Model Detail
Salience-1.5-Pro
—Salience-1.5-Pro is a code generation model with 18.0B parameters released by vectionlabs. The model is registered under the image-text-to-text pipeline tag on Hugging Face, distributed under the permissive apache-2.0 license.
Salience-1.5-Pro 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.
Salience-1.5-Pro 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.
The Sum of All Summaries: PROPALIGN for Graded Proposition Salience Evaluation
arXiv:2610.19387v1 Announce Type: new Abstract: Identification and ranking of salient propositions in documents is indirectly involved in many AI tasks, but few papers define proposition salience scores clearly, make diverse data available, or evaluate models directly on the task. This paper propose
Robust Is Salient: An Informed Adversary Moves the Optimal Signal onto the Salience Pole
arXiv:2610.00233v1 Announce Type: cross Abstract: When an informed adversary shares the audience of a constrained signalling channel, the signal that best protects the truth is the signal that best describes it. On 108 confirmatory items, the adversary-robust optimum aligns exactly with the salience
Do we need to answer that question? Salience and Answerability of Potential Questions in Naturalistic Dialogue
arXiv:2609.31130v1 Announce Type: new Abstract: We empirically investigate Question Under Discussion based modelling in naturalistic dialogue by studying whether the salience of generated potential questions predicts their subsequent resolution. Building on Wu et al. (2024), we construct a dataset o
Adversarial Attacks on Online Handwriting using Salience-based Temporal Editing
arXiv:2607.12500v2 Announce Type: replace Abstract: Deep learning models for online handwriting recognition have been shown effective and are increasingly deployed in practical applications. However, their vulnerability to adversarial attacks is still a challenge. Existing adversarial methods are pr
SALT: Salience-Aware Lexical Trie for Long-Context Compression
arXiv:2607.17486v2 Announce Type: replace-cross Abstract: As large language models (LLMs) process increasingly longer prompts, computation and KV-cache memory costs have emerged as major bottlenecks in inference systems. Existing input-level prompt compression methods address this, but rank each sen
Prox: Training-Free FFN Activation Sparsity via Approximate Intermediate-Channel Salience in LLMs
arXiv:2607.27591v1 Announce Type: cross Abstract: Feed-forward networks (FFNs) dominate memory traffic and computation in large language model (LLM) inference, making them a primary target for activation sparsification. However, existing training-free methods suffer substantial model-quality degrada
