Knowledge catalogue
arXiv:2609.14973v1 Announce Type: new Abstract: We present PhysBrain 1.5, a unified model for understanding physical environments, generating actions, and predicting future states. Motivated by the ph
arXiv:2609.14507v1 Announce Type: cross Abstract: Single-GPU long-context inference with Mixture-of-Experts (MoE) models requires spilling the key-value cache (KVCache) to CPU memory. The spilled KV s
arXiv:2609.13152v1 Announce Type: new Abstract: Large language models (LLMs) perform strongly on static science benchmarks, yet their ability to reason about the physical world through active experime
arXiv:2609.15029v1 Announce Type: cross Abstract: Backdoor poisoning attacks add poisoned examples to otherwise-clean finetuning data, pairing a trigger with a target behavior that the model learns to
arXiv:2609.15017v1 Announce Type: cross Abstract: Prompt-injection detectors are typically evaluated using aggregate F1 on in-distribution test data, which offers limited insight into behavior under d
arXiv:2609.15562v1 Announce Type: cross Abstract: As generative models continue to advance, AI-generated content (AIGC) is becoming increasingly realistic, weakening the artifact cues commonly exploit
arXiv:2609.13566v1 Announce Type: new Abstract: Industrial maintenance systems involve multiple interacting assets and shared resources, making it challenging to balance reliability and operational co
arXiv:2609.14820v1 Announce Type: cross Abstract: This work presents POLARIS, a training-free audio fingerprinting system that selects landmarks from a locally normalized saliency field and groups the
arXiv:2609.14400v1 Announce Type: new Abstract: Agent benchmarks evaluate policy compliance but assume each policy determines a unique correct action. Natural-language policies can violate this assump
arXiv:2609.13760v1 Announce Type: new Abstract: Publishing a research manuscript is a routine yet demanding part of scientific life: time-consuming, stressful, and often uncertain in outcome. Recent a
arXiv:2605.06165v2 Announce Type: replace Abstract: As the widespread adoption of Large Language Models (LLMs) accelerates, token consumption from intermediate reasoning traces increasingly contribute
arXiv:2609.15229v1 Announce Type: cross Abstract: We propose a pre-fine-tuning probing method for Parameter-Efficient Fine-Tuning (PEFT) layer selection, aiming to obtain more stable and higher gains
arXiv:2609.13507v1 Announce Type: new Abstract: Brain-computer interfaces (BCIs) decode neural activity to restore lost function. Typically, training a high-performance neural decoder requires a large
arXiv:2609.13200v1 Announce Type: cross Abstract: Compact transistor models are the mathematical backbone of circuit simulation. However, at advanced nodes such as 3nm, transport physics becomes too c
arXiv:2609.15885v1 Announce Type: cross Abstract: This study proposes a privacy-enhanced federated learning framework to address secure collaborative training in distributed data environments. The fra
arXiv:2504.08075v2 Announce Type: replace-cross Abstract: We develop a correspondence between the structure of Turing machines and the structure of singularities of real analytic functions, based on c
arXiv:2609.15679v1 Announce Type: cross Abstract: This paper studies projection-free algorithms for stochastic constrained multi-level compositional optimization. In this context, the objective functi
arXiv:2609.15847v1 Announce Type: cross Abstract: This paper proposes FREDI (Fair Resource Allocation for Edge Dual-Threshold Inference), a secure wireless edge-intelligence framework for event-trigge
arXiv:2609.14675v1 Announce Type: cross Abstract: This study addresses the PU classification problem under violations of the SCAR assumption. We investigate logistic regression-based approaches, namel
arXiv:2609.14773v1 Announce Type: new Abstract: As LLM conversations grow to hundreds of turns, full-context injection incurs O(N^2) cumulative token costs, while lossy summarization or hard truncatio
arXiv:2609.14473v1 Announce Type: new Abstract: Personal AI assistants hold the potential to evolve from digital interfaces into embodied companions capable of guiding users through complex physical a
arXiv:2607.21411v1 Announce Type: cross Abstract: Quantum transfer learning (QTL) is often evaluated by replacing a classical classifier with a fixed variational quantum head, but this hides a key que
arXiv:2609.14025v1 Announce Type: new Abstract: Forward-looking sonar object detection is essential for underwater perception, yet deployment on embedded platforms requires highly compact models. To a
arXiv:2609.15335v1 Announce Type: new Abstract: Multimodal retrieval integrates video, audio, subtitles, and text; however, recent geometric aggregators, such as Gramian volumes, hyperbolic volumes, a
arXiv:2609.06327v2 Announce Type: replace-cross Abstract: A query-oblivious coreset for a softmax-attention head is a subset of the key-value pairs whose attention output is within arepsilon of the fu
arXiv:2609.14412v1 Announce Type: new Abstract: Deep research agents answer complex questions through iterative loops of searching, reading, and reasoning. Recent work on reasoning-intensive benchmark
As you know, Qwen3.8 27B has built-in support for embeddings. It gives pretty decent results in llama.cpp with the following parameters: --embedding --pooling mean The problem is that enabling embeddi
arXiv:2609.13814v1 Announce Type: new Abstract: Natural interaction in digital and physical environments requires continuous perception and timely responses. Spoken dialogue relies on acoustic and lin
arXiv:2609.15189v1 Announce Type: new Abstract: Latent action models (LAMs) learn action representations from unlabeled videos by inferring latent actions from visual transitions and reconstructing fu
arXiv:2609.14759v1 Announce Type: cross Abstract: Alignment applied after pretraining is shallow in a measurable way: a single direction in a model's residual stream can be edited out, and the model s
