Jacky Kwok's banner

Jacky Kwok

@jackyk02 • 6,659 subscribers

Stanford CS PhD | Berkeley EECS

Shorts

Happy to share RSI-top: a framework that helps autonomous research agents escape exploration collapse 📈 RSI-top outperforms OpenEvolve and ShinkaEvolve by up to 15% on kernel optimization tasks and achieves a 77.3% medal rate on MLE-Bench Lite. We developed metrics for retrieving useful past trajectories and proposed 3 diversity control mechanisms that encourage new ideas, perspectives, and starting points when progress stalls. 📄 Blog: Work led by Yuzhen Mao, with incredible collaborators Shayan Talaei and Azalia Mirhoseini

Happy to share RSI-top: a framework that helps autonomous research agents escape exploration collapse 📈 RSI-top outperforms OpenEvolve and ShinkaEvolve by up to 15% on kernel optimization tasks and achieves a 77.3% medal rate on MLE-Bench Lite. We developed metrics for retrieving useful past trajectories and proposed 3 diversity control mechanisms that encourage new ideas, perspectives, and starting points when progress stalls. 📄 Blog: Work led by Yuzhen Mao, with incredible collaborators Shayan Talaei and Azalia Mirhoseini

19,518 views

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Introducing Contrastive Language Model (CLM): an ultra-fast System One Model trained with a contrastive learning objective that connects states and actions. CLM-8B is pre-trained on internet-scale data and delivers up to 9× faster inference than Jev ⚡ while achieving comparable performance across computer-use, gaming, and tool-calling tasks. With lightweight fine-tuning, CLM-8B sets a new SOTA on challenging agentic coding benchmarks, such as DeepSWE (81.6%) and Terminal-Bench 2.1 (87.6%). In contrast, Jev fails to serve as an effective verifier for these long-horizon tasks. We also build an efficient training and serving infra for CLMs by disaggregating states and actions, allowing their embeddings to be cached and reused independently. This substantially reduces inference latency in settings where the state evolves continuously while the action set remains fixed. Finally, 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. 📄 Blog: 💻 Code: 🗣️ Discord: 🤗 Data & Models: More details on CLM’s architecture, data recipe, and scaling laws in the thread below 🧵

Introducing Contrastive Language Model (CLM): an ultra-fast System One Model trained with a contrastive learning objective that connects states and actions. CLM-8B is pre-trained on internet-scale data and delivers up to 9× faster inference than Jev ⚡ while achieving comparable performance across computer-use, gaming, and tool-calling tasks. With lightweight fine-tuning, CLM-8B sets a new SOTA on challenging agentic coding benchmarks, such as DeepSWE (81.6%) and Terminal-Bench 2.1 (87.6%). In contrast, Jev fails to serve as an effective verifier for these long-horizon tasks. We also build an efficient training and serving infra for CLMs by disaggregating states and actions, allowing their embeddings to be cached and reused independently. This substantially reduces inference latency in settings where the state evolves continuously while the action set remains fixed. Finally, 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. 📄 Blog: 💻 Code: 🗣️ Discord: 🤗 Data & Models: More details on CLM’s architecture, data recipe, and scaling laws in the thread below 🧵

1,068,884 views • 1 month ago

CLM-8B can play Terraria now 🎮 Every move and every attack is driven by CLM in real time, ranking candidate actions in milliseconds! 🤗 HuggingFace: 💻 GitHub Code: 🗣️ Discord Channel: Huge thanks to Joshua Leonard for building this and sharing it with the community 🙌

CLM-8B can play Terraria now 🎮 Every move and every attack is driven by CLM in real time, ranking candidate actions in milliseconds! 🤗 HuggingFace: 💻 GitHub Code: 🗣️ Discord Channel: Huge thanks to Joshua Leonard for building this and sharing it with the community 🙌

34,586 views • 1 month ago

No more content to load