large language models

GroupKV: Hierarchical KV Cache Management for Long-Context Diffusion LLM Inference

Diffusion large language models (dLLMs) are emerging as a promising generative paradigm that complements autoregressive decoding. In long-context settings, KV cache bloat and offloading transfer overhead have become primary bottlenecks in inference systems. Meanwhile, the periodic full-sequence recomputation and locali...

BR-MoE: A Memory-Budget-Aware Co-Design Framework for Efficient MoE Inference on Resource-Constrained GPUs

The Mixture-of-Experts (MoE) architecture has become the dominant paradigm for scaling Large Language Models, yet its explosive parameter growth routinely overflows the GPU memory budget. Weight quantization offers a practical way to fit these models into limited GPU memory, but reducing precision below 4 bits causes s...

OmniPipe: Efficient, Flexible and Scalable Pipeline Parallelism for Large Model Training

Mixture-of-Experts (MoE) has become the de facto architecture for scaling large language models, offering expanded capacity with manageable compute. Pipeline parallelism (PP) is indispensable for distributed MoE training, but state-of-the-art PP schemes face three major limitations: large pipeline bubbles, high per-sta...

AsymFlow: Enabling Long-Context LLM Serving via CPU-GPU Prefill-Decode Disaggregation

Driven by cost and privacy constraints, many organizations deploy large language model (LLM) inference on local CPU-GPU servers. For long-context requests, the key-value (KV) cache grows linearly with sequence length and can rapidly exhaust GPU memory, reducing both the maximum supported context and request concurrency...

AccESM: Packed-Total Exact Inference for CPU ESM2 Embedding

Protein language models such as ESM2 are now common tools in biology, and a common task is to compute pooled embeddings for large sequence sets. In many labs, this workload runs on shared CPU servers rather than GPUs, making CPU inference an important systems problem. Existing CPU stacks are general-purpose: they are n...

PIM-Forge: Toward Autonomous PIM Kernel Synthesis through Constraint-Guided Hardware Exploration

PIM-Forge is proposed, a constraint-guided memory-augmented multi-agent framework that iteratively explores hardware constraints and refines synthesis knowledge, validating the efficacy of constraint-guided hardware exploration.

Can We Really Leverage AI-Assisted Automatic Item Generation for Psychological Scale Development?

With the emergence of large language models (LLMs), researchers can use chatbots such as ChatGPT to rapidly generate large numbers of items for psychological scale development. This study examines the quality of AI-generated items. Across four preregistered studies, we compared AI-generated items with human-generated b...

From Self-Protection to Experiential Engagement: A State-Dependent Autonomic Model of Psychotherapy Process

This conceptual and clinical article introduces the State-Dependent Autonomic Response Model (SDARM), a transtheoretical framework for understanding moment-to-moment client responses during psychotherapy. The model addresses a common clinical challenge: as clients approach painful emotions, attachment injuries, traumat...

Large Language Models and the Personalization into Sameness

Evaluating Large Language Models for Antisemitic Incident Classification

Addressing hate and violence in society requires timely detection of hateful events from public reporting, but automated identification of hateful events remains underexplored. We introduce the task of hateful event detection and investigate the ability of AI systems, specifically large language models (LLMs), to disco...

Quantitative Analysis Data for SCAR Mentions by the ATCMs Including Climate Change Advice

This is the data from two Large Language Model analyses of the mentions of SCAR in Antarctic Treaty Consultative Meeting Reports, either overall or from a climate change advice perspective published by Chown et al. 2026 in Philosophical Transactions of the Royal Society A. The data are subject to analyses in R to deter...

Intelligent Materials Modelling: Large Language Models Versus Partial Least Squares Regression for Predicting Polysulfone Membrane Mechanical Performance