Knowledge catalogue
arXiv:2605.11033v1 Announce Type: cross Abstract: TokaMind is a multi-modal transformer (MMT) foundation model pre-trained on tokamak plasma diagnostics data from MAST, where it was shown to outperfor
arXiv:2605.12784v1 Announce Type: new Abstract: Advances in large language models (LLMs) have recently opened new and promising avenues for small-molecule drug discovery. Yet existing LLM-based approa
arXiv:2605.12521v1 Announce Type: cross Abstract: Multi-turn tool calling is essential for LLMs to function as autonomous agents, yet synthesizing the training data required for these capabilities rem
arXiv:2603.13054v2 Announce Type: replace Abstract: Topology is critical in tubular structures such as blood vessels, nerve fibers, and road networks, where connectivity and loop structure govern down
arXiv:2605.13834v1 Announce Type: cross Abstract: In this paper, we study solution operators of physical field equations on geometric meshes from a function-space perspective. We reveal that Hodge ort
arXiv:2605.13083v1 Announce Type: new Abstract: Egocentric human video data, which captures rich human-environment interactions and can be collected at scale, has become a key driver of embodied intel
arXiv:2605.13761v1 Announce Type: new Abstract: AI-driven flood digital twins demand fast hydrodynamic surrogates for ensemble forecasting and observation assimilation. Yet even GPU-accelerated two-di
arXiv:2602.16246v3 Announce Type: replace Abstract: Interactive large language model (LLM) agents operating via multi-turn dialogue and multi-step tool calling are increasingly used in production. Ben
arXiv:2605.13430v1 Announce Type: cross Abstract: Selection bias is pervasive in observational studies. For example, large scale biobanks data can exhibit ``healthy volunteer bias'' when respondents a
arXiv:2602.06475v2 Announce Type: replace Abstract: Large language models (LLMs) excel at complex tasks with advances in reasoning capabilities. However, existing reward mechanisms remain tightly coup
arXiv:2605.13119v1 Announce Type: cross Abstract: Vision-language-action (VLA) models are effective robot action executors, but they remain limited on long-horizon tasks due to the dual burden of exte
arXiv:2605.12584v1 Announce Type: cross Abstract: Recently, multimodal graph learning (MGL) has garnered significant attention for integrating diverse modality information and structured context to su
arXiv:2605.13530v1 Announce Type: cross Abstract: Surgical scene understanding is a cornerstone of computer-assisted intervention. While recent advances, particularly in surgical image segmentation, h
arXiv:2605.13329v1 Announce Type: cross Abstract: How large language models internally represent high-level behaviors is a core interpretability question with direct relevance to AI safety: it determi
arXiv:2605.12587v1 Announce Type: new Abstract: Dense 3D tracking from monocular video is fundamental to dynamic scene understanding. While recent 3D foundation models provide reliable per-frame geome
arXiv:2605.12817v1 Announce Type: cross Abstract: Longitudinal clinical notes contain rich evidence of how patients evolve over time, but converting this signal into training supervision for clinical
arXiv:2605.12645v1 Announce Type: cross Abstract: Effective personalized question answering (PQA) in language models requires grounding responses in the user's underlying intent, where intent refers t
arXiv:2605.13831v1 Announce Type: new Abstract: Long-context modeling is becoming a core capability of modern large vision-language models (LVLMs), enabling sustained context management across long-do
arXiv:2605.13401v1 Announce Type: new Abstract: We propose a data augmentation method for offline reinforcement learning, motivated by active positioning problems. Particularly, our approach enables t
arXiv:2605.13414v1 Announce Type: new Abstract: Deploying language models as autonomous agents requires more than per-task accuracy: when an agent faces a queue of problems under a finite token budget
arXiv:2605.13433v1 Announce Type: cross Abstract: Generative recommendation (GR) has emerged as a promising paradigm that replaces fragmented, scenario-specific architectures with unified Transformer-
arXiv:2605.13470v1 Announce Type: new Abstract: Recent advances in AI have been primarily driven by large-scale neural architectures that excel at function approximation, rather than by tailored induc
arXiv:2605.12965v1 Announce Type: new Abstract: Solutions to many partial differential equations (PDEs) display coexisting smooth global transport and localized sharp features within a single trajecto
arXiv:2605.12700v1 Announce Type: new Abstract: Neural operators have become an effective framework for learning mappings between function spaces, yet most existing architectures realize operators wit
arXiv:2605.13500v1 Announce Type: new Abstract: Reliable real-time 3D localization is essential for multi-UAV navigation, collision avoidance, and coordinated flight, yet onboard estimates can degrade
arXiv:2605.13560v1 Announce Type: new Abstract: This work studies lung tumor growth prediction from sparse and irregular longitudinal computed tomography (CT) observations with measurement variability
arXiv:2605.13049v1 Announce Type: new Abstract: Infrared and Visible Image Fusion (IVIF) has shown promise in visual tasks under challenging environments, but fusion under unregistered conditions face
arXiv:2605.13816v1 Announce Type: new Abstract: Digital phenotyping enables continuous passive monitoring of behavior and physiology, offering a promising paradigm for early detection of psychotic rel
arXiv:2605.12562v1 Announce Type: cross Abstract: Multi-window CT imaging captures complementary pathological information across anatomical structures of differing densities, yet existing deep learnin
arXiv:2605.12756v1 Announce Type: cross Abstract: Large language models (LLMs) are pretrained by minimizing the cross-entropy loss for next-token prediction. In this paper, we study whether this optim
