Knowledge catalogue
arXiv:2608.04480v1 Announce Type: new Abstract: Video temporal grounding (VTG) refers to the task of identifying the time interval in a video that corresponds to a given natural-language query. A comm
arXiv:2603.19636v2 Announce Type: replace Abstract: Accurate RNA structure modeling remains difficult because RNA backbones are highly flexible, non-canonical interactions are prevalent, and experimen
arXiv:2608.04330v1 Announce Type: new Abstract: Removing the left context from a causal language model reveals a useful kind of boundary: an edge where the model processes the same right-hand tokens w
arXiv:2601.05451v2 Announce Type: replace-cross Abstract: Recent advances in text-to-SQL have been driven by larger models, better datasets, and new training methods like RLVR. However, progress remai
arXiv:2607.21597v2 Announce Type: replace Abstract: Evaluating wildfire risk systems using standard machine-learning metrics such as F1-score or IoU is fundamentally flawed: these metrics assess event
arXiv:2608.05115v1 Announce Type: cross Abstract: Can computer vision help make classrooms safer? In this pilot study, we investigate privacy-aware and computationally efficient classroom incident rec
arXiv:2608.04045v1 Announce Type: cross Abstract: Federated learning (FL) enables aircraft fleet operators to jointly train remaining-useful-life (RUL) models from engine sensor telemetry without shar
arXiv:2608.04832v1 Announce Type: new Abstract: Control policies optimized in simulation can perform poorly in the real system when the parameters x of the simulator are estimated from limited data bu
arXiv:2608.04442v1 Announce Type: cross Abstract: Robustness to natural corruptions remains a fundamental challenge for deep neural networks. In this paper, we identify a robustness fading phenomenon
arXiv:2602.11506v4 Announce Type: replace-cross Abstract: The transition toward localized intelligence through Small Language Models (SLMs) has intensified the need for rigorous performance characteri
arXiv:2608.04842v1 Announce Type: new Abstract: Replicating real-world environments into simulation by realistic visual representation like NeRF and 3D Gaussian Splatting (3DGS) has emerged as an effe
arXiv:2608.04132v1 Announce Type: new Abstract: High-resolution images and long videos provide vision-language models with rich context for multimodal reasoning and fine-grained perception, but the re
arXiv:2608.04246v1 Announce Type: cross Abstract: Vision-language-action policies often fail under deployment-time distribution shifts such as clutter, distractor objects, lighting changes, novel obje
arXiv:2608.04289v1 Announce Type: new Abstract: Long-horizon agents increasingly use persistent memory and tools to take actions with external side effects. A central failure mode is premature commitm
arXiv:2603.17430v2 Announce Type: replace Abstract: Autonomous landing of uncrewed aerial vehicles (UAVs) in unknown, dynamic environments poses significant safety challenges, particularly near people
arXiv:2608.05097v1 Announce Type: new Abstract: Reasoning about necessity and possibility depends on assumptions about accessibility between worlds and about which objects exist at each one. The same
arXiv:2608.04288v1 Announce Type: new Abstract: Calibration requires a predictor to be unbiased after conditioning on its own predictions. Multicalibration asks for this guarantee simultaneously acros
arXiv:2608.04975v1 Announce Type: cross Abstract: SciCode is the standard measure of the scientific-coding ability of language models: research-level problems that demand both frontier scientific theo
arXiv:2608.04420v1 Announce Type: new Abstract: Safe navigation with a body-mounted limited-field-of-view sensor requires the complete robot-inflated volume of an intended motion to be observed and ve
arXiv:2608.04804v1 Announce Type: cross Abstract: Frontier language models can resolve repository-level software issues, but each attempt is expensive, and existing routers select a model from the iss
arXiv:2603.18774v2 Announce Type: replace Abstract: Foundational feed-forward visual geometry models enable accurate and efficient camera pose estimation and scene reconstruction by learning strong sc
arXiv:2608.04299v1 Announce Type: new Abstract: Fifteen years ago, Low proposed that pun translators should stop searching for equivalent words and instead search for new points of contact between sou
arXiv:2608.04441v1 Announce Type: new Abstract: Transfer-based adversarial attacks often transfer poorly across heterogeneous architectures because CNNs favor local textures while Vision Transformers
arXiv:2603.14294v3 Announce Type: replace-cross Abstract: Do video diffusion models encode signals predictive of physical plausibility? We probe intermediate denoising representations of pretrained Di
arXiv:2608.04810v1 Announce Type: new Abstract: Automated assessment of degenerative pathology in the lumbar spine on magnetic resonance imaging (MRI) requires access to large-scale datasets of expert
arXiv:2507.05173v2 Announce Type: replace Abstract: Generating intermediate video content of varying lengths based on given first and last frames, along with text prompt information, offers significan
arXiv:2606.18993v2 Announce Type: replace-cross Abstract: Testing conditional independence is fundamental yet intrinsically difficult: without additional assumptions, Type I error control is impossibl
arXiv:2604.07396v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) inference on edge Neural Processing Units (NPUs) is fundamentally constrained by limited on-chip memory capacity. A
arXiv:2608.05018v1 Announce Type: new Abstract: Short-term load forecasting (STLF) play a vital role in the electric power industry. It serves infrastructure that European and German law designate as
arXiv:2608.04244v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) make grounded predictions in real-world scenes by combining visual and textual cues, yet existing benchmarks
