Knowledge catalogue
arXiv:2605.28659v1 Announce Type: new Abstract: Biological foundation models have shown strong performance in single-cell representation learning by applying transformer architectures directly to gene
arXiv:2602.06054v3 Announce Type: replace Abstract: Assessing originality in AI research is arguably the most consequential yet least reliable step in peer review. Reviewer judgments of originality re
arXiv:2605.27752v1 Announce Type: new Abstract: LLM confidence calibration is often evaluated by comparing two signals: token-probability scores and verbalized confidence. These signals are sometimes
arXiv:2512.01970v3 Announce Type: replace Abstract: Does Reinforcement Learning (RL) merely amplify existing skills, or synthesize novel skills? We investigate this question through the lens of Comple
arXiv:2601.08131v4 Announce Type: replace Abstract: Cross-layer reuse of early attention projections can improve optimization and data efficiency, but it creates a structural conflict: the first layer
arXiv:2605.27476v1 Announce Type: cross Abstract: We characterize the pre-softmax attention matrix mathbf{QK^op} in transformers as an associative memory matrix encoding pairwise associations between
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:2605.28004v1 Announce Type: new Abstract: GraphRAG extends retrieval-augmented generation by organizing corpora as explicit knowledge graphs, enabling graph-based retrieval for complex question
arXiv: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:2605.28022v1 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: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:2605.28739v1 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:2605.28392v1 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:2605.28488v1 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:2605.27962v1 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: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: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: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:2605.28778v1 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:2605.28060v1 Announce Type: new Abstract: Explaining the predictions of neural models in clinical NLP remains a significant challenge, especially for complex tasks involving long, unstructured m
arXiv:2605.28111v1 Announce Type: new Abstract: Predicting how a cell will change its transcriptional state under a developmental signal or a genetic perturbation is the computational core of in-silic
arXiv:2605.28034v1 Announce Type: new Abstract: Clark Hash is a small method for storing neural embeddings in less space. It normalizes each database vector, applies a deterministic sparse signed John
This year, there’s been a wave of notable energy companies going public via IPO in the US. The solar and battery company Solv Energy went public in February, to the tune of $6 billion. X-energy, which
arXiv:2605.27561v1 Announce Type: cross Abstract: Introduction. Early detection of malignant skin lesions is critical for prognosis, yet dermatologist shortages in Russian regions limit screening cove
arXiv:2605.27852v1 Announce Type: cross Abstract: Unified and scalable Transformers have recently achieved remarkable success in modeling diverse phenomena traditionally associated with computer graph
arXiv:2605.28484v1 Announce Type: new Abstract: Composing finite-state transducers (FSTs) for context-dependent morphophonological rules -- consonant gradation, vowel harmony, possessive suffix assimi
arXiv:2605.28304v1 Announce Type: new Abstract: Composing autoregressive models remains a core challenge in understanding how large language models can combine behaviors or skills learned across tasks
arXiv:2602.18982v4 Announce Type: replace Abstract: Common deep learning approaches for antibody engineering focus on modeling the marginal distribution of sequences. By treating sequences as independ
arXiv:2411.13479v4 Announce Type: replace-cross Abstract: We consider conformal prediction for multivariate data and focus on hierarchical data, where some components are linear combinations of others
arXiv:2605.27811v1 Announce Type: new Abstract: Auto-bidding systems aim to maximize advertiser value over long horizons under budget constraints and ratio targets such as cost-per-acquisition, yet fu
arXiv:2605.27975v1 Announce Type: new Abstract: Generative models, including diffusion models, are increasingly used as foundation models and adapted through sequential fine-tuning, making continual l
