Knowledge catalogue
arXiv:2604.22967v1 Announce Type: cross Abstract: Trust Region Bayesian Optimization (TuRBO) is an effective strategy for alleviating the curse of dimensionality in high-dimensional black-box optimiza
arXiv:2505.02922v3 Announce Type: replace Abstract: Recent large language models (LLMs) are rapidly extending their context windows, yet inference throughput lags due to increasing GPU memory and band
arXiv:2604.23283v1 Announce Type: new Abstract: Current LLM agents operate under an implicit but universal assumption: execution is a transaction -- the user submits a request, the agent works in isol
arXiv:2604.23443v1 Announce Type: new Abstract: Stochastic sampling strategies are widely adopted in large language models (LLMs) to balance output coherence and diversity. These heuristics are often
arXiv:2603.25562v2 Announce Type: replace-cross Abstract: On-policy distillation (OPD) is increasingly used in LLM post-training because it can leverage a teacher model to provide dense supervision on
arXiv:2604.24300v1 Announce Type: new Abstract: Current evaluations of spatial intelligence can be systematically invalid under modern vision-language model (VLM) settings. First, many benchmarks deri
arXiv:2604.22981v1 Announce Type: new Abstract: Reward models in RLHF are trained to score only the final token of a response - a choice that discards rich signal from every intermediate position and
arXiv:2604.24198v1 Announce Type: cross Abstract: Process Reward Models (PRMs) have achieved remarkable success in augmenting the reasoning capabilities of Large Language Models (LLMs) within static d
arXiv:2604.24153v1 Announce Type: new Abstract: Current AI systems increasingly operate in contexts where their outputs directly trigger real-world actions. Most existing approaches to AI safety, risk
arXiv:2604.23875v1 Announce Type: cross Abstract: Noisy labels are a pervasive challenge in medical image classification, where annotation errors arise from inter-observer variability and diagnostic a
arXiv:2603.04603v2 Announce Type: replace-cross Abstract: We present a risk-aware formalism for evaluating system trajectories in the presence of uncertain interactions between the system and its envi
arXiv:2604.07533v2 Announce Type: replace-cross Abstract: Time Slotted Channel Hopping (TSCH) is a widely adopted Media Access Control (MAC) protocol within the IEEE 802.15.4e standard, designed to pr
arXiv:2604.23073v1 Announce Type: new Abstract: Vision-language-action (VLA) models can learn to perform diverse manipulation skills 'out of the box,' but achieving the precision and speed that real-w
arXiv:2603.20711v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models are mainstream in embodied intelligence but face high inference costs. Edge-Cloud Collaborative (ECC) depl
arXiv:2604.23933v1 Announce Type: new Abstract: Developing robust and clinically reliable EEG biomarkers requires evaluation frameworks that explicitly address cross population generalization in multi
arXiv:2604.23323v1 Announce Type: new Abstract: Audio-text retrieval enables semantic alignment between audio content and natural language queries, supporting applications in multimedia search, access
arXiv:2604.24163v1 Announce Type: new Abstract: Robustness is a long-overlooked problem in deepfake detection. However, detection performance is nearly worthless in the real world if it suffers under
arXiv:2604.24036v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) have enhanced grounding capabilities in general scenes, their robustness in crowded scenes remains undere
arXiv:2511.09242v2 Announce Type: replace-cross Abstract: The paper studies a geometrically robust least-squares problem that extends classical and norm-based robust formulations. Rather than minimizi
arXiv:2604.22888v1 Announce Type: cross Abstract: Agent skills introduce a new and more severe form of indirect injection for LLM agents: unlike traditional indirect prompt injection, attackers can hi
arXiv:2604.23577v1 Announce Type: new Abstract: Serving diverse NLP workloads with large language models is costly: at one enterprise partner, inference costs exceeded $200K/month despite over 70% of
arXiv:2604.23783v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) grounds language models in external evidence, but multi-hop question answering remains difficult because iterativ
arXiv:2604.23296v1 Announce Type: cross Abstract: Aspect Sentiment Quad Prediction (ASQP) has seen significant advancements, largely driven by the powerful semantic understanding and generative capabi
arXiv:2604.23648v1 Announce Type: new Abstract: Convex free regions provide a structured and optimization-friendly representation of collision-free space for robot navigation in unknown and cluttered
arXiv:2603.13502v2 Announce Type: replace Abstract: Wirelessly-connected robotic systems empower robots with real-time intelligence by leveraging remote computing resources for decision-making. Howeve
arXiv:2604.24368v1 Announce Type: new Abstract: Generating high-fidelity synthetic tabular data remains a critical challenge for enhancing data availability in privacy-sensitive and low-resource domai
arXiv:2509.25358v4 Announce Type: replace Abstract: Large-scale robot learning has made progress on complex manipulation tasks, yet long horizon, contact rich problems, especially those involving defo
arXiv:2603.20738v2 Announce Type: replace Abstract: Cross-subject EEG-to-image retrieval for visual decoding is challenged by subject shift and hubness in the embedding space, which distort similarity
arXiv:2512.15930v2 Announce Type: replace-cross Abstract: Intrinsically disordered proteins (IDPs) represent crucial therapeutic targets due to their significant role in disease -- approximately 80% o
arXiv:2604.23437v1 Announce Type: cross Abstract: The global financial ecosystem confronts a critical asymmetry: while fraud syndicates operate as borderless, distributed networks, banking institution
