Many-core neuromorphic systems accelerate Spiking Neural Networks (SNNs), yet their packet-based spike communication can spend substantial traffic and energy re...
Agentic systems have recently emerged as state-of-the-art approaches for automated theorem proving in formal mathematics. To assess how far these capabilities e...
Modern Mixture-of-Experts (MoE) models increasingly rely on large-scale AI accelerator clusters for efficient training. Ascend NPUs expose heterogeneous on-chip...
Natural Language Generation (NLG) evaluation has changed dramatically since 1990, and will continue to evolve in the future. In 1990, when NLG had close ties to...
Semantic type mismatch between a noun and its context is central to coercion phenomena. This paper introduces a graph-based method to examine how lexical and co...
Online services strive to maintain application responsiveness even when the traffic is unpredictable and fluctuating. Today's online services are commonly deplo...
We study a protocol-level test for weak-label benchmarks: whether benchmark outputs change when the provided evidence is intervened on. Metadata-only shortcut c...
Chart descriptions are essential for accessibility, cross-modal retrieval, and assisting readers in extracting insights from complex visualizations. As multimod...
Blockchain systems that settle financial transactions face a structural tension: the single validator that assembles each block holds unilateral power over tran...
Transaction ordering attacks extract billions of dollars annually from decentralized finance users in the form of Maximal Extractable Value (MEV). Byzantine Fau...
We introduce the Preisach Attention Layer (PAL), a novel sequence modelling architecture grounded in the classical Preisach hysteresis operator from mathematica...
Long-horizon language agents can make many plausible local tool calls yet fail to persist until a requested count is actually complete. We study this gap as Qua...
Developers often use microbenchmarks to choose the most performant implementation of a method or a class. On the Java Virtual Machine (JVM), this is commonly do...
Cloud-based Digital Twin (DT) platforms enable real-time monitoring, simulation, and collaborative decision-making across distributed clients. However, ensuring...
The Java Stream API aims at increasing developer productivity thanks to an easy-to-read declarative syntax to express computations. It also simplifies parallel ...
The Rust programming language is increasingly being considered for safety-critical system development. However, established safety standards such as ISO 26262 r...
Enterprise AI systems, built on large language models, retrieval pipelines and autonomous agents, introduce a class of risks that traditional software quality a...
Compiler phase ordering has a strong effect on program performance. Finding an effective sequence of passes is still a difficult task because the search space i...
Directed acyclic graph (DAG)-based Byzantine Fault-Tolerant (BFT) protocols achieve high throughput by decoupling dissemination from agreement and allowing many...
High-throughput inference serving is essential for applications built on large language models (LLMs). Existing serving frameworks reduce request-level and batc...
Spiking Neural Networks (SNNs) provide an energy-efficient paradigm for visual recognition. We present SpikingMoE, which integrates a spike-driven Transformer w...
AI coding assistants have become prolific in recent years. Through a longitudinal mixed-methods investigation, we examined how professional software engineers p...
AI-assisted code review tools typically operate as generic 'expert reviewer' agents, producing homogeneous findings regardless of the analysis type needed. We p...
The majority of software developers use or are planning to use Artificial Intelligence (AI) tools in their development processes. Their top reasons include impr...
Tokenisation is an integral part of the current NLP pipeline. Current tokenisation algorithms such as BPE and Unigram are greedy algorithms -- they make locally...
Video Large Language Models (Video-LLMs) have made rapid progress on temporal video understanding, yet many fail at a basic perceptual primitive: signed image-p...
We propose the Integrable Context-Dependent Demand Network (ICDN), a demand-first neural model for multiproduct retail demand. The model learns log-demand as a ...
Camera pose matters. The position and orientation of each viewpoint define a shared spatial coordinate frame that relates observations across video frames. Yet ...
Current motion-controlled image-to-video generation models rigidly follow user-provided trajectories that are often sparse, imprecise, and causally incomplete. ...
Language models must now generalize out of the box to novel environments and work inside inference-scaling search procedures, such as AlphaEvolve, that select r...
Vision-and-Language Navigation (VLN) requires an agent to ground language instructions to its own movement within a visual environment. While state-of-the-art m...
Exploration is a prerequisite for learning useful behaviors in sparse-reward, long-horizon tasks, particularly within 3D environments. Curiosity-driven reinforc...
Vision-Language-Action (VLA) models have shown strong potential for general-purpose robot manipulation by unifying perception and action. However, existing VLA ...
Robust training and validation of Autonomous Driving Systems (ADS) require massive, diverse datasets. Proprietary data collected by Autonomous Vehicle (AV) flee...
Robustness, domain adaptation, photometric and occlusion invariance, compositional generalisation, temporal robustness, alignment safety, and classical anisotro...
We propose and analyze a conservative drifting method for one-step generative modeling. The method replaces the original displacement-based drifting velocity by...
Autonomous agentic systems are largely static after deployment: they do not learn from user interactions, and recurring failures persist until the next human-dr...
Linear attention replaces the unbounded cache of softmax attention with a fixed-size recurrent state, reducing sequence mixing to linear time and decoding to co...
Large language model (LLM)-based multi-agent systems increasingly rely on intermediate communication to coordinate complex tasks. While most existing systems co...
AI chatbots are rapidly shaping how people encounter the news, yet no prior study has systematically measured how accurately these systems, with their proprieta...
LLM-powered AI agents require high-frequency state exploration (e.g., test-time tree search and reinforcement learning), relying on rapid checkpoint and rollbac...
Production systems generate millions of log lines daily, yet most anomaly detectors operate at the session or window-level, flagging groups of lines rather than...
Cloud service platforms increasingly rely on elastic infrastructures to support dynamic workloads. Spot instances provide discounted computing resources but int...
Representation Autoencoders (RAEs) leverage frozen vision foundation models (VFMs) as tokenizer encoders, providing robust high-level representations that facil...
Survival analysis aims to estimate a time-to-event distribution from data with censored observations. Many existing methods either impose structural assumptions...
Real-time cognitive load assessment from eye-tracking signals could potentially enable adaptive human-centered-AI such as safety-critical applications such as d...
Real-time cognitive load assessment is essential for adaptive human-computer interaction but remains challenging due to limited labeled data and poor cross-subj...
Large language models (LLMs) exhibit systematic political bias across a variety of sensitive contexts. We find that LLMs handle counterpart topics from opposing...
