Knowledge catalogue
arXiv:2608.18727v1 Announce Type: new Abstract: Applying machine learning to web pages is challenging due to the need to interpret HTML together with associated resources and perform rendering to obta
arXiv:2608.17776v1 Announce Type: new Abstract: We demonstrate that RL finetuning an LLM using debate, a two-player adversarial game between a generator and a critic adjudicated by a weaker LLM judge,
arXiv:2608.17445v1 Announce Type: cross Abstract: Most large language model services use stateless defenses, which judge only the current request, to refuse harmful tasks. Decomposition attacks exploi
arXiv:2608.17646v1 Announce Type: new Abstract: This monograph develops elimination geometry (EG), a typed, native-loss, audit-oriented framework for studying when locally optimal objects can be reali
arXiv:2608.16930v1 Announce Type: cross Abstract: Existing multi-task learning methods rely on hard sharing, multiple paths or experts, adaptive sharing, and dynamic expansion. However, their capacity
arXiv:2608.17665v1 Announce Type: new Abstract: LLM-driven agents can autonomously exchange opinions on online platforms and form communities. Such agent-operated social platforms raise a new security
arXiv:2608.18041v1 Announce Type: new Abstract: Language has two parameters. Count how often words occur together and you estimate amplitude, the strength of association. Word embeddings and attention
arXiv:2608.17644v1 Announce Type: new Abstract: Agents increasingly interpret a person's natural-language preferences by querying an LLM for numerical preference judgments, e.g., by asking how much th
arXiv:2608.17386v1 Announce Type: new Abstract: Foundation-model policies for robotic manipulation are advancing rapidly on task success, but rigorous evaluation of whether they succeed safely is stil
arXiv:2608.17342v1 Announce Type: cross Abstract: Forecasting cryptocurrency prices remains a formidable challenge due to inherent non-stationarity, abrupt regime shifts, and multi-scale stochastic de
arXiv:2608.17605v1 Announce Type: cross Abstract: Conversational AI is moving beyond isolated text prompts toward sustained, multimodal interaction. In real conversations, users clarify goals, revise
arXiv:2608.16913v1 Announce Type: new Abstract: Road safety monitoring has historically been reactive, relying on crash-record analysis after fatalities and injuries have already occurred. Proactive i
arXiv:2603.06505v2 Announce Type: replace Abstract: Automatic speech recognition (ASR) has benefited from advances in pretrained speech and language models, yet most systems remain constrained to mono
arXiv:2608.16963v1 Announce Type: new Abstract: Learning analytics often treats unsupervised clusters of intelligent tutoring system (ITS) logs as learner types that should predict learning. We test t
arXiv:2608.17209v1 Announce Type: cross Abstract: End-to-end vision-language-action (VLA) and world-action models offer an elegant route to general-purpose robotics, but their reliability is bounded b
arXiv:2608.17965v1 Announce Type: cross Abstract: Online log anomaly detection is critical for maintaining the reliability of large-scale computing systems. Although recent language model-based log an
arXiv:2608.16978v1 Announce Type: new Abstract: Turning a frontier vision-language model into a robot policy usually means fine-tuning it to emit an action representation it never saw in pretraining,
We will continue to offer Zero Data Retention for frontier models. As AI takes on longer, more autonomous work and delivers greater value to businesses, safety systems also need to identify risks acro
arXiv:2608.17205v1 Announce Type: new Abstract: Vision-language models (VLMs) combine images and text, but when the two conflict and one becomes harder to read, it is unclear how a model shifts its re
arXiv:2608.14698v1 Announce Type: cross Abstract: Hyperlocal meteorological sensing is essential for accurate solar photovoltaic forecasting, yet professional-grade meteorological stations require inv
arXiv:2608.16236v1 Announce Type: new Abstract: Collaborative inference (CI) splits a model between an edge device and a server, whereby the client computes an intermediate activation, transmits it, a
arXiv:2608.15405v1 Announce Type: cross Abstract: Afterlife Delegation Protocol is a speculative design project that asks what death becomes when a will can act eternally. We design a speculative prot
arXiv:2608.15419v1 Announce Type: new Abstract: Articulated-object reconstructions recover explicit geometry and kinematics, but their parts often remain semantically anonymous and must be controlled
As models become more capable, the risks associated with developing and testing them internally also grow. We temporarily paused reinforcement learning (RL) training on our latest models intended for
arXiv:2608.16381v1 Announce Type: new Abstract: Agentic systems often organize execution and state around a single conversation, model invocation, or agent instance, even when real work spans many cal
arXiv:2608.16876v1 Announce Type: cross Abstract: We introduce Automatic Symbolic Regression (AutoSR), a fully automated system that instantiates Research-Space Symbolic Regression by searching persis
arXiv:2601.10161v3 Announce Type: replace-cross Abstract: Named Entity Recognition (NER) and Personally Identifiable Information (PII) anonymization are critical tasks in Natural Language Processing (
arXiv:2608.15788v1 Announce Type: new Abstract: Spatial intelligence requires foundation models to maintain coherent spatial state across interactions with the physical world. However, existing data-c
arXiv:2608.16126v1 Announce Type: cross Abstract: Identification of dominant polynomial-chaos modes is usually formulated as a sparse-regression problem on a sampled multivariate polynomial dictionary
arXiv:2608.14666v1 Announce Type: new Abstract: Unsupervised fault detection in industrial systems is dominated by reconstruction based methods that monitor individual sensor marginal distributions. T