arXiv:2605.13026v1 Announce Type: cross Abstract: Masked diffusion models (MDMs) have emerged as a promising alternative to autoregressive models (ARMs) for language modeling. However, MDMs are known
arXiv:2402.15415v2 Announce Type: replace Abstract: Low-Rank Adaptation (LoRA) is the dominant parameter-efficient fine-tuning method due to its favorable compute-performance trade-off, yet it suffers
arXiv:2605.13148v1 Announce Type: cross Abstract: Understanding why deep neural networks (DNNs) fail to generalize to unseen samples remains a long-standing challenge. Existing studies mainly examine
arXiv:2605.13260v1 Announce Type: new Abstract: Physics-Informed Neural Networks (PINNs) and their variational counterparts (VPINNs) are neural networks that incorporate physical laws, making them use
arXiv:2511.17001v2 Announce Type: replace Abstract: Cross-embodiment robot learning requires a unified action representation with consistent semantics across robot platforms. Existing representations
arXiv:2512.06109v3 Announce Type: replace-cross Abstract: This paper develops a unified perspective on several optimal control formulations through the lens of Kullback-Leibler (KL) regularization. We
arXiv:2605.13158v1 Announce Type: new Abstract: Image restoration under multiple adverse weather conditions aims to develop a single model to recover the underlying scene with high visibility. Weather
arXiv:2510.10642v3 Announce Type: replace-cross Abstract: Building generalist robot policies that can handle diverse tasks in open-ended environments is a central challenge in robotics. To leverage kn
arXiv:2509.15642v3 Announce Type: replace Abstract: Joint RGB-infrared perception is essential for achieving robustness under diverse weather and illumination conditions. Although foundation models ex
arXiv:2509.04477v3 Announce Type: replace-cross Abstract: A wide range of optimization problems can often be written in terms of generalized convex functions (GCFs). When this structure is present, it
arXiv:2605.13835v1 Announce Type: new Abstract: Class-Incremental Learning (CIL) enables models to continuously integrate new knowledge while mitigating catastrophic forgetting. Driven by the remarkab
arXiv:2605.13601v1 Announce Type: new Abstract: As intelligent systems are increasingly implemented in our society to make autonomous decisions, their commitment to human values raises serious concern
arXiv:2605.12978v1 Announce Type: new Abstract: Learning from past experience benefits from two complementary forms of memory: episodic traces -- raw trajectories of what happened -- and consolidated
arXiv:2605.13277v1 Announce Type: cross Abstract: Visual evidence selection is a critical component of multimodal retrieval-augmented generation (RAG), yet existing methods typically rely on semantic
arXiv:2605.13407v1 Announce Type: new Abstract: Predicting cross-sectional stock returns is challenging due to low signal-to-noise ratios and evolving market regimes. Classical factor models offer int
arXiv:2605.13764v1 Announce Type: cross Abstract: Modern retrieval-augmented generation (RAG) systems convert sensitive content into high-dimensional embeddings and store them in vector databases that
arXiv:2510.15297v4 Announce Type: replace-cross Abstract: We introduce VERA-MH (Validation of Ethical and Responsible AI in Mental Health), an automated evaluation of the safety of AI chatbots used in
arXiv:2605.13318v1 Announce Type: new Abstract: Chatbot usage has increased, including in fields for which they were never developed for--notably mental health support. To that end, we introduce Valid
arXiv:2605.12571v1 Announce Type: cross Abstract: Long video question answering requires locating sparse, time-scattered visual evidence within highly redundant content. Although current MLLMs perform
arXiv:2605.13034v1 Announce Type: new Abstract: Recent deep research systems have improved the ability of large language models to produce long, grounded reports through iterative retrieval and reason
arXiv:2605.12904v1 Announce Type: new Abstract: Tabular foundation models (TFMs) have emerged as a powerful paradigm for in-context learning on structured data, enabling direct prediction on new tabul
arXiv:2504.11944v3 Announce Type: replace-cross Abstract: Offline reinforcement learning (RL) learns effective policies from pre-collected datasets, offering a practical solution for applications wher
arXiv:2412.06341v2 Announce Type: replace-cross Abstract: We propose Ciliary-DETR (previous name: Elastic-DETR), a framework for test-time resolution adjustment analogous to biological accommodation.
arXiv:2605.12684v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) are now routinely deployed for visual understanding, generation, and curation. A substantial fraction of thes
arXiv:2506.15953v2 Announce Type: replace Abstract: Dexterous manipulation is a cornerstone capability for robotic systems aiming to interact with the physical world in a human-like manner. Although v
arXiv:2605.13087v1 Announce Type: cross Abstract: Fine-tuning multilingual ASR models like Whisper for low-resource languages often improves read speech but degrades spontaneous audio performance, a p
arXiv:2605.13798v1 Announce Type: new Abstract: Cross-modal 3D medical image analysis requires voxelwise representations that remain anatomically consistent across imaging contrasts, scanners, and acq
arXiv:2605.13846v1 Announce Type: cross Abstract: This paper introduces WARDEN, an early language model system capable of transcribing and translating Wardaman, an endangered Australian indigenous lan
arXiv:2605.13095v1 Announce Type: cross Abstract: Watermarking is widely proposed for provenance, attribution, and safety monitoring in generative models, yet is typically evaluated only under adversa
arXiv:2605.13621v1 Announce Type: new Abstract: Infrared-visible object detection improves detection performance by combining complementary features from multispectral images. Existing backbone-specif