Knowledge catalogue
arXiv:2509.24728v2 Announce Type: replace Abstract: Latent categorical variables are frequently found in deep learning architectures. They can model actions in discrete reinforcement-learning environm
arXiv:2605.12534v1 Announce Type: cross Abstract: Most work in audio enhancement targets human speech, while bioacoustics is less studied due to noisy recordings and the distinct traits of animal soun
arXiv:2605.12804v1 Announce Type: new Abstract: Positive-negative pressure regulation is critical to soft robotic actuators, enabling large motion ranges and versatile actuation modes. However, achiev
arXiv:2605.13669v1 Announce Type: cross Abstract: This paper proposes a nonlinear guidance strategy capable of intercepting a constant-velocity, non-maneuvering target while strictly satisfying the pr
arXiv:2605.12560v1 Announce Type: cross Abstract: Improving patient outcomes depends on the prompt and accurate diagnosis of brain tumors, but manual MRI scan analysis is still time-consuming and unre
arXiv:2605.13059v1 Announce Type: new Abstract: Clinical diagnostic workups typically follow a modality escalation pathway: after initial clinical evaluation, clinicians begin with routine structural
arXiv:2605.12517v1 Announce Type: cross Abstract: Vision-language models (VLMs) are often deployed on text-only inputs, although they are trained with images. We find that removing the vision modality
arXiv:2605.13283v1 Announce Type: new Abstract: We revisit Byzantine robust distributed estimation for high-dimensional sparse linear models. By combining local ell_1-regularized robust estimation wit
arXiv:2605.13589v1 Announce Type: cross Abstract: Causal discovery, the problem of inferring the direction of causality, is generally ill-posed. We use the language of structural causal models (SCM) t
arXiv:2605.12580v1 Announce Type: new Abstract: Randomized neural networks (RdNNs) enable efficient, backpropagation-free training by freezing randomly initialized input-to-hidden weights, which permi
arXiv:2605.13262v1 Announce Type: new Abstract: Modern SMILES-based chemical language models obtain strong MoleculeNet performance by treating SMILES as generic text and compensating with multi-millio
arXiv:2605.13178v1 Announce Type: cross Abstract: In large vision-language models, visual tokens typically constitute the majority of input tokens, leading to substantial computational overhead. To ad
arXiv:2407.01602v2 Announce Type: replace-cross Abstract: Transformers are extremely successful machine learning models whose mathematical properties remain poorly understood. Here, we rigorously char
arXiv:2605.13306v1 Announce Type: new Abstract: Illuminant estimation aims to infer scene illumination from image measurements despite intrinsic ambiguities between surface reflectance and lighting. M
Nous Research announced that their project reached 150,000 stars on GitHub, a significant milestone reflecting community support and adoption. The announcement celebrated the contributions of their te
arXiv:2605.13362v1 Announce Type: cross Abstract: Computational social choice and algorithmic decision theory offer rich aggregation theory but no end-to-end, polynomial-time process for egalitarian s
arXiv:2605.13337v1 Announce Type: cross Abstract: Security Information and Event Management (SIEM) systems aggregate log data from heterogeneous sources to detect coordinated attacks. Traditional rule
arXiv:2605.13050v1 Announce Type: cross Abstract: Most existing large language models (LLMs) are expensive to adapt after deployment, especially when a task requires newly produced information or nich
Continual Harness proposes an approach to online adaptation for foundation agents that moves beyond traditional gradient-based retraining by introducing a dual-agent architecture (Teacher/Student) wit
arXiv:2605.13415v1 Announce Type: cross Abstract: This paper presents a multi-stage framework for detecting reclaimed slurs in multilingual social media discourse. It addresses the challenge of identi
arXiv:2408.15621v3 Announce Type: replace Abstract: The powerful cooperation of federated learning (FL) and differential privacy~(DP) provides a promising paradigm for the large-scale private clients.
arXiv:2605.13729v1 Announce Type: cross Abstract: Trajectory-controlled human motion generation aims to synthesize realistic human motions conditioned on both textual descriptions and spatial trajecto
arXiv:2605.12951v1 Announce Type: cross Abstract: We propose Coreset-Induced Conditional Velocity Flow Matching (CCVFM), a generative model that augments hierarchical rectified flow with a data-inform
arXiv:2605.12519v1 Announce Type: cross Abstract: Training language models to produce both correct answers and sound reasoning remains an open challenge. Reinforcement learning with verifiable rewards
arXiv:2605.13174v1 Announce Type: cross Abstract: A likelihood-free transport filtering method is proposed based on the couplings between state and observation variables. By exploiting a block-triangu
arXiv:2605.12938v1 Announce Type: cross Abstract: Camera-conditioned video generation requires positional encoding that remains reliable under changes in camera motion, lens configuration, and scene s
arXiv:2605.13686v1 Announce Type: cross Abstract: Medical image-to-image (I2I) translation enables virtual scanning, i.e. the synthesis of a target imaging modality from a source one without additiona
arXiv:2605.05875v2 Announce Type: replace Abstract: Cephalopod pulsed-jet locomotion is not a single isolated expulsion event, but a coordinated cycle involving jet expulsion, passive gliding, and man
arXiv:2605.12906v1 Announce Type: cross Abstract: Data selection during supervised fine-tuning (SFT) can critically change the behavior of large language models (LLMs). Although existing work has stud
arXiv:2603.10305v3 Announce Type: replace Abstract: Machine learning models can represent climate processes that are nonlocal in horizontal space, height, and time, often by combining information acro
