Knowledge catalogue
arXiv:2605.12031v1 Announce Type: cross Abstract: Multimodal deep learning has shown strong potential in medical applications by integrating heterogeneous data sources such as medical images and struc
arXiv:2605.11374v1 Announce Type: cross Abstract: Test-time compute is widely believed to benefit only large reasoning models. We show it also helps small embedding models. Most modern embedding check
arXiv:2605.11856v1 Announce Type: cross Abstract: Multimodal large language models are increasingly expected to perform thinking with images, yet existing visual latent reasoning methods still rely on
arXiv:2605.11710v1 Announce Type: cross Abstract: Object-centric representations promise a key property for few-shot learning: Rather than treating a scene as a single unit, a model can decompose it i
arXiv:2605.08785v1 Announce Type: cross Abstract: Neural Networks (NNs) have been widely adopted due to their outstanding efficacy and adaptability across computer vision and deep learning application
arXiv:2510.18184v3 Announce Type: replace-cross Abstract: Large language models (LLMs) excel at generating fluent text, but their internal reasoning remains opaque and difficult to control. Sparse aut
arXiv:2605.10397v1 Announce Type: cross Abstract: Visual anomaly detection (VAD) is crucial in many real-world fields, such as industrial inspection, medical imaging, infrastructure monitoring, and re
arXiv:2605.08271v1 Announce Type: cross Abstract: Understanding ultra-long videos such as egocentric recordings, live streams, or surveillance footage spanning days to weeks, remains a challenge. For
arXiv:2605.08590v1 Announce Type: cross Abstract: LLMs are increasingly used to explain personal sensing data, translating traces of activity and mood into natural-language accounts of why an anomalou
arXiv:2605.08885v1 Announce Type: new Abstract: SO(3) equivariant graph neural networks have become the dominant paradigm for atomistic foundation models, achieving high accuracy and data efficiency b
arXiv:2605.09188v1 Announce Type: cross Abstract: Reinforcement learning improves the reasoning ability of large language models but remains costly and sample-inefficient, as many rollouts provide wea
arXiv:2605.08389v1 Announce Type: cross Abstract: Zero-shot composed image retrieval (ZS-CIR) retrieves a target image from a reference image and a text modification without human-annotated CIR triple
arXiv:2605.10190v1 Announce Type: new Abstract: Open-vocabulary object detection (OVOD) aims to detect both seen and unseen categories, yet existing methods often struggle to generalize to novel objec
arXiv:2605.08568v1 Announce Type: new Abstract: Large language models (LLMs) have rapidly grown in scale, creating substantial memory and computational costs that hinder efficient deployment. Singular
arXiv:2605.09537v1 Announce Type: new Abstract: Despite rapid progress in Vision-Language-Action (VLA) models for robotic control, instruction drift remains a persistent failure mode in long-horizon t
arXiv:2605.10765v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) achieve strong performance through instruction tuning, yet real-world deployment often requires continual cap
arXiv:2602.06550v2 Announce Type: replace-cross Abstract: Zero-shot generalization in contextual reinforcement learning remains a core challenge, particularly when the context is latent and must be in
arXiv:2605.09278v1 Announce Type: new Abstract: Multi-agent debate (MAD) systems increasingly rely on shared memory to support long-horizon reasoning, but this convenience opens a critical vulnerabili
arXiv:2601.21484v2 Announce Type: replace Abstract: Reinforcement Learning (RL) post-training alignment for language models is effective, but also costly and unstable in practice, owing to its complic
arXiv:2605.10318v1 Announce Type: new Abstract: Large language models (LLMs) allow users to query databases using natural language by translating questions into executable queries. Despite strong prog
arXiv:2605.09986v1 Announce Type: cross Abstract: Training a language model on data scattered across bandwidth-limited nodes that cannot be centralized is a setting that arises in clinical networks, e
arXiv:2605.09430v1 Announce Type: new Abstract: Large-scale autoregressive models have demonstrated remarkable capabilities in image generation. However, their sequential raster-scan decoding relies o
arXiv:2605.10645v1 Announce Type: new Abstract: Data-driven medical AI is traditionally formulated as a discriminative mapping from input X to output Y via a learned function f, which does not general
arXiv:2605.10893v1 Announce Type: new Abstract: Large vision-language models suffer from visual ungroundedness: they can produce a fluent, confident, and even correct response driven entirely by langu
arXiv:2605.10386v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are increasingly integrated into autonomous driving (AD) systems; however, they remain vulnerable to diverse sa
arXiv:2605.10942v1 Announce Type: new Abstract: World Action Models (WAMs) have emerged as a promising paradigm for robot control by modeling physical dynamics. Current WAMs generally follow two parad
arXiv:2605.10717v1 Announce Type: cross Abstract: Multi-agent trajectory modeling traditionally focuses on forecasting, often neglecting more general tasks like trajectory completion, which is essenti
arXiv:2605.10628v1 Announce Type: new Abstract: Few-shot anomaly detection (FSAD) has made significant strides, yet existing methods still face critical challenges: (i) dependence on task- or dataset-
arXiv:2605.09954v1 Announce Type: cross Abstract: Articulated objects used in simulation and embodied AI are typically specified by geometry and kinematic structure, but lack the fine-grained dynamica
arXiv:2605.08156v1 Announce Type: cross Abstract: Zero-shot recognition aims to classify an image by selecting the most compatible label description from a set of candidate classes without any task-sp
