Related papers: TransForm: Formally Specifying Transistency Models…
Large language models (LLMs) have demonstrated significant potential in automating hardware synthesis, yet substantial barriers remain for industrial-scale, datapath-centric designs due to ambiguous specifications and a lack of formal…
The Memory stress (Mess) framework provides a unified view of the memory system benchmarking, simulation and application profiling. The Mess benchmark provides a holistic and detailed memory system characterization. It is based on hundreds…
Unsupervised neural machine translation(NMT) is associated with noise and errors in synthetic data when executing vanilla back-translations. Here, we explicitly exploits language model(LM) to drive construction of an unsupervised NMT…
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…
Large Multimodal Models (LMMs) have made significant breakthroughs with the advancement of instruction tuning. However, while existing models can understand images and videos at a holistic level, they still struggle with instance-level…
Despite recent advances in understanding and leveraging long-range conversational memory, existing benchmarks still lack systematic evaluation of large language models(LLMs) across diverse memory dimensions, particularly in multi-session…
To produce accurate predictions, language models (LMs) must balance between generalization and memorization. Yet, little is known about the mechanism by which transformer LMs employ their memorization capacity. When does a model decide to…
The ML-Schema, proposed by the W3C Machine Learning Schema Community Group, is a top-level ontology that provides a set of classes, properties, and restrictions for representing and interchanging information on machine learning algorithms,…
Large language models suffer from knowledge staleness and lack of interpretability due to implicit knowledge storage across entangled network parameters, preventing targeted updates and reasoning transparency. We propose ExplicitLM, a novel…
We study the formal semantics of non-volatile memory in the x86-TSO architecture. We show that while the explicit persist operations in the recent model of Raad et al. from POPL'20 only enforce order between writes to the non-volatile…
Emerging Persistent Memory technologies (also PM, Non-Volatile DIMMs, Storage Class Memory or SCM) hold tremendous promise for accelerating popular data-management applications like in-memory databases. However, programmers now need to deal…
Software transactional memory (STM) allows programmers to easily implement concurrent data structures. STMs simplify atomicity. Recent STMs can achieve good performance for some workloads but they have some limitations. In particular, STMs…
We introduce Mini-Sequence Transformer (MsT), a simple and effective methodology for highly efficient and accurate LLM training with extremely long sequences. MsT partitions input sequences and iteratively processes mini-sequences to reduce…
Accelerators provide large performance and energy-efficiency benefits, but can significantly change the hardware-software interface. The t\"{a}k\={o} programmable memory hierarchy accelerates data movement by enabling programmers to run…
Modern SoCs are heterogeneous parallel systems comprised of components developed by distinct teams and possibly even different vendors. The memory consistency model (MCM) of processors in such SoCs specifies the ordering rules which…
Computational pathology demands both visual pattern recognition and dynamic integration of structured domain knowledge, including taxonomy, grading criteria, and clinical evidence. In practice, diagnostic reasoning requires linking…
Large Language Models (LLMs) have demonstrated impressive capabilities in language generation and general task performance. However, their application to spoken language understanding (SLU) remains challenging, particularly for token-level…
Existing memory systems enable Large Language Models (LLMs) to support long-horizon human-LLM interactions by persisting historical interactions beyond limited context windows. However, while recent approaches have succeeded in constructing…
Long Short-Term Memory (LSTM) and Transformers are two popular neural architectures used for natural language processing tasks. Theoretical results show that both are Turing-complete and can represent any context-free language (CFL).In…
Memory performance is often the main bottleneck in modern computing systems. In recent years, researchers have attempted to scale the memory wall by leveraging new technology such as CXL, HBM, and in- and near-memory processing. Developers…