Related papers: NGM: A Plug-and-Play Training-Free Memory Module f…
Neural Module Networks (NMN) are a compelling method for visual question answering, enabling the translation of a question into a program consisting of a series of reasoning sub-tasks that are sequentially executed on the image to produce…
This paper presents a novel neural network training approach for faster convergence and better generalization abilities in deep reinforcement learning. Particularly, we focus on the enhancement of training and evaluation performance in…
Kernel conditional mean embeddings (CMEs) offer a powerful framework for representing conditional distribution, but they often face scalability and expressiveness challenges. In this work, we propose a new method that effectively combines…
As transistor-based memory technologies like dynamic random access memory (DRAM) approach their scalability limits, the need to explore alternative storage solutions becomes increasingly urgent. Phase-change memory (PCM) has gained…
The global scarcity of GPUs necessitates more sophisticated strategies for Deep Learning jobs in shared cluster environments. Accurate estimation of how much GPU memory a job will require is fundamental to enabling advanced scheduling and…
Repeated off-chip memory accesses to DRAM drive up operating power for data-intensive applications, and SRAM technology scaling and leakage power limits the efficiency of embedded memories. Future on-chip storage will need higher density…
Non-Volatile Memory offers the possibility of implementing high-performance, durable data structures. However, achieving performance comparable to well-designed data structures in non-persistent (transient) memory is difficult, primarily…
Neural Module Network (NMN) exhibits strong interpretability and compositionality thanks to its handcrafted neural modules with explicit multi-hop reasoning capability. However, most NMNs suffer from two critical drawbacks: 1) scalability:…
We present a framework of Training Free Graph Matching (TFGM) to boost the performance of Graph Neural Networks (GNNs) based graph matching, providing a fast promising solution without training (training-free). TFGM provides four widely…
Persistent Memory (PMEM), also known as Non-Volatile Memory (NVM), can deliver higher density and lower cost per bit when compared with DRAM. Its main drawback is that it is typically slower than DRAM. On the other hand, DRAM has…
Large language models (LLMs) have demonstrated exceptional performance across a variety of tasks. However, their substantial scale leads to significant computational resource consumption during inference, resulting in high costs.…
Clinical decision-making agents can benefit from reusing prior decision experience. However, many memory-augmented methods store experiences as independent records without explicit relational structure, which may introduce noisy retrieval,…
The rapid advancement of deep neural networks has significantly improved various tasks, such as image and speech recognition. However, as the complexity of these models increases, so does the computational cost and the number of parameters,…
Memory, additional information beyond the training of large language models (LLMs), is crucial to various real-world applications, such as personal assistant. The two mainstream solutions to incorporate memory into the generation process…
Large reasoning models (LRMs) excel on complex problems but face a critical barrier to efficiency: reinforcement learning (RL) training requires long rollouts for outcome-based rewards, where autoregressive decoding dominates time and…
We introduce Lossless Context Management (LCM), a deterministic architecture for LLM memory that outperforms Claude Code on long-context tasks. When benchmarked using Opus 4.6, our LCM-augmented coding agent, Volt, achieves higher scores…
Modern language agents must operate over long-horizon, multi-turn interactions, where they retrieve external information, adapt to observations, and answer interdependent queries. Yet, most LLM systems rely on full-context prompting,…
Contextually Entangled Gradient Mapping (CEGM) introduces a new approach to gradient optimization, redefining the relationship between contextual embeddings and gradient updates to enhance semantic coherence and reasoning capabilities in…
Generative Reward Models (GRMs) provide greater flexibility than scalar reward models in capturing human preferences, but their effectiveness is limited by poor reasoning capabilities. This often results in incomplete or overly speculative…
This paper introduces the Modular Neural Computer (MNC), a memory-augmented neural architecture for exact algorithmic computation on variable-length inputs. The model combines an external associative memory of scalar cells, explicit read…