arXiv:2602.04120v2 Announce Type: replace-cross Abstract: Though Explainable AI (XAI) has made significant advancements, its inclusion in edge and IoT systems is typically ad-hoc and inefficient. Most
arXiv:2604.24708v1 Announce Type: cross Abstract: Training large neural networks with data-parallel stochastic gradient descent allocates N GPU replicas to compute effectively identical updates -- a p
arXiv:2604.23255v1 Announce Type: cross Abstract: Research shows that dialogue, the interactive process through which participants articulate their thinking, plays a central role in constructing share
arXiv:2604.23841v1 Announce Type: cross Abstract: Efficiently solving the Job Shop Scheduling Problem in real-world industrial applications requires policies that are both computationally lean and top
arXiv:2604.05013v2 Announce Type: replace-cross Abstract: Current LLM coding agents are predominantly trained on composite benchmarks (e.g., bug fixing), which often leads to task-specific overfitting
arXiv:2604.23150v1 Announce Type: cross Abstract: Most recent state-of-the-art (SOTA) large language models (LLMs) use Mixture-of-Experts (MoE) architectures to scale model capacity without proportion
arXiv:2604.24416v1 Announce Type: cross Abstract: Speech-only spoken language models (SLMs) lag behind text and text-speech models in performance, with recent discrete autoregressive (AR) SLMs indicat
arXiv:2604.24514v1 Announce Type: new Abstract: Accurate trajectory prediction is fundamentally challenging due to high scene heterogeneity - the severe variance in motion velocity, spatial density, a
arXiv:2510.24832v2 Announce Type: replace Abstract: Using Reinforcement Learning with Verifiable Rewards (RLVR) to optimize Large Language Models (LLMs) can be conceptualized as progressively editing
arXiv:2510.12826v2 Announce Type: replace-cross Abstract: As large language model (LLM) agents are deployed autonomously in diverse contexts, evaluating their capacity for strategic deception becomes
arXiv:2604.22948v1 Announce Type: new Abstract: History-dependent sampling can reduce long-run Monte Carlo variance by discouraging redundant revisits, but existing schemes typically encode history th
arXiv:2512.23213v3 Announce Type: replace-cross Abstract: We propose LLM-PeerReview, an unsupervised LLM Ensemble method that selects the most ideal response from multiple LLM-generated candidates for
arXiv:2603.29928v2 Announce Type: replace Abstract: Tabular foundation models such as TabPFN and TabICL already produce full predictive distributions, yet prevailing regression benchmarks evaluate the
arXiv:2601.03555v2 Announce Type: replace Abstract: Training reliable tool-augmented agents remains a significant challenge, largely due to the difficulty of credit assignment in multi-step reasoning.
arXiv:2604.24372v1 Announce Type: cross Abstract: LLM-guided evolutionary search has emerged as a promising paradigm for automated algorithm discovery, yet most systems track search progress primarily
arXiv:2604.24515v1 Announce Type: new Abstract: Multi-hop Question Answering (MHQA) aims to answer questions that require multi-step reasoning. It presents two key challenges: generating correct reaso
arXiv:2604.22768v1 Announce Type: cross Abstract: Purpose: To design, implement, evaluate, and report on the regulatory requirements of a self-hosted LLM infrastructure for radiology adhering to the p
arXiv:2603.09002v2 Announce Type: replace-cross Abstract: Multi-agent artificial intelligence systems or MAS are systems of autonomous agents that exercise delegated tool authority, share persistent m
arXiv:2604.24339v1 Announce Type: cross Abstract: Recent advances in Vision-Language Models (VLMs) have benefited from Reinforcement Learning (RL) for enhanced reasoning. However, existing methods sti
arXiv:2604.22805v1 Announce Type: cross Abstract: Augmented reality (AR) systems pose unique privacy risks due to their continuous capture of visual data. Existing AR privacy frameworks lack semantic
arXiv:2604.24197v1 Announce Type: cross Abstract: Frontier image generation has moved from artistic synthesis toward synthetic visual evidence. Systems such as GPT Image 2, Nano Banana Pro, Nano Banan
arXiv:2303.14897v4 Announce Type: replace Abstract: Imagining the future trajectory is the key for robots to make sound planning and successfully reach their goals. Therefore, text-conditioned video p
arXiv:2512.12844v2 Announce Type: replace-cross Abstract: Reliable uncertainty quantification is essential for deploying machine learning systems in high-stakes domains. Conformal prediction provides
arXiv:2604.24313v1 Announce Type: cross Abstract: Training large-scale deep neural networks effectively and stably is essential for applying deep learning across various fields. However, conventional
arXiv:2312.15020v4 Announce Type: replace-cross Abstract: Technical debt (TD) refers to the long-term costs associated with suboptimal design or code decisions in software development, often made to m
arXiv:2604.22939v1 Announce Type: cross Abstract: While the next-token prediction (NTP) paradigm enables large language models (LLMs) to express their intrinsic knowledge, its sequential nature constr
arXiv:2509.00747v2 Announce Type: replace-cross Abstract: Learning with physical systems is an emerging paradigm that seeks to harness the intrinsic nonlinear dynamics of physical substrates for learn
arXiv:2508.19652v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) often suffer from visual hallucinations: generating things that are not consistent with visual inputs and language sho
arXiv:2604.23025v1 Announce Type: cross Abstract: Android malware detectors built with machine learning often suffer from temporal bias: models are trained and evaluated without respecting apps' actua
arXiv:2604.24498v1 Announce Type: new Abstract: Modern self-supervised representation learning methods often relies on empirical heuristics that are not theoretically grounded. In this study we propos