33 articles mentioning Sage-A1.5
arXiv:2610.28578v1 Announce Type: new Abstract: In this report, we introduce Sage-A1.5, a 35B Mixture-of-Experts agentic model that builds on A1 to advance long-horizon problem solving through adaptive capability composition. Compared with A1, Sage-A1.5 learns not only to solve individual tasks, but
arXiv:2610.31838v1 Announce Type: new Abstract: This paper introduces Sense-Aligned Grounding Evaluation (SAGE), a unified 10-candidate image-selection benchmark that reformulates VWSD, VerSe, and WikiDiverse into a shared term-centric protocol covering noun-, verb-, and entity-centered grounding. S
arXiv:2609.32755v3 Announce Type: replace-cross Abstract: Audio autoencoders compress waveforms into compact latent representations that serve as the interface between raw audio and downstream models. Current systems navigate a three-way trade-off between reconstruction quality, semantic structure o
arXiv:2610.14745v1 Announce Type: new Abstract: Extreme low-bit weight-only quantization is an effective approach to reducing the deployment costs of large language models. Below 3 bits, scalar quantization often suffers severe accuracy loss, while vector quantization (VQ) better preserves accuracy
arXiv:2610.14089v1 Announce Type: cross Abstract: Smart glasses are a promising platform for vision-language assistants, but private split inference remains expensive: protecting visual representations before transmission does not remove the cost of on-device vision encoding, wide protected tokens,
arXiv:2610.11469v1 Announce Type: cross Abstract: Recent large vision-language models (VLMs) pair a visual encoder with a large language model (LLM) and perform well on diverse image-text tasks, yet their reliability is often limited by decoder attention pathologies that suppress visual evidence and
arXiv:2610.08093v1 Announce Type: cross Abstract: Developing reliable models for clinical tasks, such as Medical Question Answering (QA), is severely constrained by the limited availability of high-quality, expert-annotated training data. This challenge is exacerbated by stringent privacy requiremen
arXiv:2610.01788v1 Announce Type: new Abstract: As machine learning increasingly relies on public, untrusted data sources, data poisoning attacks, which inject malicious examples into training data to induce misclassification of a chosen target, pose a growing threat. Existing defenses either assume
arXiv:2609.35790v2 Announce Type: replace-cross Abstract: While neural theorem provers have achieved impressive milestones in formal mathematics, they largely operate on the assumption that faithful Lean 4 formal statements are already provided. Translating informal natural language into a formal la
arXiv:2609.39635v1 Announce Type: cross Abstract: Given a target dataset, such as faces with eyeglasses, and a background dataset, such as faces without, contrastive analysis separates \textit{salient} factors specific to the target from \textit{common} content shared by both. We aim for salient rep
arXiv:2609.35794v1 Announce Type: cross Abstract: Just as Socrates recognized the limits of his own knowledge, Retrieval-Augmented Language Models (RALMs) should learn to abstain when the retrieved evidence cannot support a reliable response. Existing approaches largely rely on monolithic LLMs to ha
arXiv:2609.36043v1 Announce Type: new Abstract: Large Language Model (LLM)-based agents increasingly self-evolve by editing a persistent skill document that encodes their workflow, tool-use rules, and decision logic. This loop has two steps, an optimizer that proposes a candidate edit and a gate tha
arXiv:2609.31082v1 Announce Type: new Abstract: Knowing where species occur is fundamental for biodiversity research and conservation. Species distribution models (SDMs) link species observations to environmental conditions to estimate their spatial distribution. However, accuracy varies with the un
arXiv:2609.30703v1 Announce Type: cross Abstract: Spatial misregistration and cross-modal discrepancies often cause ghosting, structural blurring, and content imbalance in RGB-T fusion. Existing methods typically decouple appearance adaptation, geometric alignment, and information fusion, limiting d
arXiv:2609.30192v1 Announce Type: new Abstract: Long-horizon reasoning remains a central challenge for large language models (LLMs) under sparse-reward regimes. We argue that this brittleness arises from two biases induced by complex reasoning spaces: an exploration bias, where models are drawn towa
arXiv:2609.23773v1 Announce Type: cross Abstract: Decentralised federated learning replaces server aggregation with peer-to-peer model exchange, making collaborator selection a local decision under uncertainty. Fixed probe budgets waste effort on easy choices yet fall short when peers are hard to di