arXiv:2609.15684v1 Announce Type: new Abstract: Language agents increasingly rely on reusable skills, but post-failure repair is often handled by opaque one-shot reflection: a model generates a skill
arXiv:2609.13798v1 Announce Type: cross Abstract: Operator learning is formulated on function spaces, but training data are typically available only through finite-dimensional representations. In enco
arXiv:2609.14377v1 Announce Type: new Abstract: Camouflage image generation (CIG) aims to synthesize realistic camouflaged images by blending foreground objects into concealment-compatible background
arXiv:2609.14590v1 Announce Type: new Abstract: Deep learning-based spatio-temporal disease progression models commonly overlook the incubation period of progressive diseases, limiting the use of thos
arXiv:2609.13524v1 Announce Type: cross Abstract: Critically ill patients with acute kidney injury (AKI) on continuous renal replacement therapy (CRRT) face high mortality, yet current risk assessment
arXiv:2609.13463v1 Announce Type: new Abstract: The increasing deployment of AI agents in long-horizon tasks yields massive execution logs. Diagnosing failures within these records is crucial for reli
arXiv:2508.13488v2 Announce Type: replace-cross Abstract: Loop closure detection is important for simultaneous localization and mapping (SLAM), which associates current observations with historical ke
arXiv:2602.13576v2 Announce Type: replace-cross Abstract: Evaluation and alignment pipelines for large language models increasingly rely on LLM-based judges, whose behavior is guided by natural-langua
arXiv:2609.13280v1 Announce Type: new Abstract: Prescription transcription errors are not interchangeable. A model that fabricates a drug and a model that misreads a legible dose pose very different c
Salesforce Inc. said today at its annual user conference Dreamforce that it has partnered with Nvidia Corp. to train and release Koa, a specialized artificial intelligence model that’s custom built fo
arXiv:2609.15066v1 Announce Type: cross Abstract: We present Salesforce Koa, an enterprise language model built by post-training the open-weight Nemotron-3-Super-120B foundation model with reinforceme
arXiv:2609.15022v1 Announce Type: new Abstract: Defense is a knowledge-intensive domain that requires precise understanding of specialized terminology, doctrinal concepts, operational procedures, and
arXiv:2609.15498v1 Announce Type: new Abstract: Recurrent Transformers reusing their weights rather than stacking L distinct layers are becoming widely adopted due to their parameter efficiency [1,2,3
arXiv:2609.13582v1 Announce Type: cross Abstract: A clinical agent benchmark can report the same verdict on identical inputs while the agent files a materially different order on each run. Such agents
arXiv:2502.20099v3 Announce Type: replace-cross Abstract: We evaluate methods for causal representation learning (CRL) on a simple, real-world system that satisfies the basic problem setup of CRL. The
arXiv:2609.13203v1 Announce Type: new Abstract: Pairwise relationships among mental-health symptoms are routinely summarised asscalar edge weights, which cannot express whether two symptoms carry over
The telecommunications industry is currently undergoing a paradigm shift, moving from traditional manual human-driven operations to fully Autonomous Network Operations. Modern networks have grown incr
arXiv:2601.19930v2 Announce Type: replace-cross Abstract: We introduce Daisy, a factual knowledge benchmark for Danish cultural heritage, based on curated topics from the Danish Culture Canon 2006. Fo
arXiv:2609.13236v1 Announce Type: new Abstract: Humanoid robots are becoming an important part of embodied artificial intelligence, driven by advances in reinforcement learning for locomotion, world m
arXiv:2609.15598v1 Announce Type: cross Abstract: Generative recommendation has emerged as a promising end-to-end paradigm for personalized recommendation. However, user preferences continuously evolv
arXiv:2609.13823v1 Announce Type: new Abstract: Point cloud data face serious semantic privacy risks during acquisition, transmission, and cross-institutional sharing. Existing methods mostly rely on
arXiv:2609.15011v1 Announce Type: new Abstract: Memory-augmented and tool-using agents expose exact private values when remote LLMs process retrieved memory, tool actions, and intermediate observation
arXiv:2609.14593v1 Announce Type: cross Abstract: Living-Off-the-Land (LOTL) is the dominant evasion technique of Advanced Persistent Threat (APT) actors, exploiting legitimate Windows utilities to co
arXiv:2609.15758v1 Announce Type: new Abstract: Extending large-scale multilingual automatic speech recognition (ASR) models to low-resource languages remains challenging. Model performance is skewed
arXiv:2609.13856v1 Announce Type: new Abstract: Enterprise customer support systems must answer customer questions correctly, retrieve the right policy information, use customer context, and pass diff
arXiv:2609.14122v1 Announce Type: new Abstract: We study the challenge of sign language video mimicking: given a driving video and a single reference frame, synthesize a video where the target signer
arXiv:2607.10198v2 Announce Type: replace Abstract: Search APIs expose ranked snippets, URLs, and metadata on which agents decide whether to answer, search again, or fetch pages. We evaluate these int
arXiv:2609.13353v1 Announce Type: cross Abstract: Agent skills are reusable units for language-model agents, but their risks emerge through model decisions, user context, tool calls, and execution fee
arXiv:2609.14560v1 Announce Type: new Abstract: General-purpose object detectors lose accuracy on UAV footage, where targets span only a handful of pixels and onboard compute is limited. Prior work co
arXiv:2609.13277v1 Announce Type: new Abstract: Lunar orbital missions, such as Lunar Reconnaissance Orbiter, Kaguya/SELENE, Gravity Recovery and Interior Laboratory, and Lunar Prospector, among other