arXiv:2608.15798v1 Announce Type: new Abstract: Language models are compared by their held-out per-token cross-entropy risk---the quantity scaling laws are fitted to. We show that it cannot be consist
arXiv:2608.15881v1 Announce Type: new Abstract: The Multiphysics Object-Oriented Simulation Environment (MOOSE) is an open-source finite-element framework for building multiphysics simulation applicat
arXiv:2608.16159v1 Announce Type: cross Abstract: Digital Twins (DTs) are increasingly used to monitor and analyze Cyber Physical Systems (CPS). However, in adversarial environments, the fidelity of a
arXiv:2608.15818v1 Announce Type: new Abstract: Music-driven dance video synthesis aims to animate a reference person according to a given music clip. The task is challenging because it requires a mod
arXiv:2608.15602v1 Announce Type: cross Abstract: While binary quantization theoretically promises extreme compression and acceleration for Large Language Models (LLMs), existing research often overlo
arXiv:2608.15127v1 Announce Type: cross Abstract: Agentic applications are shifting AI serving from isolated model inference to long-running workloads in which LLMs coordinate tools, environments, and
arXiv:2608.14804v1 Announce Type: new Abstract: Large language models (LLMs) have become the dominant interface of clinical artificial intelligence, yet the interface they expose (text in, text out, o
arXiv:2608.15032v1 Announce Type: cross Abstract: Converting a set of architectural blueprints into a complete material quantity takeoff requires visual perception across drawing sheets, dimensional a
arXiv:2608.15703v1 Announce Type: new Abstract: Large language model (LLM) agents often perform poorly on complex, long-horizon tasks because their context becomes increasingly cluttered over time. As
arXiv:2608.15922v1 Announce Type: cross Abstract: We show that the natural-gradient stationary condition of variational inference has an edge-local form on a Forney-style factor graph. We start from t
arXiv:2608.15755v1 Announce Type: new Abstract: User-centric multi-turn agents must act on an evolving task situation shaped by changing user intents, accumulated tool-grounded facts, missing informat
arXiv:2608.14626v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved substantial progress in safety alignment, yet their safety guarantees remain significantly weaker in low-re
arXiv:2608.15919v1 Announce Type: cross Abstract: Retrieval-Augmented Generation over knowledge graphs (Graph-RAG) has emerged as a powerful paradigm for grounding large language models in domain-spec
arXiv:2608.16477v1 Announce Type: new Abstract: AI-RAN brings large language model (LLM) serving close to mobile users, but cellular handover can separate an active request from its inference state: t
arXiv:2608.16425v1 Announce Type: new Abstract: Parallel reasoning improves the accuracy and robustness of large reasoning models by exploring multiple solution paths, but its computational cost grows
arXiv:2608.16831v1 Announce Type: new Abstract: Generative pretraining established reusable task representations; later work on language-based task conditioning and in-context learning showed that a f
arXiv:2608.15583v1 Announce Type: new Abstract: While Text-to-Image (T2I) diffusion models have achieved remarkable success, precise spatial and orientational control in multi-object scenes remains a
arXiv:2608.14569v1 Announce Type: new Abstract: Neural solvers for constraint satisfaction problems have achieved remarkable in-distribution accuracy, yet they suffer from a fundamental limitation per
arXiv:2608.14724v1 Announce Type: cross Abstract: The rapid advancement of intelligent transportation systems and autonomous driving relies heavily on multi-modal urban traffic datasets. However, cura
arXiv:2608.16033v1 Announce Type: new Abstract: In cognitive science, resource rationality asks how an agent should allocate limited computation to maximize expected value. Most reasoning and agent be
arXiv:2608.16338v1 Announce Type: cross Abstract: Video lane detection requires predictions that remain stable across frames, yet severe vehicle occlusions can break temporal cues. In streaming recurr
arXiv:2608.15089v1 Announce Type: new Abstract: Long-horizon agents can fail even when their underlying models can solve the constituent steps. They may lose track of mutable state, fail to reactivate
arXiv:2608.15012v1 Announce Type: cross Abstract: The rapid advancement of large language models (LLMs) has created a growing asymmetry in cybersecurity, where attack accelerates toward autonomous exe
arXiv:2608.16345v1 Announce Type: new Abstract: Pre-trained models (PTMs) provide a strong foundation for continual learning by offering stable representations that facilitate lightweight adaptation t
arXiv:2608.15341v1 Announce Type: new Abstract: Text-to-image diffusion models can be misused to generate harmful content through adversarial or paraphrased prompts that bypass built-in safety mechani
arXiv:2608.14588v1 Announce Type: new Abstract: Sequential multi-agent LLM pipelines chain specialized agents without verification at handoffs, creating a structural flaw with measurable and severe co
arXiv:2608.15337v1 Announce Type: cross Abstract: We disprove the expectation stated by Xin, Yu, and Ronney that the physical positive part strain G-equation should possess an effective burning veloci
arXiv:2608.14940v1 Announce Type: new Abstract: Current agent evaluations score models on the state visible at the end of a stopped run which they count as one trial. However, interpreting the score a
arXiv:2608.16502v1 Announce Type: new Abstract: Large-scale agents increasingly rely on retrieval to access external capabilities. We study this retrieval gate in structured tools and APIs, a measurab
arXiv:2608.14811v1 Announce Type: new Abstract: Teams that adopt cycle-consistent adversarial networks for unpaired image-to-image translation meet the same obstacles: adversarial training oscillates