Related papers: Step 3.5 Flash: Open Frontier-Level Intelligence w…

Multimodal Transformers often produce predictions without clarifying how different modalities jointly support a decision. Most existing multimodal explainable AI (MXAI) methods extend unimodal saliency to multimodal backbones, highlighting…

Most recent state-of-the-art (SOTA) large language models (LLMs) use Mixture-of-Experts (MoE) architectures to scale model capacity without proportional per-token compute, enabling higher-quality outputs at manageable serving costs.…

With the widespread adoption of Mixture-of-Experts (MoE) models, there is a growing demand for efficient inference on memory-constrained devices. While offloading expert parameters to CPU memory and loading activated experts on demand has…

Autonomous driving holds transformative potential but remains fundamentally constrained by the limited perception and isolated decision-making with standalone intelligence. While recent multi-agent approaches introduce cooperation, they…

Despite recent advancements in offline multi-task reinforcement learning (MTRL) have harnessed the powerful capabilities of the Transformer architecture, most approaches focus on a limited number of tasks, with scaling to extremely massive…

As LLMs shift toward autonomous agents, Deep Research has emerged as a pivotal metric. However, existing academic benchmarks like BrowseComp often fail to meet real-world demands for open-ended research, which requires robust skills in…

Frontier AI safety policies highlight automation of AI research and development (R&D) by AI agents as an important capability to anticipate. However, there exist few evaluations for AI R&D capabilities, and none that are highly realistic…

The interpretability of Mixture-of-Experts (MoE) models, especially those with heterogeneous designs, remains underexplored. Existing attribution methods for dense models fail to capture dynamic routing-expert interactions in sparse MoE…

We introduce CFE-Bench (Classroom Final Exam), a multimodal benchmark for evaluating the reasoning capabilities of large language models across more than 20 STEM domains. CFE-Bench is curated from repeatedly used, authentic university…

A method is presented for accelerating inference in transformer language models by exploiting the low effective rank of the token activation manifold at each layer. The method decomposes each activation vector into a subspace component and…

Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of natural language processing tasks. Exploiting the heterogeneous capabilities of edge LLMs is crucial for diverse emerging applications, as it…

Before applying data analytics or machine learning to a data set, a vital step is usually the construction of an informative set of features from the data. In this paper, we present SMARTFEAT, an efficient automated feature engineering tool…

In the continued development of next-generation networking and artificial intelligence content generation (AIGC) services, the integration of multi-agent systems (MAS) and the mixture of experts (MoE) frameworks is becoming increasingly…

Penetration testing is essential for identifying vulnerabilities in web applications before real adversaries can exploit them. Recent work has explored automating this process with Large Language Model (LLM)-powered agents, but existing…

Automatic multi-agent systems aim to instantiate agent workflows without relying on manually designed or fixed orchestration. However, existing automatic MAS approaches remain only partially adaptive: they either perform training-free…

Performance optimization of deep learning models is conducted either manually or through automatic architecture search, or a combination of both. On the other hand, their performance strongly depends on the target hardware and how…

This paper introduces BioAgent Bench, a benchmark dataset and an evaluation suite designed for measuring the performance and robustness of AI agents in common bioinformatics tasks. The benchmark contains curated end-to-end tasks (e.g.,…

This article presents a modular, component-based architecture for developing and evaluating AI agents that bridge the gap between natural language interfaces and complex enterprise data warehouses. The system directly addresses core…

Mixture-of-Experts models have become a dominant architecture for scaling Large Language Models by activating only a sparse subset of experts per token. However, latency-critical MoE inference faces a fundamental tension: while expert…

Mixture of Experts (MoE) LLMs, characterized by their sparse activation patterns, offer a promising approach to scaling language models while avoiding proportionally increasing the inference cost. However, their large parameter sizes…