Model Detail
lift
▲ 6.5%lift is a multimodal model with 4.8B parameters released by datalab-to. The model is registered under the image-text-to-text pipeline tag on Hugging Face, released under the openrail license.
lift ships with 4.8B parameters. Total weight footprint is approximately 9.7 GB, which is the relevant figure when planning local-inference VRAM. Distribution is governed by the openrail license — review the exact terms before commercial deployment.
Downloads of lift have moved +6.5% over the past 24 hours, +1278.5% over the trailing seven days. That puts the model in active uptrend territory; a sustained move of this size usually reflects a recent release, a viral integration, or a benchmark surprise rather than steady-state demand. These numbers are signal, not guarantee — week-over-week download counts on Hugging Face also reflect mirror traffic, CI scrapes, and one-off benchmarking runs.
lift is best fit for mixed text-and-image reasoning tasks such as document understanding. 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.
Safeguard-Conditioned Uplift: Measuring Utility-Risk Frontiers for Dual-Use Biology Assistants
arXiv:2607.13039v1 Announce Type: cross Abstract: Safety evaluations for dual-use biology assistants often measure base-model capability, refusal behavior, or jailbreak success. These metrics miss a deployment question: for a fixed base model, how does the access condition users actually see change
CaLiSym: Learning Symplectic Dynamics of Real-World Systems through Structured Canonical Lifts
arXiv:2607.06824v2 Announce Type: replace-cross Abstract: Physics-informed learning promises data-efficient and stable dynamics prediction, yet its strongest geometric guarantees have largely remained confined to closed conservative systems. This excludes robotic systems of interest, where actuation
A Threshold Exceedance Framework for CBRN Uplift Evaluation in Frontier Language Models
arXiv:2607.12200v1 Announce Type: new Abstract: As frontier language models advance, policymakers and model developers need methods for assessing whether model access materially increases a non-expert actor's ability to plan high-consequence Chemical, Biological, Radiological, or Nuclear (CBRN) misu
TOLiD: Bridging the Architecture Gap in Vision Foundation Model to LiDAR Pretraining via Token Lifting for Distillation
arXiv:2607.10762v1 Announce Type: cross Abstract: Cross-modal distillation from Vision Foundation Models (VFMs) to LiDAR backbones has recently emerged as a self-supervised pretraining strategy that reduces reliance on dense point-wise annotation for 3D scene understanding. However, existing distill
Source-Lifted Flow Matching for Intervenable Multimodal Imitation
arXiv:2607.10206v1 Announce Type: cross Abstract: Flow-matching policies are promising for imitation learning because they model complex multimodal action distributions. However, their stochasticity is largely passive: repeated sampling may yield diverse behaviors, but users cannot directly choose a
RCTs for Frontier AI Governance: Methodological Challenges and Solutions for Human Uplift Studies
arXiv:2603.11001v3 Announce Type: replace-cross Abstract: Human uplift studies, or studies that measure the effects of AI access on human performance via randomized controlled trials (RCT) or similar methodologies, increasingly inform frontier AI governance and deployment decisions. While RCT method
