arXiv:2601.21920v1 Announce Type: cross Abstract: In the future of work discourse, AI is touted as the ultimate productivity amplifier. Yet, beneath the efficiency gains lie subtle erosions of human expertise and agency. This paper shifts focus from the future of work to the future of workers by navigating the AI-as-Amplifier Paradox: AI’s dual role as […]
SIA: Symbolic Interpretability for Anticipatory Deep Reinforcement Learning in Network Control
arXiv:2601.22044v1 Announce Type: cross Abstract: Deep reinforcement learning (DRL) promises adaptive control for future mobile networks but conventional agents remain reactive: they act on past and current measurements and cannot leverage short-term forecasts of exogenous KPIs such as bandwidth. Augmenting agents with predictions can overcome this temporal myopia, yet uptake in networking is scarce because […]
RedSage: A Cybersecurity Generalist LLM
arXiv:2601.22159v1 Announce Type: cross Abstract: Cybersecurity operations demand assistant LLMs that support diverse workflows without exposing sensitive data. Existing solutions either rely on proprietary APIs with privacy risks or on open models lacking domain adaptation. To bridge this gap, we curate 11.8B tokens of cybersecurity-focused continual pretraining data via large-scale web filtering and manual collection […]
Dr. Bench: A Multidimensional Evaluation for Deep Research Agents, from Answers to Reports
arXiv:2510.02190v2 Announce Type: replace Abstract: As an embodiment of intelligence evolution toward interconnected architectures, Deep Research Agents (DRAs) systematically exhibit the capabilities in task decomposition, cross-source retrieval, multi-stage reasoning, information integration, and structured output, which markedly enhance performance on complex and open-ended tasks. However, existing benchmarks remain deficient in evaluation dimensions, response format, and scoring […]
Scaling Behavior Cloning Improves Causal Reasoning: An Open Model for Real-Time Video Game Playing
arXiv:2601.04575v2 Announce Type: replace Abstract: Behavior cloning has seen a resurgence as scaling model and data sizes demonstrate strong performance. In this work, we introduce an open recipe for training a video game playing foundation model designed for inference in realtime on a consumer GPU. We release all data (8300+ hours of high quality human […]
One Model, Any Conjunctive Query: Graph Neural Networks for Answering Queries over Incomplete Knowledge Graphs
arXiv:2409.13959v3 Announce Type: replace-cross Abstract: Motivated by the incompleteness of modern knowledge graphs, a new setup for query answering has emerged, where the goal is to predict answers that do not necessarily appear in the knowledge graph, but are present in its completion. In this paper, we formally introduce and study two query answering problems, […]
Hexcute: A Compiler Framework for Automating Layout Synthesis in GPU Programs
arXiv:2504.16214v3 Announce Type: replace-cross Abstract: Efficient GPU programming is crucial for achieving high performance in deep learning (DL) applications. The performance of GPU programs depends on how data is parallelized across threads and arranged within memory subsystems. The mapping functions describing tensors on GPUs are known as emphtensor layouts. Low-level programming frameworks, such as CUTLASS […]
FastDINOv2: Frequency Based Curriculum Learning Improves Robustness and Training Speed
arXiv:2507.03779v3 Announce Type: replace-cross Abstract: Large-scale vision foundation models such as DINOv2 boast impressive performances by leveraging massive architectures and training datasets. But numerous scenarios require practitioners to reproduce those pre-training solutions, such as on private data, new modalities, or simply for scientific questioning–which is currently extremely demanding computation-wise. We thus propose a novel pre-training […]
Bridging Performance Gaps for ECG Foundation Models: A Post-Training Strategy
arXiv:2509.12991v2 Announce Type: replace-cross Abstract: ECG foundation models are increasingly popular due to their adaptability across various tasks. However, their clinical applicability is often limited by performance gaps compared to task-specific models, even after pre-training on large ECG datasets and fine-tuning on target data. This limitation is likely due to the lack of an effective […]
Language Lives in Sparse Dimensions: Toward Interpretable and Efficient Multilingual Control for Large Language Models
arXiv:2510.07213v2 Announce Type: replace-cross Abstract: Large language models exhibit strong multilingual capabilities despite limited exposure to non-English data. Prior studies show that English-centric large language models map multilingual content into English-aligned representations at intermediate layers and then project them back into target-language token spaces in the final layer. From this observation, we hypothesize that this […]
Formal Verification of Noisy Quantum Reinforcement Learning Policies
arXiv:2512.01502v2 Announce Type: replace-cross Abstract: Quantum reinforcement learning (QRL) aims to use quantum effects to create sequential decision-making policies that achieve tasks more effectively than their classical counterparts. However, QRL policies face uncertainty from quantum measurements and hardware noise, such as bit-flip, phase-flip, and depolarizing errors, which can lead to unsafe behavior. Existing work offers […]
When Ads Become Profiles: Uncovering the Invisible Risk of Web Advertising at Scale with LLMs
arXiv:2509.18874v3 Announce Type: replace-cross Abstract: Regulatory limits on explicit targeting have not eliminated algorithmic profiling on the Web, as optimisation systems still adapt ad delivery to users’ private attributes. The widespread availability of powerful zero-shot multimodal Large Language Models (LLMs) has dramatically lowered the barrier for exploiting these latent signals for adversarial inference. We investigate […]