Pine AI
Popular repositories Loading
-
user-as-engram
user-as-engram PublicA user's facts become a few rows in a content-addressed memory table — not a rewrite of the model. Paper, code, data, and interactive site for "User as Engram" (arXiv:2606.19172).
-
transparent-offload
transparent-offload PublicFine-grained computation offload for off-the-shelf servers in tens of lines — paper (arXiv:2607.02630), code, and every measurement. Overlap accelerator offloads (GPU/HSM/inference) with other requ…
C 7
-
user-as-code
user-as-code PublicExecutable memory for personalized agents: represent a user's memory as typed Python state + constraints an interpreter can run, instead of retrieved text. Code, experiments, and reference implemen…
Python 6
-
openclaw-pine-voice
openclaw-pine-voice PublicOpenClaw plugin for Pine Voice — let your AI agent make real phone calls and get transcripts
Repositories
- interaction-scaling Public
Interaction Scaling: a third inference-time compute axis grounded in environment feedback — proposer–reviewer harness, grounded evaluation, and the paper source.
19PINE-AI/interaction-scaling’s past year of commit activity - aoi Public
AOI: a model-agnostic perception layer giving computer-use agents adaptive video + audio perception with zero retraining, plus DynaCU-Bench (100 dynamic browser tasks). Paper + benchmark + code.
19PINE-AI/aoi’s past year of commit activity - rlvp Public
Penalize the Path, Reward the Outcome — verifiable per-action penalties as a dense channel for deployable, sample-efficient agentic RL (GRPO). Paper: arXiv:2607.07435
19PINE-AI/rlvp’s past year of commit activity - transparent-offload Public
Fine-grained computation offload for off-the-shelf servers in tens of lines — paper (arXiv:2607.02630), code, and every measurement. Overlap accelerator offloads (GPU/HSM/inference) with other requests by rerouting through the server's own suspend/resume machinery, plus a zero-edit LD_PRELOAD fiber runtime.
19PINE-AI/transparent-offload’s past year of commit activity - metronome Public
Real-time serving of full-duplex interaction models: per-tick deadline scheduling + KV-budget admission control. Systems research.
19PINE-AI/metronome’s past year of commit activity - principal-loyalty Public
Whose Side Is Your Agent On? PrincipalBench — a multi-turn benchmark and post-training methods (prompt scaffold + per-token-KL distillation) for multi-party principal loyalty in LLM agents.
19PINE-AI/principal-loyalty’s past year of commit activity - user-as-engram Public
A user's facts become a few rows in a content-addressed memory table — not a rewrite of the model. Paper, code, data, and interactive site for "User as Engram" (arXiv:2606.19172).
19PINE-AI/user-as-engram’s past year of commit activity - programmable-kv Public
Models Take Notes at Prefill: KV Cache Can Be Editable and Composable (arXiv:2606.17107) — paper, code, results, and interactive companion.
19PINE-AI/programmable-kv’s past year of commit activity - latent-bridge-games Public
A learned continuous slow→fast latent channel for real-time game agents: frozen MiniCPM-o 4.5 (fast) + Qwen3-VL-8B-Thinking (slow), 33M-param bridge. The latent helps iff slow reasoning helps (T>F). Paper: arXiv:2606.24470
19PINE-AI/latent-bridge-games’s past year of commit activity
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Most used topics
Loading…