Knowledge catalogue
arXiv:2608.23959v1 Announce Type: cross Abstract: Safety alignment in large language models (LLMs) remains brittle against a growing spectrum of attacks. Jailbreak attacks bypass safety mechanisms thr
arXiv:2608.24534v1 Announce Type: new Abstract: Clinical LLMs can generate recommendations that are factually plausible yet physiologically unsafe. We investigate whether safety alignment can be impro
arXiv:2608.24199v1 Announce Type: new Abstract: Generative simulation for surgical robotics still lacks real-time interaction. Physical-robot experiments, often involving animal or cadaver labs, are t
arXiv:2608.24727v1 Announce Type: cross Abstract: EEG foundation models pretrained via self-supervised learning promise transferable representations, but their generalization remains limited, especial
arXiv:2608.23824v1 Announce Type: cross Abstract: Unmanned aerial vehicle (UAV)-mounted 5G New Radio base stations (gNBs) can augment terrestrial networks with an on-demand, repositionable Frequency R
arXiv:2608.24069v1 Announce Type: new Abstract: LLM-based multi-agent trading systems, in which specialized agents collaborate through structured communication to produce trading decisions, are moving
arXiv:2608.23568v1 Announce Type: new Abstract: Memory and RAG evaluations often treat the answering model's input as an implementation detail, even though systems may render the same history as a mem
arXiv:2608.23799v1 Announce Type: cross Abstract: Recent progress in image restoration has converged on all-in-one architectures that jointly handle multiple degradations within a single network. Thes
arXiv:2608.24146v1 Announce Type: new Abstract: In reinforcement learning policy evaluation, classic on-policy methods often suffer from high variance when estimating policy performance. To mitigate t
arXiv:2608.24561v1 Announce Type: new Abstract: Rapid earthquake magnitude estimation is central to earthquake early warning, yet many operational systems depend on dense regional seismic networks and
arXiv:2608.23840v1 Announce Type: cross Abstract: Training large-scale AI models often outgrows a single data center, demanding sharded, multi-cluster, and decentralized training. However, the huge sp
arXiv:2608.23953v1 Announce Type: cross Abstract: An agent harness is what turns a language model into an autonomous agent: the surrounding code that builds the model's context, mediates its tools, ru
The first phase of the generative artificial intelligence infrastructure boom was defined by a race for graphics processing units. The next phase will be defined by what happens after those GPUs arriv
arXiv:2608.23763v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) has emerged as the standard layer connecting Large Language Model agents to external tool backends. This openness int
arXiv:2608.24674v1 Announce Type: new Abstract: Joint text-to-video-audio generation produces synchronized visual and acoustic content, but the long sampling trajectories and heterogeneous multimodal
arXiv:2608.24479v1 Announce Type: new Abstract: Massively parallel simulation changes the data regime in which off-policy reinforcement learning (RL) is trained, challenging stabilizers designed for d
arXiv:2608.24053v1 Announce Type: new Abstract: Universal multimodal embeddings are becoming a core component of modern AI systems, enabling heterogeneous content to be represented in a shared space f
arXiv:2608.24022v1 Announce Type: cross Abstract: LLM agents integrated with external resources gain complex task capabilities, yet the unified natural-language context channel makes them vulnerable t
arXiv:2608.24044v1 Announce Type: new Abstract: Latent world models plan by predicting how candidate actions transform learned representations. In self-predictive models, however, the encoder and pred
arXiv:2608.22235v1 Announce Type: new Abstract: Pore-scale flow governs transport and permeability behaviour in porous media engineering applications, yet repeated lattice Boltzmann method (LBM) simul
arXiv:2608.21385v1 Announce Type: cross Abstract: Social media has become a central arena in which armed conflicts are contested, yet the pro-Israel and pro-Palestine communities on Telegram, whose br
arXiv:2608.22496v1 Announce Type: new Abstract: Autonomous underwater vehicles (AUVs) rely on the fusion of inertial navigation systems (INS) and Doppler velocity logs (DVL) for accurate navigation. B
arXiv:2608.23478v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models can turn multimodal context into robot actions, but their action decoders are still trained largely by behavior cl
arXiv:2608.22066v1 Announce Type: cross Abstract: Attention-based multiple instance learning (ABMIL) using pathology foundation model embeddings is effective for slide-level tasks, but exhaustive infe
arXiv:2603.12031v3 Announce Type: replace-cross Abstract: Cloud-native container orchestration requires resource schedulers capable of balancing infrastructure expenditure, fault resilience, and node
arXiv:2608.21423v1 Announce Type: cross Abstract: Agentic security uses large-language-model (LLM) agents to plan, dispatch, and interpret security tools. As these systems move from demonstrations to
arXiv:2608.23217v1 Announce Type: cross Abstract: Fast and reliable plasma equilibrium prediction is essential for real-time tokamak operation and control, but conventional Grad-Shafranov (GS) solvers
arXiv:2608.21841v1 Announce Type: new Abstract: Conversational AI increasingly shapes consequential decisions, yet users have limited support for recognizing and resisting manipulation. We present AI
arXiv:2608.23143v1 Announce Type: new Abstract: Prostate cancer is among the most frequently diagnosed malignancies worldwide, and structured reporting of each biopsy core burdens pathologists. Existi
arXiv:2608.23283v1 Announce Type: new Abstract: General-purpose language models can reason and synthesize knowledge, but complex work also requires sustained interaction with files, information source
