Knowledge catalogue
arXiv:2601.18116v2 Announce Type: replace Abstract: We argue that multi-document reasoning is constrained not only by how much text a model can read, but also by how limited query-time evidence budget
arXiv:2605.27681v1 Announce Type: new Abstract: Alignment faking (AF) refers to a model strategically complying with a training objective to avoid behavioural modification while preserving its deploym
arXiv:2605.28508v1 Announce Type: new Abstract: Existing AI evaluation practices often fail to capture how systems actually perform in low-resource environments, where operational constraints shape us
arXiv:2604.00913v2 Announce Type: replace-cross Abstract: 2D assembly diagrams are often abstract and hard to follow, creating a need for intelligent assistants that can monitor progress, detect error
arXiv:2605.27407v1 Announce Type: cross Abstract: Evaluating fairness in Spiking Neural Networks (SNNs) demands rigorous benchmarks that reflect real-world complexities, yet existing assessments remai
arXiv:2605.28103v1 Announce Type: new Abstract: We present a unified experiment, analysis, and benchmark study of multivariate time-series (MTS) anomaly detection. Ten family-representative detectors
arXiv:2605.27796v1 Announce Type: cross Abstract: Ultrasound is widely used in obstetric care due to its safety, accessibility, and real-time imaging. However, interpretation remains operator-dependen
arXiv:2605.27492v1 Announce Type: cross Abstract: LLM agents are rapidly evolving from coding assistants into autonomous software engineering systems. However, existing evaluation methodologies remain
arXiv:2605.28183v1 Announce Type: cross Abstract: We introduce the BenGER (Benchmark for German Law) dataset for evaluating LLM systems on subsumption-based legal reasoning in German law. The BenGER d
arXiv:2605.28301v1 Announce Type: new Abstract: Chain-of-thought (CoT) distillation trains a smaller model to imitate a teacher's reasoning trace, but it is typically evaluated by final-answer metrics
arXiv:2605.28131v1 Announce Type: new Abstract: We revisit punctuation-aware tree binarization for constituency parsing and ask whether dependency-induced headedness improves binary parser supervision
arXiv:2605.28707v1 Announce Type: new Abstract: Critical decision-making in socially consequential spaces is increasingly involving AI systems at varying capacities. Yet, despite the ubiquity of auton
arXiv:2605.28812v1 Announce Type: cross Abstract: A primary bottleneck in contact-rich manipulation is the difficulty of collecting real-world data. Sim-to-real reinforcement learning offers a scalabl
arXiv:2605.28004v1 Announce Type: new Abstract: GraphRAG extends retrieval-augmented generation by organizing corpora as explicit knowledge graphs, enabling graph-based retrieval for complex question
arXiv:2502.05242v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are becoming increasingly capable, but the mechanisms of their thinking and decision-making processes remain uncl
arXiv:2605.27715v1 Announce Type: new Abstract: Large reasoning models (LRMs) achieve strong mathematical reasoning performance in English, but remain much less reliable in many low- and medium-resour
arXiv:2605.28729v1 Announce Type: cross Abstract: Robustness of neural networks is commonly quantified via local or global Lipschitz constants. However, Lipschitz continuity can be overly coarse or ov
arXiv:2509.23074v3 Announce Type: replace-cross Abstract: In the era of increasingly complex AI models for time series forecasting, progress is often measured by marginal improvements on benchmark lea
arXiv:2605.27464v1 Announce Type: cross Abstract: AR smart glasses need continuous behavioral context to offer proactive assistance, yet their most practical always-on sensor, the head-mounted Inertia
arXiv:2605.28465v1 Announce Type: new Abstract: Divergent thinking is a core dimension of creativity, yet existing evaluations of Large Language Models (LLMs) treat them as single-turn text generation
arXiv:2605.28022v1 Announce Type: new Abstract: LLMs for code generation are commonly evaluated in repeated-sampling settings using Pass@k, where multiple candidate programs are executed against unit
arXiv:2605.28051v1 Announce Type: new Abstract: Visual token pruning reduces the computational cost of Vision-Language Models (VLMs) by removing redundant visual tokens. Existing methods typically rel
arXiv:2605.28780v1 Announce Type: new Abstract: Vision classifiers can exploit spurious correlations, achieving high in-distribution accuracy yet failing under distribution shift. Existing approaches
arXiv:2605.28450v1 Announce Type: cross Abstract: Visual data from the Web power image classifiers, which often underpin many web services, such as recommendation and content moderation. However, the
arXiv:2605.28444v1 Announce Type: new Abstract: Fine-tuning large-scale pre-trained models is a recent prevalent paradigm for adapting general representations to specialized tasks. However, when a new
arXiv:2603.10961v2 Announce Type: replace Abstract: Wearable accelerometers enable large-scale health monitoring, yet learning robust human-activity representations has been constrained by scarce labe
arXiv:2605.27380v1 Announce Type: cross Abstract: Cross-lingual biomedical entity linking (BEL) maps mentions in any language to unique identifiers in a biomedical knowledge base (KB), supporting clin
arXiv:2605.28739v1 Announce Type: cross Abstract: Tabular data in knowledge-rich domains often carries a latent prior in the form of Boolean implication relationships (BIRs) between pairs of features.
