AI 日报hiw3c.com

Contrastive Language Models

Hacker News Top contrastive-lm.notion.site 网页快照
正文为英文,可一键机器翻译(仅首次需要等待)
A System One Model for Fast and Generalizable Decision-Making

Jacky Kwok $^{\dagger}$, Hangoo Kang , Tarun Suresh , Jon Saad-Falcon , Marco Pavone

Christopher Ré , Azalia Mirhoseini :stanford:Stanford University :nvidia:NVIDIA Research

New Architecture, Data Recipe, and Scaling Laws

We introduce Contrastive Language Models (CLMs), a new class of System One model trained with a contrastive learning objective that connects states and actions .

We release CLM-8B , which is pre-trained on 60M Nemotron Q&A pairs , mid-trained on 30M synthetic hard negatives , and post-trained on 1M agentic trajectories .

CLM-8B delivers performance comparable to Jev across computer-use, gaming, and tool-calling tasks, while achieving up to 9× lower latency . With lightweight fine-tuning, CLM-8B also sets a new SOTA on challenging agentic coding benchmarks, including DeepSWE (81.6%) and Terminal Bench 2.1 (87.6%).

We build an ultra-efficient training and serving infra for CLM by disaggregating states and actions , allowing their embeddings to be cached and reused independently.

We establish scaling laws for CLMs and show that the test contrastive loss decreases predictably as a power law in training compute , model size , and dataset size .

Overview

CLM first trains a state encoder and an action encoder on a large-scale dataset with a contrastive objective (InfoNCE), so that each state is pulled toward the ground truth action that was taken and pushed away from all others. The two encoders then serve directly as a zero-shot action classifier .

At deployment, given the current state and a set of candidate actions, CLM scores each action by how well its embedding aligns with the state embedding and selects the highest-scoring action.

Dino Run (CLM vs. Jev)

Zero-shot Evaluation

Across computer-use, gaming, and tool-calling tasks , CLM-8B performs on par with Jev while running up to 9× faster . The speedups are most pronounced when the number of candidate actions is large (e.g., WikiRacing) or when actions can be frequently reused across states (e.g., T-Rex Game).