Related papers: The BinProlog Experience: Architecture and Impleme…

Designing mechanical linkages involves combinatorial topology selection and continuous parameter fitting. We show that language models can systematically improve linkage designs through symbolic representations. Language model agents…

Computing-in-Memory architectures based on non-volatile emerging memories have demonstrated great potential for deep neural network (DNN) acceleration thanks to their high energy efficiency. However, these emerging devices can suffer from…

Memory pressure has emerged as a dominant constraint in scaling the training of large language models (LLMs), particularly in resource-constrained environments. While modern frameworks incorporate various memory-saving techniques, they…

We present a new approach to termination analysis of numerical computations in logic programs. Traditional approaches fail to analyse them due to non well-foundedness of the integers. We present a technique that allows overcoming these…

Digital computing-in-memory (DCIM) has emerged as a promising solution for large language model (LLM) acceleration by minimizing data transfers between external DRAM and on-chip accelerators while maintaining high precision for superior…

Processing-In-Memory (PIM) is a novel approach that augments existing DRAM memory chips with lightweight logic. By allowing to offload computations to the PIM system, this architecture allows for circumventing the data-bottleneck problem…

Robotic imitation learning typically requires models that capture multimodal action distributions while operating at real-time control rates and accommodating multiple sensing modalities. Although recent generative approaches such as…

We introduce WAM-Flow, a vision-language-action (VLA) model that casts ego-trajectory planning as discrete flow matching over a structured token space. In contrast to autoregressive decoders, WAM-Flow performs fully parallel, bidirectional…

Making large language models (LLMs) more efficient in memory, latency, and serving cost is crucial for edge deployment, interactive applications, and sustainable inference at scale. Pruning is a promising technique, but existing pruning…

We introduce BigBang-Proton, a unified sequence-based architecture for auto-regressive language modeling pretrained on cross-scale, cross-structure, cross-discipline real-world scientific tasks to construct a scientific multi-task learner.…

This paper describes an analytical modeling tool called Bitlet that can be used, in a parameterized fashion, to understand the affinity of workloads to processing-in-memory (PIM) as opposed to traditional computing. The tool uncovers…

The speed of modern digital systems is severely limited by memory latency (the ``Memory Wall'' problem). Data exchange between Logic and Memory is also responsible for a large part of the system energy consumption. Logic--In--Memory (LiM)…

In this paper, we aim to address issues of (1) joint spatial-temporal modeling and (2) side information injection for deep-learning based in-loop filter. For (1), we design a deep network with both progressive rethinking and collaborative…

ProbLog is a popular probabilistic logic programming language/tool, widely used for applications requiring to deal with inherent uncertainties in structured domains. In this paper we study connections between ProbLog and a variant of…

The Teyjus system realizes the higher-order logic programming language$\lambda$Prolog by compiling programs into bytecode for an abstract machine and executing this translated form using a simulator for the machine. Teyjus supports a number…

Language models are increasingly used to reason over content they were not trained on, such as new documents, evolving knowledge, and user-specific data. A common approach is retrieval-augmented generation (RAG), which stores verbatim…

We introduce Llamba, a family of efficient recurrent language models distilled from Llama-3.x into the Mamba architecture. The series includes Llamba-1B, Llamba-3B, and Llamba-8B, which achieve higher inference throughput and handle…

In the rapidly evolving field of business process management, there is a growing need for analytical tools that can transform complex data into actionable insights. This research introduces a novel approach by integrating Large Language…

Advancing machine intelligence requires developing the ability to perceive across multiple modalities, much as humans sense the world. We introduce OmniVinci, an initiative to build a strong, open-source, omni-modal LLM. We carefully study…

Agentic workflows interleave configurable LLM stages with tool stages and often include retries or refinement loops. Existing workflow managers profile full workflow configurations offline and assign each request a static workflow-level…