arXiv:2605.08626v1 Announce Type: cross Abstract: Large language models (LLMs) are transforming society, powering applications from smartphone assistants to autonomous driving. Yet cloud-based LLM ser
arXiv:2605.08975v1 Announce Type: new Abstract: Reasoning-based end-to-end (E2E) autonomous driving has recently emerged as a promising approach to improving the interpretability of driving decisions
arXiv:2605.08489v1 Announce Type: new Abstract: Accurate modeling of nonlinear vehicle dynamics is essential for high-speed autonomous racing, where controllers operate at the handling limits. Model-b
arXiv:2605.09217v1 Announce Type: new Abstract: For AI systems to be useful to humans, they must understand and act in accordance with our values and preferences. Since specifying preferences is a har
arXiv:2602.00877v2 Announce Type: replace Abstract: Low speed does not always guarantee safety in off-road driving. For instance, crossing a ditch may be risky at a low speed due to the risk of gettin
arXiv:2605.08805v1 Announce Type: new Abstract: Audio-Visual Segmentation (AVS) targets pixel level localization of sounding emitting objects in videos. However, existing models rely on dense cross-mo
arXiv:2605.08305v1 Announce Type: cross Abstract: Large Language Model (LLM) systems have been the frontier of AI in many application domains, leading to new challenges and opportunities for hyperpara
arXiv:2605.10820v1 Announce Type: new Abstract: Scientific discovery is fundamentally a resource-constrained process that requires navigating complex trade-offs between the quality and quantity of mea
arXiv:2605.10008v1 Announce Type: cross Abstract: Optical readout in low-light imaging is fundamentally limited by measurement noise, including photon shot noise, detector noise, and quantization erro
arXiv:2605.10067v1 Announce Type: cross Abstract: Red teaming is critical for uncovering vulnerabilities in Large Language Models (LLMs). While automated methods have improved scalability, existing ap
arXiv:2605.10148v1 Announce Type: new Abstract: The Vision Transformer (ViT) achieves remarkable accuracy across visual tasks but remains computationally expensive for edge deployment. This paper pres
arXiv:2605.10120v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) show remarkable potential for scientific reasoning, yet their performance in specialized domains such as micr
$NBIS announced a partnership with LangChain to integrate Nebius Token Factory with LangChain’s Deep Agents. The goal is to make it easier for teams building AI agents on LangChain to run those worklo
arXiv:2510.05635v2 Announce Type: replace-cross Abstract: Test-Time Adaptation (TTA) methods are often computationally expensive, require a large amount of data for effective adaptation, or are brittl
arXiv:2605.08762v1 Announce Type: cross Abstract: Current omni-modal benchmarks mainly evaluate models under settings where multiple modalities are provided simultaneously, while the ability to start
arXiv:2603.10165v2 Announce Type: replace-cross Abstract: Every agent interaction generates a next-state signal, namely the user reply, tool output, terminal or GUI state change that follows each acti
arXiv:2605.09434v1 Announce Type: cross Abstract: Low-cost air quality sensors are becoming ubiquitous in our daily lives as public awareness of air pollution continues to grow, and people take measur
arXiv:2605.10458v1 Announce Type: new Abstract: Atomic properties such as partial charges or multipoles encode chemically meaningful information that can inform downstream molecular property predictio
arXiv:2605.10931v1 Announce Type: cross Abstract: Transformers with self-attention modules as their core components have become an integral architecture in modern large language and foundation models.
arXiv:2605.10612v1 Announce Type: cross Abstract: Graph neural networks are increasingly adopted in trigger systems for collider experiments, where strict latency and throughput constraints render dep
arXiv:2605.08454v1 Announce Type: cross Abstract: Recovering continuous-time dynamics from discrete observations is difficult because local supervision (e.g., pointwise regression targets, derivative
arXiv:2510.20129v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) remain vulnerable to jailbreak attacks, where adversarially crafted prompts induce policy-violating responses des
arXiv:2605.09630v1 Announce Type: new Abstract: Tokenizer-free language models eliminate the tokenizer step of the language modeling pipeline by operating directly on bytes; patch-based variants furth
arXiv:2605.05736v2 Announce Type: replace Abstract: Vector quantization (VQ) with autoregressive (AR) token modeling is a widely adopted and highly competitive paradigm for time-series generation. How
arXiv:2605.08526v1 Announce Type: new Abstract: While LLM-based agents excel at planning and executing long action sequences, their execution often remains inconsistent across trials, limiting reliabi
arXiv:2510.22767v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) typically come with a fixed architecture, despite growing evidence that not all layers contribute equally to ever
arXiv:2605.06047v2 Announce Type: replace-cross Abstract: Tabular foundation models (TFMs), such as TabPFN-2.6, TabICLv2, ConTextTab, Mitra, LimiX, and TabDPT, achieve strong zero-shot performance thr
arXiv:2605.08116v1 Announce Type: cross Abstract: Recent work on text diffusion models offers a promising alternative to autoregressive generation, but controlling their safety remains underexplored.
arXiv:2605.09670v1 Announce Type: cross Abstract: Teleoperation systems are fundamentally limited by communication latency, which degrades situational awareness and control performance. Predictive dis
arXiv:2605.10843v1 Announce Type: cross Abstract: Large language models increasingly mediate decisions that turn on moral judgement, yet a growing body of evidence shows that their implicit preference