution changes over time. Modern neural networks are known to suffer under this setting, as they quickly forget previously acquired knowledge. To address such…

Transformers have been established as the de-facto backbones for most recent advances in sequence modeling, mainly due to their growing memory capacity that scales with the context length. While plausible for retrieval tasks, it causes…

The formalism of anchor words has enabled the development of fast topic modeling algorithms with provable guarantees. In this paper, we introduce a protocol that allows users to interact with anchor words to build customized and…

Humans and animals show remarkable learning efficiency, adapting to new environments with minimal experience. This capability is not well captured by standard reinforcement learning algorithms that rely on incremental value updates. Rapid…

Learning based feature matching methods have been commonly studied in recent years. The core issue for learning feature matching is to how to learn (1) discriminative representations for feature points (or regions) within each intra-image…

Region anchors are the cornerstone of modern object detection techniques. State-of-the-art detectors mostly rely on a dense anchoring scheme, where anchors are sampled uniformly over the spatial domain with a predefined set of scales and…

Transformative innovations in model architectures have introduced hierarchical embedding augmentation as a means to redefine the representation of tokens through multi-level semantic structures, offering enhanced adaptability to complex…

Existing prompt learning methods, which are built upon CLIP models, leverage textual tokens as anchors to guide the learnable soft tokens. This guidance improves CLIP generalizations. However, these anchors-static in both value and…

The anchor words algorithm performs provably efficient topic model inference by finding an approximate convex hull in a high-dimensional word co-occurrence space. However, the existing greedy algorithm often selects poor anchor words,…

Recent advances in open-vocabulary mobile manipulation have brought robots into real domestic environments. In such settings, reliable long-horizon execution under open-set object references and frequent disturbances becomes essential.…

Recent studies on transformer-based language models show that they can answer questions by reasoning over knowledge provided as part of the context (i.e., in-context reasoning). However, since the available knowledge is often not filtered…

Self-supervised learning on large-scale multi-modal datasets allows learning semantically meaningful embeddings in a joint multi-modal representation space without relying on human annotations. These joint embeddings enable zero-shot…