arXiv:2608.04196v1 Announce Type: cross Abstract: Recent years have witnessed an explosive trend of scaling ego-centric human videos for robot manipulation, yet it remains unclear which data actually
arXiv:2608.04750v1 Announce Type: cross Abstract: Similes provide a compact and expressive way to describe visual characteristics in text prompts. Recent text-to-image models (t2i models) can produce
arXiv:2603.29152v2 Announce Type: replace Abstract: Metal-organic frameworks (MOFs) offer a vast design space, and as such, computational simulations play a critical role in predicting their structura
arXiv:2603.11532v2 Announce Type: replace-cross Abstract: We study the problem of estimating multiple discrete unimodal distributions, motivated by search behavior analysis on a real-world platform. T
arXiv:2608.04060v1 Announce Type: cross Abstract: Joint-embedding predictive architectures learn abstract states by predicting target embeddings from context embeddings, but their transition models ar
arXiv:2608.04828v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on skills, structured documents that specify when to act, which procedure to follow, and which tools
arXiv:2608.05137v1 Announce Type: new Abstract: Understanding 3D scenes is fundamental to embodied intelligence, requiring joint reasoning over heterogeneous information from multiple modalities, incl
arXiv:2608.04415v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to detect unsafe content. A common approach is to combine judgments from a panel of models to correct
arXiv:2608.05033v1 Announce Type: cross Abstract: Sparse matrix kernels are fundamental to scientific computing, graph analytics, and machine learning. Their GPU performance depends strongly on the in
arXiv:2608.04075v1 Announce Type: cross Abstract: Accurate traffic forecasting is essential for proactive resource management in edge computing, where service demand evolves dynamically across both sp
arXiv:2608.04084v1 Announce Type: cross Abstract: Mixture-of-experts (MoE) networks pursue specialization through learned routers, gates, and load-balancing losses, yet at matched total-parameter budg
arXiv:2608.04962v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training improves the reasoning capabilities of large language models, but autoregressive rollout generation remains
arXiv:2608.04074v1 Announce Type: cross Abstract: Long-context LLM decoding reads the key-value (KV) cache at every step. Loading it takes longer than computing attention over it, so throughput is ban
arXiv:2608.05078v1 Announce Type: new Abstract: Embodied navigation requires an agent to make sequential decisions from egocentric observations in a physical environment. Existing Artificial Neural Ne
arXiv:2608.04764v1 Announce Type: new Abstract: X-ray computed tomography (CT) suffers from severe metal artifacts when high-attenuation objects such as dental fillings or orthopedic implants are pres
arXiv:2608.05126v1 Announce Type: new Abstract: Spoken Language Understanding (SLU) is the core component of task-oriented dialogue systems and a pivotal link in achieving seamless human-agent interac
arXiv:2608.04419v1 Announce Type: cross Abstract: On-policy distillation (OPD) provides dense teacher supervision on student-generated trajectories, but standard reverse-KL training can assign insuffi
arXiv:2608.04425v1 Announce Type: new Abstract: Subtask labels decompose a long-horizon manipulation demonstration into shorter semantic segments for policy training and evaluation. Natural language d
arXiv:2608.05127v1 Announce Type: cross Abstract: Achieving local differential privacy in distributed optimization while maintaining low communication cost remains challenging. Existing vector quantiz
arXiv:2511.12265v2 Announce Type: replace-cross Abstract: Deep Neural Networks (DNNs) remain vulnerable to diverse adversarial perturbations, motivating multi-attack adversarial training (AT) for impr
arXiv:2608.05112v1 Announce Type: cross Abstract: The Subspace Constrained Mean Shift (SCMS) algorithm is a popular nonparametric method for extracting density ridges, which serve as a low-dimensional
arXiv:2608.04934v1 Announce Type: new Abstract: Training LLM agents commonly relies on supervised fine-tuning from expert trajectories or online reinforcement learning over human-specified tasks with
arXiv:2608.04600v1 Announce Type: new Abstract: As robotic systems become increasingly complex, generating control firmware from structural description files has emerged as a promising paradigm for re
arXiv:2608.04811v1 Announce Type: new Abstract: Structured pruning enhances the efficiency of deep neural networks (DNNs) by eliminating groups of parameters during inference. Previous methods mostly
arXiv:2608.04049v1 Announce Type: cross Abstract: The principle of Occam's razor, which instructs us to prefer simplicity in inductive inference, has attracted much scrutiny both in the philosophy of
arXiv:2608.04887v1 Announce Type: new Abstract: On-policy distillation (OPD) has become an effective approach for consolidating multiple task-specialized image generation models into a single student.
arXiv:2608.05006v1 Announce Type: new Abstract: Metamodels are instrumental in reducing the computational burden associated with nested reliability analyses and optimization loops in Performance-Based
arXiv:2608.04265v1 Announce Type: cross Abstract: Evaluations of LLM planning agents largely ask whether a task succeeds or a declared plan is followed. In strategic cyber-physical systems, a stronger
arXiv:2603.03589v3 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) transform how machine learning (ML) pipelines are developed and evaluated. LLMs enable a new t
arXiv:2608.04904v1 Announce Type: new Abstract: Multilingual large language models exhibit substantial performance differences across languages, while existing adaptation methods often require paramet