Leakage-aware hybrid IMU and egocentric VideoMAE research scaffold for the 3rd WEAR Dataset Challenge @HASCA 2026.
Quick read
Latest capture 2026-10-17 04:01
Archive status reflects the last catalog sync, not a maintenance assessment. Check recent releases, issue responses, and fit for your project with the repository shortlisting checklist.
0 paths
Agent instructions and tool configuration found in this repository.
No config files detected.
23 observed captures since 2026-09-25. Observed captures are shown by default.
Stars from first capture +2
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
Participant-aware multimodal inertial and VideoMAE baseline for the WEAR 2026 challenge.
Deterministic-first cognitive orchestration with bounded TypeSafe JEV supervision, evidence-aware escalation, and privacy-minimizing telemetry.
Open-source 16-band hyperspectral object detection baseline for the 2026 Kaggle challenge.
This project aims to classify human activities using data obtained from accelerometer and gyroscope sensors from phone and watch.
Executable cognitive architecture: validated graph context, deterministic cache, bounded JEV routing and evidence-gated model collaboration.
Official AHE code — Agentic Harness Engineering: observability-driven automatic evolution of coding-agent harnesses (concurrent w/ meta-harness). NexAU-AHE reaches 84.7% ± 2.1 pass@1 on Terminal-Bench 2 (GPT-5.5). Lifts GPT-5.4 69.7→77.0% over 10 iters, beats Codex/ACE/Training-Free GRPO; frozen harness transfers to SWE-bench-Verified.
