Model Detail
Sage-A1.5
—Sage-A1.5 is a code generation model with 18.0B parameters released by InternScience. The model is registered under the text-generation pipeline tag on Hugging Face, distributed under the permissive apache-2.0 license.
Sage-A1.5 ships with 18.0B parameters. Total weight footprint is approximately 36.0 GB, which is the relevant figure when planning local-inference VRAM. The apache-2.0 license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.
Sage-A1.5 is best fit for code completion, repository-scale Q&A, and pair-programming integrations. It is a less obvious choice for one-shot generation of security-critical code without review. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition
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
SAGE: Sense-Aligned Multimodal Grounding Evaluation with Gloss-Augmented Reasoning
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
SAGE: Semantic Audio Generative Encoder
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
SAGE: Pushing 2-Bit Vector-Quantized LLMs toward Real-World Usability
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
SAGE: Efficient Protected Vision-Language Inference on Smart Glasses
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,
SAGE: Sink-Aware Guided Emphasis for Visual Grounding in Vision-Language Decoders
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