arXiv:2605.12952v1 Announce Type: new Abstract: Grad-ECLIP is published at ICML 2024 and represents a new Transformer interpretation technical route (intermediate features-based). First, this paper de
arXiv:2601.00417v3 Announce Type: replace-cross Abstract: Transformer residual streams evolve by additive accumulation: each layer appends a feature update to a shared hidden state, but has no direct
arXiv:2605.13619v1 Announce Type: cross Abstract: Extended depth of field microscopy encodes axial information into a single acquisition through engineered point spread functions, but conventional and
arXiv:2605.13287v1 Announce Type: cross Abstract: Most exploration algorithms search broadly until uncertainty is resolved. When the action space is too large to resolve within budget, practitioners d
arXiv:2509.25781v2 Announce Type: replace Abstract: We address the issue of defining a semantics for deontic argumentation that supports weak permission. Some recent results show that grounded semanti
arXiv:2605.13613v1 Announce Type: new Abstract: In this paper, we discuss a novel continuum robot design that enables the online tuning of the magnetic response at its tip. The proposed method allows
arXiv:2605.12522v1 Announce Type: cross Abstract: Diffusion language models (DLMs) are promising alternatives to autoregressive language models (ARMs), yet the intrinsic differences in their generated
arXiv:2511.01303v2 Announce Type: replace-cross Abstract: We consider the problem of constructing differentially private nonparametric confidence intervals (CIs) for an arbitrary quantity using resamp
arXiv:2602.08920v2 Announce Type: replace Abstract: Uncertainty calibration in pre-trained transformers is critical for their reliable deployment in risk-sensitive applications. Yet, most existing pre
arXiv:2605.12939v1 Announce Type: new Abstract: Recent diffusion- and flow-based VTON methods achieve strong results with pretrained generative models, but their reliance on multi-step sampling incurs
arXiv:2605.13708v1 Announce Type: cross Abstract: Federated learning enables collaborative model training across distributed clients, yet vanilla FL exposes client updates to the central server. Secur
arXiv:2605.12805v1 Announce Type: cross Abstract: MeanFlow enables one-step generation in continuous spaces by learning an average velocity over a time interval rather than the instantaneous velocity
arXiv:2605.12836v1 Announce Type: new Abstract: Continuous diffusion is a natural framework for non-autoregressive generation but has generally lagged behind masked discrete diffusion models (MDMs) on
arXiv:2605.13332v1 Announce Type: new Abstract: Argumentation is an important topic of AI for modelling and reasoning about arguments. In abstract argumentation, we consider directed graphs, so-called
arXiv:2509.13316v4 Announce Type: replace-cross Abstract: Recent interpretability methods have proposed to translate LLM internal representations into natural language descriptions using a second verb
arXiv:2605.13084v1 Announce Type: cross Abstract: Meta-learning has been shown to have better performance than supervised learning for few-shot monolingual spoken word classification. However, the met
arXiv:2605.13418v1 Announce Type: new Abstract: Differentially private optimization suffers from a fundamental geometric mismatch: deep networks have highly anisotropic loss landscapes, yet DP-SGD inj
arXiv:2605.13156v1 Announce Type: new Abstract: Vision-language models (VLMs) have demonstrated remarkable capabilities in bridging visual perception and natural language understanding, enabling a wid
arXiv:2605.13192v1 Announce Type: new Abstract: This paper presents a motion analysis framework for an athlete wearing sport-specific flexible prosthesis based on the soft-rigid hybrid-link system. Su
arXiv:2605.12897v1 Announce Type: new Abstract: DynoJEPP is a factor-graph-based framework that jointly formulates and simultaneously optimizes estimation, prediction, and planning in dynamic environm
arXiv:2605.12705v1 Announce Type: new Abstract: How can we train models whose post-trained capabilities survive subsequent fine-tuning? Rather than focusing on downstream interventions to mitigate for
arXiv:2605.13122v1 Announce Type: new Abstract: Instruction-based image editing (IIE) models have recently demonstrated strong capability in modifying specific image regions according to natural langu
arXiv:2605.13789v1 Announce Type: cross Abstract: Protein structure tokenizers (PSTs) are workhorses in protein language modeling, function prediction, and evolutionary analysis. However, existing PST
arXiv:2505.18604v3 Announce Type: replace Abstract: State-Space Models (SSMs) excel at capturing long-range dependencies with structured recurrence, making them well-suited for sequence modeling. Howe
arXiv:2605.12523v1 Announce Type: cross Abstract: Generative Artificial Intelligence (AI) introduces new considerations for English as a foreign language (EFL) writing pedagogy. This study explores ho
arXiv:2605.13380v1 Announce Type: new Abstract: This work compares three interaction modalities for human-robot collaboration: passive, reactive, and proactive. We studied 18 participants assembling a
arXiv:2601.19979v2 Announce Type: replace-cross Abstract: We develop a reinforcement learning algorithm to study the holographic entropy cone. Given a target entropy vector, our algorithm searches for
arXiv:2512.21075v2 Announce Type: replace-cross Abstract: Deep neural networks have achieved remarkable success in practice, yet a mechanistic understanding of how features evolve during training rema
arXiv:2605.12704v1 Announce Type: cross Abstract: A fundamental challenge in symbolic regression (SR) is efficiently recovering complex mathematical expressions from observational data. Although this
arXiv:2409.02708v2 Announce Type: replace Abstract: Data scarcity poses a serious threat to modern machine learning and artificial intelligence, as their practical success typically relies on the avai