Knowledge catalogue
arXiv:2404.00727v3 Announce Type: replace Abstract: All state-of-the-art coreference resolution (CR) models involve finetuning a pretrained language model. Whether the superior performance of one CR m
arXiv:2609.13481v1 Announce Type: new Abstract: Large language models have made abstractive summarization remarkably fluent, but generated summaries can hallucinate facts, posing serious risks in biom
arXiv:2609.14180v1 Announce Type: new Abstract: Fault detection in autonomous VTOL aircraft is critical because even minor component degradations can rapidly destabilize multirotor vehicles operating
arXiv:2609.13729v1 Announce Type: new Abstract: We present the Variational Incompressible Optimal Transport (VIOT) operator, a generative neural operator for amortized incompressible density transport
arXiv:2607.19223v2 Announce Type: replace-cross Abstract: Speculative decoding, in which a lightweight draft model first generates a draft sequence that is then verified by the target model, has becom
arXiv:2609.13303v1 Announce Type: cross Abstract: Medical image classification is frequently complicated by transitional categories whose feature distributions overlap those of adjacent classes, produ
arXiv:2609.14709v1 Announce Type: new Abstract: Immune therapies act across cell-intrinsic programs, tissue ecosystems, and patient-specific immune states, yet most predictors address these scales sep
arXiv:2609.15888v1 Announce Type: cross Abstract: Deep networks trained on structural MRI for Alzheimer's disease (AD) staging often reach reasonable accuracy while attending to anatomically irrelevan
arXiv:2504.19962v3 Announce Type: cross Abstract: Gravitational waves emitted by binary neutron-star inspirals carry information on components' masses and tidal deformabilities, but not directly radii
arXiv:2609.15277v1 Announce Type: new Abstract: Entrepreneurial cognition is a foundation of entrepreneurship research. Yet the growing involvement of large language models (LLMs) in entrepreneurial w
arXiv:2609.15524v1 Announce Type: new Abstract: BraTS-GoAT evaluates tumor segmentation across heterogeneous populations. We trained a conventional 3D nnU-Net on 1,351 labeled cases using five-fold cr
arXiv:2609.13531v1 Announce Type: cross Abstract: Can attention move a shock across several cells in one update without breaking it? We develop a conservative, fixed grid finite-volume scheme in which
arXiv:2609.14248v1 Announce Type: cross Abstract: Faithful citation attribution begins with identifying the intended source for a scientific claim. We study this source-identification capability throu
arXiv:2609.15523v1 Announce Type: cross Abstract: Logic attack graphs grounded in scanner output provide explicit and auditable attack path reasoning LLM-based agents lack. Integrating symbolic framew
arXiv:2609.15702v1 Announce Type: new Abstract: Pretrained score-based diffusion models provide strong unconditional priors, yet enforcing measurement or physics consistency in inverse problems is oft
arXiv:2609.15940v1 Announce Type: new Abstract: Vision-language-action policies are typically evaluated one perturbation at a time, providing a useful diagnosis of their sensitivity to individual dist
Manually tagging thousands of catalog products is slow and inconsistent. This walkthrough shows how to customize Qwen3-8B with supervised fine-tuning (SFT) and reinforcement learning with verifiable r
arXiv:2609.15054v1 Announce Type: new Abstract: Multi-Agent (MA) systems are effective at solving complex tasks that demand planning, tool use, and the synthesis of evidence from multiple sources. Exi
arXiv:2609.13807v1 Announce Type: new Abstract: Large language models reason in high-dimensional hidden-state spaces, while users observe only final outputs. We introduce Bypass Observation, a non-int
arXiv:2609.13271v1 Announce Type: new Abstract: Medical image segmentation needs diverse training data, but hospitals hold complementary scans they cannot share for privacy and regulatory reasons. Kno
arXiv:2609.13499v1 Announce Type: cross Abstract: Private Evolution (PE) generates high-fidelity synthetic data in federated settings without exposing users' raw data. It aggregates clipped user votes
arXiv:2609.13559v1 Announce Type: new Abstract: Large Language Models (LLMs) with function-calling capabilities are becoming critical for modern agentic AI systems. Nevertheless, current deployments t
arXiv:2609.13445v1 Announce Type: new Abstract: Speech-to-speech LLMs like Moshi, and its derivative PersonaPlex, can listen and speak concurrently through full-duplex generation. However, they can be
arXiv:2609.15664v1 Announce Type: cross Abstract: Amid the rapid advancement of physical-world intelligence, cloud-edge collaborative large language models (LLMs) have emerged as a promising roadmap f
arXiv:2609.15668v1 Announce Type: cross Abstract: Through pre-training on extensive text and image datasets, current multi-modal large language models (MLLMs) achieve strong performance on general tas
arXiv:2603.04419v3 Announce Type: replace-cross Abstract: Vision-language models produce different object and use descriptions under different persona prompts, but low overlap alone does not identify
arXiv:2510.19266v3 Announce Type: replace Abstract: State-space models (SSMs) have emerged as promising alternatives to Transformers for sequence modeling. However, training competitive SSMs from scra
arXiv:2609.15570v1 Announce Type: new Abstract: World Action Models (WAMs) use video generation models to predict future visual dynamics for robotic manipulation, but iterative denoising introduces ad
arXiv:2606.17995v2 Announce Type: replace-cross Abstract: We study the privacy of releasing functional posterior sample paths from a Gaussian process (GP) when the entire training set including covari
arXiv:2609.13800v1 Announce Type: new Abstract: Routing and cascades reduce tool-agent cost by transferring control across models, but stateful handoffs must preserve accepted choices, realized effect