arXiv:2605.28742v1 Announce Type: new Abstract: Language models can use verifiable rewards to improve at a wide variety of reasoning tasks. However, both parametric (e.g. RLVR) and non-parametric (e.g
arXiv:2605.24302v2 Announce Type: replace Abstract: Egocentric action recognition is a challenging task due to erratic camera motion, frequent hand occlusion, and the difficulty of maintaining consist
arXiv:2605.28763v1 Announce Type: new Abstract: Interactive 3D assets used in games and simulation are typically decomposed into specific semantic parts to support animation, physics, and scripted beh
arXiv:2605.27800v1 Announce Type: new Abstract: CASTLE 2026 asks 185 multiple-choice questions over 600+ hours of synchronized multi-view egocentric video. We explore two approaches on top of a shared
arXiv:2512.00252v4 Announce Type: replace-cross Abstract: Data assimilation (DA) is a cornerstone of scientific and engineering applications, combining model forecasts with sparse and noisy observatio
arXiv:2605.27483v1 Announce Type: cross Abstract: Despite theoretical promise, debate as a scalable oversight protocol has produced mixed empirical results: gains in some settings, and null effects in
arXiv:2605.28340v1 Announce Type: cross Abstract: The use of residential photovoltaics has increased dramatically in recent years. With battery systems becoming more affordable, the optimal operation
arXiv:2602.06880v2 Announce Type: replace Abstract: Adaptive methods like Adam have become the extit{de facto} standard for large-scale vector and Euclidean optimization due to their coordinate-wise a
arXiv:2605.28697v1 Announce Type: cross Abstract: Speckle tracking echocardiography (STE) is the clinical standard for myocardial strain estimation. Despite good performance on global strain (GLS), it
arXiv:2605.27991v1 Announce Type: cross Abstract: Deep neural networks (DNNs) have achieved remarkable empirical success, yet their training dynamics remain understood mainly from optimization rather
arXiv:2605.27809v1 Announce Type: new Abstract: Despite recent progress in backdoor attacks, existing methods remain susceptible to post-training defenses that erase the backdoor through fine-tuning o
arXiv:2605.27661v1 Announce Type: new Abstract: We describe our preliminary design of a real-time asynchronous event-based monocular odometry for planetary exploration. Operating under strict computat
arXiv:2605.28355v1 Announce Type: new Abstract: The boundary between real and diffusion-generated time series is becoming increasingly difficult to draw, yet detection in this domain remains underexpl
arXiv:2605.27656v1 Announce Type: cross Abstract: Online recruitment platforms require recommendation methods capable of retrieving relevant job opportunities from large and heterogeneous collections
DiffusionBlocks is a novel training method that enables neural networks to be trained sequentially, one architectural block at a time, rather than end-to-end. This approach, developed by Sakana AI, le
arXiv:2602.16872v2 Announce Type: replace Abstract: Optical Character Recognition (OCR) is a fundamental task for digitizing information, serving as a critical bridge between visual data and textual u
arXiv:2509.04192v2 Announce Type: replace Abstract: A Markov logic network (MLN) M determines a probability distribution P_n^M on the set mathbf{W}_n of structures, or ``possible worlds'', with domain
arXiv:2605.28269v1 Announce Type: new Abstract: Dynamic topic modeling is widely used to analyze evolving trends in scientific literature, medical records, and social media. Traditional topic models r
arXiv:2510.11170v2 Announce Type: replace-cross Abstract: With the rise of reasoning language models and test-time scaling methods as a paradigm for improving model performance, substantial computatio
arXiv:2605.28272v1 Announce Type: new Abstract: Real-time synthesis of high-fidelity 3D character motion from audio is a pivotal component for next-generation interactive avatars and virtual assistant
Economy then vs now: GDP growth: 2024 2.8% 2026 1.6% Inflation: 2024 2.9% 2026 3.8% Wages: 2024 rising faster than inflation 2026 rising slower than inflation Unemployment rate: 2024 4% 2026 4.3% Jobs
arXiv:2605.28409v1 Announce Type: new Abstract: Post-training using online reinforcement learning (RL) is an important training step for LLMs, including code-generating models. However, online RL for