arXiv:2609.20829v1 Announce Type: new Abstract: Grant reviewers must apply detailed criteria to application forms, budgets, and supporting documents while producing assessments that colleagues can inspect. We present SAGE, Schema-Guided Aspect-Based Grant Evaluation, a system that translates a grant
arXiv:2609.17775v1 Announce Type: new Abstract: Enterprise guideline documents mix narrative text, complex tables, and embedded images, and converting them into structured work artifacts still takes two to three days of manual effort each. Current language and vision-language models extract from suc
arXiv:2609.12455v1 Announce Type: new Abstract: Automated machine learning (AutoML) is reshaping data-driven science and industrial practice, and as large language models are introduced into AutoML, pipeline reliability becomes as important as automation efficiency. However, existing AutoML still st
arXiv:2511.18493v5 Announce Type: replace-cross Abstract: The significant variability in cell size and shape continues to pose a major obstacle in computer-assisted cancer detection on gigapixel Whole Slide Images (WSIs), due to cellular heterogeneity. Current CNN-Transformer hybrids use static comp
arXiv:2609.06611v1 Announce Type: cross Abstract: Assessing the literary quality of narratives requires evaluating interpretive dimensions (cultural representation, emotional depth, and philosophical engagement) that existing NLG metrics cannot measure. We introduce SAGE, a six-layer evaluation fram
arXiv:2609.01051v1 Announce Type: new Abstract: Spurious correlations pose a significant challenge to the robustness of modern machine learning. The inherent imbalance in dataset distributions often leads traditional Empirical Risk Minimization (ERM) models to rely on majority spurious attributes fo
arXiv:2609.00434v1 Announce Type: new Abstract: Evaluating task-oriented dialogue agents requires judging not merely whether a reply reads well but whether each turn advances the underlying workflow state correctly--a distinction conventional holistic LLM judges can miss because they evaluate the av
arXiv:2608.16921v3 Announce Type: replace-cross Abstract: Effective cybersecurity operations require timely and accurate analysis of large-scale heterogeneous security information; however, analysts increasingly struggle with information overload, alert fatigue, and time-constrained decision-making.
arXiv:2608.26829v1 Announce Type: new Abstract: Time series forecasting models operate on raw numerical sequences, lacking the semantic knowledge that domain experts implicitly leverage, such as the physical meaning of each variable, its statistical behavior, and its temporal dynamics. Recent effort
arXiv:2608.24011v1 Announce Type: cross Abstract: Chinese ancient document understanding demands complex visual, linguistic, and historical reasoning. Current Large Vision-Language Models (LVLMs) typically rely on an opaque, single-pass generation paradigm, often producing overconfident and weakly g
arXiv:2606.18902v2 Announce Type: replace Abstract: Context engineering has emerged as a primary lever for improving AI systems without parameter updates. Recent work showing that textual gradients do not function as real gradients motivates treating automatic prompt optimization (APO) as black-box
arXiv:2607.22926v1 Announce Type: new Abstract: High-impact generative AI makes catastrophic misuse a lifecycle-control problem, not merely a prompt-filtering problem. SAGE is a safety-first, authorization-separated architecture in which credible catastrophic-enablement risk constrains admissibility
arXiv:2607.17973v1 Announce Type: new Abstract: Latent world models have emerged as a powerful planning paradigm by learning action-conditioned predictive dynamics and using them as internal simulators to imagine and evaluate candidate action sequences. However, as the planning horizon grows, perfor
arXiv:2607.00454v1 Announce Type: new Abstract: Agricultural advisory systems face a fundamental tension: static agronomic guidelines offer consistent, evidence-based recommendations, yet remain blind to in-season variability and dynamic uncertainties. Recent advisory systems powered by LLMs are lia
arXiv:2504.07385v3 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) become increasingly used for question-answering (QA), relying on static, pre-annotated references for evaluation poses significant challenges in cost, scalability, and completeness. Meanwhile, using LLMs themse
arXiv:2606.19659v1 Announce Type: new Abstract: On-policy distillation (OPD) improves student models by training them on trajectories induced by their own policy, making it a promising approach for mitigating exposure bias in agent training. However, most OPD studies focus on single-turn settings, w
arXiv:2606.18309v1 Announce Type: cross Abstract: Large Language Model (LLM) unlearning aims to remove undesirable knowledge or behaviors while preserving retained capabilities. Current unlearning methods all involve a trade-off between unlearning and retention. We have found that the retention acti