arXiv:2609.15171v1 Announce Type: new Abstract: Airborne optical tracking of uncrewed aerial vehicle (UAV) swarms is challenging due to extremely small target scales, rapid viewpoint changes, and clut
arXiv:2609.13233v1 Announce Type: new Abstract: Thin structures such as tree branches are among the hardest cases for stereo matching: a branch is only a few pixels wide, the background is cluttered,
arXiv:2609.15161v1 Announce Type: cross Abstract: Large language model (LLM) driven multi-agent systems have shown promise in complex clinical reasoning, yet existing approaches rely on static strateg
arXiv:2609.15078v1 Announce Type: new Abstract: Vibe design agents turn natural-language briefs into rendered interfaces and frontend code. Yet a useful design agent should do more than produce one va
arXiv:2609.15049v1 Announce Type: cross Abstract: An ensemble can improve photovoltaic forecasts while adding components that contribute little or increase computation. We assess these effects through
arXiv:2609.15077v1 Announce Type: new Abstract: Molecular design is typically approached as a problem of finding molecules which can adopt a single bioactive conformation. In reality, molecules occupy
arXiv:2609.14187v1 Announce Type: cross Abstract: Memory-efficient feature representations are increasingly important in machine learning settings where storage, transmission cost, bandwidth, or priva
arXiv:2609.15089v1 Announce Type: new Abstract: Empathetic response generation in spoken dialogue systems requires both accurate emotion perception and appropriate emotion regulation. Grounded in psyc
arXiv:2609.15625v1 Announce Type: cross Abstract: Driven by the escalating demand for privacy-preserving computing, Federated Learning (FL) has witnessed remarkable progress, becoming a cornerstone te
arXiv:2609.13661v1 Announce Type: new Abstract: Knowledge graph question answering usually assumes that one system can reach the whole graph. In practice, facts are often held by organizations that sh
arXiv:2609.13519v1 Announce Type: new Abstract: Molecular design is most effective when generation mirrors the edits chemists actually make: extending a scaffold, replacing a substituent, or decoratin
arXiv:2609.15219v1 Announce Type: new Abstract: Founders face two linked decisions: whether to pursue an idea before founding, and which operating actions and capital partners fit afterward. We presen
arXiv:2609.14802v1 Announce Type: cross Abstract: Importance weights are essential in domain adaptation under label shift, yet their utility is often undermined by the finite sample uncertainty associ
arXiv:2609.15649v1 Announce Type: new Abstract: Compositional Zero Shot Learning aims to recognize unseen compositions by recombining learned primitives. Recent methods rely on vision language models
arXiv:2609.10714v1 Announce Type: cross Abstract: The ambitious requirements of sixth-generation (6G) networks are driving communication systems from reliable bit delivery toward meaning-aware and tas
arXiv:2609.14561v1 Announce Type: new Abstract: Active exploration and semantic navigation require an embodied agent to build memory from partial observations, predict how the evolution of observed sp
arXiv:2609.15895v1 Announce Type: new Abstract: Physical AI relies on frequently-updated, latency-sensitive video stream to perceive, reason, and interact with the physical world, resulting in strict
arXiv:2609.13695v1 Announce Type: new Abstract: Chunked vision language action (VLA) policies execute several commands per query, but jerk within chunks and across replanning boundaries can induce osc
arXiv:2609.13308v1 Announce Type: new Abstract: A companion evaluation found that naming the target part in a manipulation prompt increased action accuracy by 0.32-0.63 across eight vision-language mo
arXiv:2609.13534v1 Announce Type: new Abstract: We identify extbf{Harmfulness Propagation Dynamics (HPD)}: for harmful prompts, the projection of the last-token hidden state onto a learned harm direct
NVIDIA NVLink 6 offers a natively lossless fabric for large‑scale AI factories by integrating lightweight Forward Error Correction, physical‑layer retries, UPHY recovery and credit‑based flow control
After two days of fighting with benchmarking infrastructure, I finally benchmarked IFM/K2-Horizon-7B on 16GB VRAM. TL/DR: it works, but far behind Qwen-3.8-27B. Setup I compared 3 models - Qwen3.8-27B
arXiv:2609.13182v1 Announce Type: cross Abstract: Robert Smithson's 1970 land artwork Spiral Jetty, located in the north arm of Utah's Great Salt Lake, has alternated between submergence and exposure
arXiv:2609.14299v1 Announce Type: new Abstract: Predicting under an acquisition budget requires choosing feature groups whose value can depend on later queries. O-MPAC transfers finite-horizon risk-co
arXiv:2601.19567v3 Announce Type: replace-cross Abstract: We address the intrinsic dimensionality (ID) of high-dimensional trajectories, comprising n_s = 4,000,000 data points, of the Fermi-Pasta-Ulam
arXiv:2609.13845v1 Announce Type: cross Abstract: World models trained with joint-embedding predictive architectures learn compact, structured latent representations from physical interaction, yet pla
arXiv:2609.13154v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have made prompts increasingly large and complex. Techniques such as chain-of-thought reasoning (Wei et
arXiv:2609.14374v1 Announce Type: cross Abstract: Dynamic trajectory prediction has become an important paradigm for data-driven transient stability analysis (TSA), yet most existing predictors remain
arXiv:2609.15871v1 Announce Type: cross Abstract: Rising societal and lifestyle complexity has been linked to a growing prevalence of mental distress worldwide. Educational institutions, workplaces, c
arXiv:2609.14849v1 Announce Type: cross Abstract: We characterize how people are turning to LLMs as oracles: all-knowing authorities on subjective personal questions. Motivated by risks to users' auto