At a glance
| Booth | P6117 |
| Country | SG |
| Website | www.sixsense.ai |
Company profile
SixSense's AI suite turbo-charges fabs and OSAT lines by automating defect review at scale, tracing recurring faults to their root cause, and instantly flagging at-risk wafers. The result is less yield exposure, tighter quality control, higher productivity and higher confidence on every run. AI-ADC is our end-to-end solution for automating visual inspection: with tools for training, deployment, and maintenance, it delivers faster accurate defect classification with fewer labeled samples, reducing cycle time and cleanroom footprint. Build AI is an end-to-end environment for preparing training data with least effort and building high-accuracy AI models; it enables sampling of the most useful images automatically and model training with minimal manual effort and exceptional accuracy. The models are true classification models rather than patched detection or anomaly workarounds, skip bounding boxes so data prep is quick and easy, and retain high accuracy even on extremely small and similar looking defects. Large vision foundation models specialized for semiconductors are pre-trained on millions of wafer-defect images and deliver more than 95% automation, 0% UR, and up to less than 0.05% OR. Explainable AI lets users verify what the model learns and look inside the model to see what it recognizes as a defect, instead of black-box AI. Smart data preparation picks a diverse, balanced, de-duplicated set including hard-to-find examples from millions of images, with AI-assisted label correction at 10x speed. ClassifAI provides smart and scalable defect classification built for high-throughput inspection lines: a single model covers hundreds of devices and tools across generations, with built-in support for multi-view, multi-tool and multiple magnifications, and ready integrations for rescans, Klarf variants and incoming defects, deployable by yield engineers. An operator-first production interface auto-grades and funnels new defects to a built-in manual review interface allowing one-click retraining. SixSense is an AI platform for automating defect inspection, lot disposition and root cause analysis of defects, founded in 2018.
Exhibits
Unlock 95% of your fab's hidden intelligence. Our AI predicts and prevents costly excursions to slash scrap costs, cut cycle time by 30%, and scale your output 1.3x—all without new CAPEX. Sixsense is a purpose-built AI platform for fabs and OSATs, automating defect inspection to lot disposition to root cause analysis of defect. AI-ADC is our end-to-end solution for automating visual inspection , with tools for training, deployment, and model maintenance. Lot Disposition and Root-Cause Analysis brings intelligence to lot disposition by highlighting high-risk wafers based on defect severity and yield impact. It helps prioritize reviews, recover yield, and reduce escapes and scrap. Predict AI Go beyond automation—AI predicts when, where, and what to inspect, enabling proactive action that cuts scrap, reduces downtime, and drives self-optimizing fabs . AI-ADC is a real-time vision engine that analyzes every captured image and classifies suspected defects into hundreds of types with over 99% accuracy and zero escapee . It converts defect images into meaningful insights at line speed —slashing review queues, freeing clean-room headcount , and providing a rock-solid foundation for downstream analytics . Fabs can now scale without concerns about hiring, training, or human-driven quality slips. Built on AI-ADC's trusted labels, Lot Disposition automatically decides pass, hold, rework, or scrap for each lot—balancing yield impact, recurrence patterns, and defect severity. Always-on AI agents correlate classified defects with tool, recipe, and chamber data across hundreds of steps , instantly flagging parameters drifting out of spec , quantifying yield exposure, and surfacing the quickest fix. What once took weeks now takes minutes—safeguarding future yield with speed and precision. Move beyond automation and correlation into prediction—where AI intelligently forecasts when, where, and what to inspect by learning defect likelihood across time, layers, and lots. These insights trigger proactive adjustments to inspection sampling and tools before faults occur, dramatically reducing scrap and downtime. As a result, fabs shift from reactive firefighting to self-optimizing production, guided entirely by data-driven agents. AI classifies every suspected defect 24/7, giving round-the-clock coverage and reducing footprint in clean rooms. Instant pass/fail decisions by AI keep the lots moving; hours get saved at each review step and add savings in up to days for the fab. By catching even the tiniest critical defects early, AI lets engineers correct the process before scrap accumulates—saving thousands of dies that would have been tossed. It also prevents unnecessary over-rejection that comes from cautious manual screening. Consistent, bias-free checks stop bad wafers from moving downstream, slashing reworks, scraps, RMAs and customer complaints from field failures. AI now does the work of dozens of operators, freeing people for higher-value engineering and improvement tasks.
Capabilities and products
- AI platform for automating defect inspection
- AI-ADC end-to-end automated visual inspection
- large vision foundation models specialized for semiconductors
- more than 95% automation and 0% under-rejection
- ClassifAI scalable defect classification
- single model covering devices and tools across generations
- ready integrations for rescans and Klarf variants
- explainable AI for defect recognition
- Build AI end-to-end training data environment
- manual review interface with one-click retraining
- tracing recurring faults to root cause