Related papers: Does Engram Do Memory Retrieval in Autoregressive …

The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically…

We propose a novel AutoRegressive Generation-based paradigm for image Segmentation (ARGenSeg), achieving multimodal understanding and pixel-level perception within a unified framework. Prior works integrating image segmentation into…

Large token-indexed lookup tables provide a compute-decoupled scaling path, but their practical gains are often limited by poor parameter efficiency and rapid memory growth. We attribute these limitations to Zipfian under-training of the…

Autoregressive (AR) models have demonstrated significant success in the realm of text-to-image generation. However, they usually face two major challenges. Firstly, the generated images may not always meet the quality standards expected by…

While GAN is a powerful model for generating images, its inability to infer a latent space directly limits its use in applications requiring an encoder. Our paper presents a simple architectural setup that combines the generative…

Multi-step retrieval-augmented generation (RAG) has become a widely adopted strategy for enhancing large language models (LLMs) on tasks that demand global comprehension and intensive reasoning. Although many RAG systems incorporate a…

We design an Enriched Deep Recurrent Visual Attention Model (EDRAM) - an improved attention-based architecture for multiple object recognition. The proposed model is a fully differentiable unit that can be optimized end-to-end by using…

The ability to form, retrieve, and reason about memories in response to stimuli serves as the cornerstone for general intelligence - shaping entities capable of learning, adaptation, and intuitive insight. Large Language Models (LLMs) have…

Large reasoning models (LRMs) achieve strong accuracy through test-time scaling, generating longer chains of thought or sampling multiple solutions, but at steep costs in tokens and latency. We argue that memory is a core ingredient for…

Zero-shot entity retrieval, aiming to link mentions to candidate entities under the zero-shot setting, is vital for many tasks in Natural Language Processing. Most existing methods represent mentions/entities via the sentence embeddings of…

Embodied control increasingly requires models to follow compositional language instructions while reasoning over dynamic visual states. However, current vision-language-action policies and world-action models often couple linguistic…

The two main impediments to continual learning are catastrophic forgetting and memory limitations on the storage of data. To cope with these challenges, we propose a novel, cognitively-inspired approach which trains autoencoders with Neural…

Modern large language models (LLMs) excel at tasks that require storing and retrieving knowledge, such as factual recall and question answering. Transformers are central to this capability because they can encode information during training…

We introduce \emph{Adaptive RAG Memory} (ARM), a retrieval-augmented generation (RAG) framework that replaces a static vector index with a \emph{dynamic} memory substrate governed by selective remembrance and decay. Frequently retrieved…

Autoregressive (AR) visual generation has achieved remarkable performance but suffers from high memory usage and low throughput, as it requires caching previously generated visual tokens. Recent research has shown that retaining only a few…

To overcome the poor scalability of convolutional neural network, recurrent attention model(RAM) selectively choose what and where to look on the image. By directing recurrent attention model how to look the image, RAM can be even more…

Despite substantial research into the biological basis of memory, the precise mechanisms by which experiences are encoded, stored, and retrieved in the brain remain incompletely understood. A growing body of evidence supports the engram…

This study presents a novel model for invertible sentence embeddings using a residual recurrent network trained on an unsupervised encoding task. Rather than the probabilistic outputs common to neural machine translation models, our…

Biological neural networks are capable of recruiting different sets of neurons to encode different memories. However, when training artificial neural networks on a set of tasks, typically, no mechanism is employed for selectively producing…

Large Language Models (LLMs) exhibit remarkable capabilities but suffer from apparent precision loss, reframed here as information spreading. This reframing shifts the problem from computational precision to an information-theoretic…