arXiv:2608.21747v1 Announce Type: cross Abstract: LLM-based coding agents generate complete software systems from high-level descriptions, yet little is known about how the format of architecture spec
arXiv:2608.21880v1 Announce Type: new Abstract: Bangla large language model (LLM) safety is difficult to evaluate with English-centric or standard-script benchmarks because Bangla users routinely writ
arXiv:2508.18646v3 Announce Type: replace Abstract: Despite their rapid advancement, large language models (LLMs) suffer from a critical disconnect between benchmark scores and real-world utility. Cur
arXiv:2508.05206v2 Announce Type: replace Abstract: Online advertising systems typically use a cascaded architecture to manage massive requests and candidate volumes, where the ranking stages allocate
The reinforcement learning (RL) ecosystem is rapidly adopting Ray as the unified compute runtime for complex post-training workflows. Across Google Cloud, we see customers using Ray for workloads rang
arXiv:2608.22610v1 Announce Type: new Abstract: Agent skills, structured artifacts distilled from interaction trajectories and dynamically reused from skill banks, have become a central mechanism for
arXiv:2608.23152v1 Announce Type: new Abstract: Counterspeech effectively neutralizes the impact of online hate. Although prior work explores automated counterspeech generation, it largely emphasizes
arXiv:2608.22221v1 Announce Type: new Abstract: We study counterfactual protocol evaluation: whether data collected under a realised observation protocol determine the predictive value of alternatives
arXiv:2607.27836v2 Announce Type: replace Abstract: Large language model unlearning is consistently fragile under relearn attacks. On TOFU, fine-tuning on twenty forget examples substantially recovers
Data center power startup Emerald AI Inc. today said that it has raised 150 million in new funding in an oversubscribed round at a valuation of 1.05 billion. Emerald will put the money into scaling up
arXiv:2608.22923v1 Announce Type: cross Abstract: Dense IoT networks require reliable communication despite limited spectrum and substantial multi-user interference while maintaining manageable receiv
arXiv:2608.22770v1 Announce Type: new Abstract: Financial institutions need an independent way to detect missing, stale, and misclassified corporate-event records in vendor databases. We introduce Sea
arXiv:2608.22638v1 Announce Type: cross Abstract: Copying a function from a chat window into an editor takes less than a second. For many uses of AI coding tools, that speed is the point; in settings
arXiv:2608.22278v1 Announce Type: new Abstract: Vision-based whole-body loco-manipulation on humanoid robots is challenging due to partial observability, contact-rich dynamics, and the difficulty of l
arXiv:2608.23268v1 Announce Type: new Abstract: Frontier multimodal large language models (MLLMs) deliver impressive perception yet still falter on scientific and mathematical reasoning. Parameter-lev
arXiv:2608.22014v1 Announce Type: new Abstract: Automated prompt and skill optimization typically produces a single static instruction that is reused across inference instances until the next optimiza
arXiv:2601.19066v3 Announce Type: replace-cross Abstract: Bug Reproduction Tests (BRTs) have been used in many Automated Program Repair (APR) systems, primarily for validating fixes and aiding fix gen
arXiv:2608.22629v1 Announce Type: new Abstract: Transferring reinforcement learning policies from simulation to Real-World robots remains a major challenge, particularly when dealing with low-level to
arXiv:2508.02609v3 Announce Type: replace-cross Abstract: Graph Neural Networks (GNN) have been extensively applied to industry recommendation systems, as seen in models like GraphSageite{GraphSage},
arXiv:2608.21766v1 Announce Type: cross Abstract: Both capability and safety benchmarks rest upon the assumption that the behavior of language models undergoing a test is informative about their behav
arXiv:2608.21571v1 Announce Type: new Abstract: Lung cancer remains a leading cause of cancer-related mortality worldwide, and early diagnosis is critical for improving survival. However, early-stage
arXiv:2607.16646v2 Announce Type: replace-cross Abstract: Large language models now translate natural-language descriptions of decision problems into solver-ready optimization models, and they fail si
arXiv:2608.21399v1 Announce Type: new Abstract: Supply chain forecasting systems increasingly operate under market shocks, non-identically distributed regional demand, and limited willingness to centr
arXiv:2608.21427v1 Announce Type: new Abstract: Tuberculosis (TB) is one of the most common and dangerous bacterial ailments. Every year, it causes a large number of deaths worldwide. Although many de
arXiv:2608.22842v1 Announce Type: new Abstract: Financial document parsing requires accuracy, structural consistency, and verifiability that current benchmarks often fail to reflect. We present FinixD
arXiv:2608.21702v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) grounds LLM generation on retrieved documents, but the standard terminal retrieval stage--dense-vector similarity,
arXiv:2608.23248v1 Announce Type: cross Abstract: Traditional clinical prediction models rely on task-specific pipelines and curated, structured data, which scale poorly and underutilize unstructured
arXiv:2608.21550v1 Announce Type: new Abstract: Disassembling end-of-life electric vehicle (EV) battery packs is dull and dangerous work, performed almost entirely by humans. We present GOLEM (General
IBM has released Granite 4.2, an open‑source agentic AI model that adds native reasoning, tool use, coding instruction following and speech capabilities to enterprise agents. The suite of pre‑built mo
arXiv:2608.22229v1 Announce Type: new Abstract: Normative rules like institutional charters and workplace policies must be both human-readable and operationally verifiable against actual environment r