CS 601.471/671 NLP: Self-supervised Models - Johns Hopkins University vs SavirOS

Provides structured educational progression through self-supervised learning techniques for NLP, covering masked language modeling, contrastive learning, and representation learning approaches. The curriculum is organized as a semester-long course with lectures, assignments, and projects that build foundational understanding of how modern language models learn from unlabeled data without explicit supervision signals.

Unique: University-level curriculum specifically focused on self-supervised NLP at Johns Hopkins, combining theoretical foundations with hands-on implementation of techniques like masked prediction, contrastive objectives (SimCLR, MoCo), and momentum-based learning — taught by NLP researchers actively publishing in this space

vs alternatives: Deeper theoretical grounding and research-oriented perspective compared to industry bootcamp courses; provides access to cutting-edge self-supervised techniques before they become mainstream, with faculty expertise in representation learning

Structured programming assignments that guide students through implementing core self-supervised learning algorithms from first principles, including masked language model training loops, contrastive loss functions, and evaluation frameworks. Assignments progress from implementing basic objectives to building complete training pipelines with data loading, optimization, and validation.

Unique: Assignments are designed by active NLP researchers and iterate on real self-supervised techniques used in production models; includes debugging guidance and common pitfalls specific to self-supervised training (e.g., collapse in contrastive learning, convergence issues with masked prediction)

vs alternatives: More rigorous and research-aligned than generic deep learning assignments; focuses on implementation details that matter for production self-supervised systems rather than simplified toy problems

Structured seminar component where students read, present, and critically analyze recent self-supervised NLP research papers. The seminar covers landmark papers (BERT, RoBERTa, SimCLR, MoCo) and recent advances, with student presentations and group discussions that develop research literacy and understanding of the field's evolution.

Unique: Seminar is led by faculty actively publishing in self-supervised NLP; paper selection reflects current research frontiers and includes unpublished work or preprints from the research group, providing insider perspective on research directions

vs alternatives: More curated and research-focused than generic paper reading groups; provides direct access to researchers' perspectives on which papers matter and why, rather than relying on citation counts or popularity

Capstone project framework where students design and implement novel self-supervised learning approaches or apply existing techniques to new domains. Projects are guided through proposal, implementation, and evaluation phases with feedback from instructors and peers, culminating in a research-quality report and code release.

Unique: Projects are mentored by NLP researchers with active publication records; guidance includes not just technical feedback but also research methodology, experimental rigor, and publication-readiness standards that align with top-tier venues

vs alternatives: More research-oriented than typical course projects; emphasizes reproducibility, statistical significance, and contribution novelty rather than just technical correctness, preparing students for research careers

Comprehensive coverage of the mathematical and theoretical underpinnings of self-supervised learning, including information theory perspectives (mutual information maximization), contrastive learning theory (noise contrastive estimation, triplet loss), and convergence analysis. Lectures bridge intuitive explanations with rigorous mathematical proofs and derivations.

Unique: Theory lectures are taught by researchers with publications in theoretical self-supervised learning; includes recent theoretical advances (e.g., understanding collapse in contrastive learning, sample complexity bounds) not yet in textbooks

vs alternatives: Deeper theoretical rigor than industry courses; connects self-supervised learning to broader mathematical frameworks (information theory, statistical learning theory) rather than treating it as isolated techniques

SavirOS is an AI-powered Relationship Operating System that enhances meeting preparation by auto-generating intelligence briefs, tracking promises, and compiling relationship memory, ensuring users are always prepared and informed for their meetings.

Unique: SavirOS uniquely compounds relationship intelligence across all interactions, making it smarter with each meeting unlike competitors that treat meetings in isolation.

vs alternatives: SavirOS offers a more integrated and intelligent approach to meeting preparation compared to traditional tools that focus solely on transcription or note-taking.

SavirAI is a triage-RAG agent that answers questions about relationships, schedules actions, drafts emails, generates documents, and manages contacts — all through natural conversation. 84 tools across 7 agents: platform, calendar, relationship, pre-meeting, post-meeting, communication, creation. Autonomy policy gates sensitive actions (email sending, rescheduling) behind user confirmation.

Seven AI-powered generators for meeting-related communications: icebreaker conversation starters, meeting agenda generator, follow-up email drafts, email subject line optimizer, meeting decline message writer, introduction email generator, and out-of-office reply creator. All free, no signup required.

Automatically enriches contacts with LinkedIn profile data (Proxycurl), company intelligence (Hunter.io), recent news (NewsData.io), and web search (Tavily). Creates comprehensive contact profiles with career history, company details, mutual connections, and recent activity.

Four utility tools: QR code generator (URL, WiFi, vCard, text — PNG/SVG export), browser-based image compressor (JPEG/PNG/WebP, no upload), JSON formatter/validator with tree view, and file sharing (up to 50MB, shareable links). All free, no signup, privacy-first.

Four free lookup tools: reverse caller ID (global, spam detection, confidence scoring), professional email finder (Hunter.io verification), person lookup (career history, talking points via Proxycurl/Tavily), and company lookup (industry, funding, team size, news, social links).

Five meeting utilities: real-time meeting timer with agenda tracking, meeting link decoder (extracts ID/passcode from Zoom/Teams/Meet URLs), instant meeting link generator, WhatsApp link builder with prefilled messages, and downloadable .ics calendar event creator.

Auto-detects ended meetings (every 3 minutes). Processes transcripts from Recall.ai, Fireflies.ai, or user-pasted notes. Extracts structured summary, key points, decisions (with rationale and decision maker), and commitments. Builds episodic memory records. Extracts individual facts and consolidates into per-contact intelligence profiles.