arXiv:2605.27480v1 Announce Type: cross Abstract: Large language model (LLM) serving creates environmental impacts beyond carbon and water, including ecosystem damage through biodiversity-related path
arXiv:2605.28067v1 Announce Type: new Abstract: The remarkable generation quality of modern diffusion models often comes at the cost of massive parameter counts, which necessitate server-side inferenc
arXiv:2605.28632v1 Announce Type: cross Abstract: Cryptographic watermarking is a leading defense for attributing text generated by large language models (LLMs). Existing schemes, including KGW, Unigr
arXiv:2605.28392v1 Announce Type: new Abstract: This study proposes a bound-constrained sparse representation (BC-SR) framework for electrical impedance tomography (EIT), aimed at improving conductivi
arXiv:2605.27969v1 Announce Type: new Abstract: Post-trained language-model assistants are often optimized to avoid under-answering, encouraging complete, helpful, cautious, and proactive responses. W
arXiv:2605.27737v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly attractive for multimodal quality assessment, but their default reliance on autoregressive text generatio
arXiv:2605.28028v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) is widely used for training reasoning models, but updating all sampled completions in each group incurs substa
arXiv:2605.28438v1 Announce Type: new Abstract: Automatic Speech Recognition (ASR) systems are commonly evaluated using aggregate metrics such as Word Error Rate (WER), which do not capture the lingui
arXiv:2605.28488v1 Announce Type: cross Abstract: We study inference in stochastic block models (SBMs) through the lens of optimal transport (OT). We first establish that maximum likelihood variationa
arXiv:2605.28070v1 Announce Type: new Abstract: We highlight a failure mode of large reasoning models on questions with insufficient information: models may recognize that a problem is under-specified
arXiv:2605.27962v1 Announce Type: new Abstract: This paper describes our approach for the 8th UG2+ Workshop (CVPR 2026) Track~2, which targets semantic segmentation of outdoor scenes degraded by five
arXiv:2605.28234v1 Announce Type: new Abstract: Learning-based radio map estimation (RME) plays a critical role in UAV-assisted wireless sensing, enabling tasks such as coverage prediction and network
arXiv:2605.27383v1 Announce Type: cross Abstract: Spoken Language Models (SLMs) have emerged as a promising paradigm for speech synthesis by bypassing explicit grapheme-to-phoneme pipelines. However,
arXiv:2605.28089v1 Announce Type: new Abstract: BuddyBench introduces a privacy-constrained multi-task benchmark for pediatric social-communication personalization. Unlike existing neurodevelopmental
arXiv:2605.28253v1 Announce Type: new Abstract: The preservation of under-resourced languages requires digital tools and resources shaped by and for their speakers. We present the first dedicated ASR
arXiv:2603.13283v2 Announce Type: replace-cross Abstract: Continuous-time, event-native spiking neural networks (SNNs) operate strictly on spike events, treating spike timing and ordering as the repre
arXiv:2605.27860v1 Announce Type: new Abstract: Retrieval-augmented generation combined with reinforcement learning has shown promise for grounding large language models in trustworthy medical evidenc
arXiv:2605.27473v1 Announce Type: cross Abstract: Estimating how much an intervention helps a given individual the conditional average treatment effect (CATE) is increasingly central to decision-makin
arXiv:2605.28807v1 Announce Type: new Abstract: Agentic AI systems capable of autonomous planning and extended environmental interaction pose a fundamental control problem: how can humans maintain mea
arXiv:2601.10085v2 Announce Type: replace Abstract: Therapeutic dialogue is not a sequence of isolated responses: client goals, motivation, resistance, and therapeutic alliance evolve over time. Yet c
arXiv:2605.28792v1 Announce Type: new Abstract: Electroencephalography (EEG) is a critical, non-invasive method to monitor electrical brain activity. EEGs can span anywhere from a couple seconds to mu
arXiv:2510.05291v2 Announce Type: replace Abstract: As Large Language Models (LLMs) develop stronger multilingual capabilities, their sensitivity to culturally diverse entities becomes increasingly im
arXiv:2603.12344v2 Announce Type: replace Abstract: Molecular Property Prediction (MPP) is a fundamental problem in drug discovery that has recently attracted growing attention. Large Language Models
arXiv:2605.27733v1 Announce Type: new Abstract: Training instabilities such as loss spikes are frequently the result of stochastic gradient noise. Because of rare expressions in language training data
arXiv:2605.27596v1 Announce Type: new Abstract: Recently, there has been increased interest in Small Language Models (SLMs), which are fast, show good performance, and have lower hardware demands than
arXiv:2602.12586v2 Announce Type: replace Abstract: While plan-and-infill decoding in Masked Diffusion Models (MDMs) shows promise for mathematical and code reasoning, performance remains highly sensi
arXiv:2605.28782v1 Announce Type: new Abstract: Discourse particles, such as extit{well} and extit{kind of}, are crucial components that enable LLMs to ``speak'' more like humans. They are used to con
arXiv:2605.28778v1 Announce Type: new Abstract: LLMs' linguistically expressed confidence should faithfully reflect their intrinsic uncertainty. While recent work shows LLMs struggle to use epistemic
arXiv:2605.27416v1 Announce Type: cross Abstract: Quantum Federated Learning (QFL) inherits the core vulnerability of federated optimization to malicious clients, while also introducing an attack surf
arXiv:2605.27764v1 Announce Type: cross Abstract: Recent segmentation models couple large language models (LLMs) with mask decoders to ground complex language expressions into masks, yet their instruc
arXiv:2412.08052v2 Announce Type: replace Abstract: Off-policy evaluation (OPE) is critical for applying contextual bandit algorithms to high-stakes decision-making settings such as healthcare, where
arXiv:2605.27835v1 Announce Type: cross Abstract: We introduce CAREF, a parameter-efficient fine-tuning framework that jointly optimizes predictive accuracy and explanation faithfulness via calibratio