Event owner lens
Use this record to benchmark whether a comparable event makes the work after the room visible. The score is 39/100, so the next move is to benchmark the weakest pillars before repeating the format.
applied learning or working session agenda analysis
ICML - Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI - 2020 - Schedule for Unregistered Attendees
This applied learning or working session in Academic / Research / Science shows 80 visible agenda rows from icml.cc and scores 39/100: a thin but inspectable design signal. The clearest public signals sit in Learning Transfer and Participation Architecture; the main limits are Follow Through and Network Design. Visible mechanisms include Participant work, Feedback, and Learning transfer. The public record does not show follow-up or tracking, so the score should be read as design intent rather than durable impact. A practical reading: For a reader, this is a comparison record more than a model to copy: it reads as an applied learning or working session, with the strongest visible signal in learning transfer and participation architecture and the biggest open question around follow through and network design. The practical test is whether the published agenda connects the room to post-event continuation and evidence. This page is an original public-evidence analysis, not a copy of the source agenda or an endorsement of the event. The score places the visible agenda in the thin outcome architecture band. The strongest visible pillars are Learning Transfer, Participation Architecture, and Future-of-Work Fit; the thinnest visible pillars are Follow Through, Network Design, and Personalization. Visible mechanisms include Participant work, Feedback, and Learning transfer. The extracted agenda preview includes 153 visible rows. The most common formats are Poster Session, Training, and Unknown; the most common inferred purposes are Showcase, Skill Building, and Unknown.
Eight-pillar fingerprint
Hover any pillar to see what it measures and, where it scored low, what the agenda is missing.
Participation Architecture?62
Participation Architecture - 62/100. Participant work, contribution, interaction, and alternatives to passive broadcast.
Follow Through?5
Follow Through - 5/100. Owners, dates, commitments, progress checks, and accountability after the room.Missing: Add named owners, dates, implementation checkpoints, and a visible post-event continuation path.
Problem Specificity?43
Problem Specificity - 43/100. A clear costly problem, objective, decision, or performance target.
Personalization?33
Personalization - 33/100. Role, path, goal, preparation, or connection tailoring for participants.Missing: Create role-based paths, prepared questions, tailored breakouts, or participant-specific next steps.
Network Design?6
Network Design - 6/100. Structured weak ties, bridge-building, mixers, and relationship persistence.Missing: Replace generic networking blocks with designed introductions, ask-offer exchanges, peer groups, or bridge-building rituals.
Learning Transfer?63
Learning Transfer - 63/100. Applied practice, feedback, workplace use, refreshers, and 30-90 day transfer.
Evidence Maturity?45
Evidence Maturity - 45/100. Baseline, comparison, follow-up, isolation, and attribution confidence.
Future-of-Work Fit?55
Future-of-Work Fit - 55/100. Value against time, hybrid reality, accessibility, AI, and meeting load.
Fix the gaps
Field-tested exercises matched to this agenda's weakest pillars, from the exercise library.
Follow Through (5/100)
Exercises that strengthen it: Mental Toughness Workshop • WorkshopBank · 15% Solutions • WorkshopBank · Network Patches
Network Design (6/100)
Exercises that strengthen it: Fun Trust-Building Group Game for Team Connection - Izzat... · Exciting Group Trust Activity for Building Confidence... · PFP: September 2005
Personalization (33/100)
Exercises that strengthen it: Journey Mapping • WorkshopBank · Group Energiser & Perspective-Changing Exercise - Paradigm... · Photo Storytelling
Agenda Preview
The actual agenda we captured. Every block is classified by format and purpose. Open any block to see how we read it; the colored edge shows whether it is participant work, broadcast, logistics, or a showcase.
Room vs wrapper
35 percent of the 153 classified blocks put participants to work; the rest broadcast, show, or handle logistics. That mix is what drives the participation score.
Participant workBroadcastShowcaseLogistics
all eventCall for TutorialsTrainingSkill building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisParticipant work is implied by the formatInferred from format
all eventCall for WorkshopsWorkshopParticipant work+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisParticipant work is implied by the formatInferred from format
all eventExpo DemonstrationDemoShowcase+
Format · Participant workDemoA hands-on or applied walkthrough that invites attendee questions and direct engagement.
Evidence basisOutcome inferred from formatInferred from format
all eventExpo Talk PanelPanelDiscussion+
Format · BroadcastPanelExperts discuss while the audience watches. Surfaces perspective but rarely creates participant work.
Evidence basisNo participant output visible from this rowRead from source, no work signal
all eventPosterPoster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all eventTutorialTrainingSkill building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisParticipant work is implied by the formatInferred from format
all eventWorkshopWorkshopParticipant work+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisParticipant work is implied by the formatInferred from format
all eventToggle Poster VisibilityPoster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
09:45 PMSat Jul 11 -- & Sun Jul 12 -- (PDT)PresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
12:15 AMSun Jul 12 -- & Sun Jul 12 -- (PDT)PresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
all eventMachine Learning for Drug Discovery in the era of SARS-CoV-2. A panel discussionPanelDiscussion+
Format · BroadcastPanelExperts discuss while the audience watches. Surfaces perspective but rarely creates participant work.
Evidence basisNo participant output visible from this rowRead from source, no work signal
11:00 PMSun Jul 12 -- (PDT)PresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
01:00 AMMon Jul 13 -- & Mon Jul 13 -- (PDT)PresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
all eventTutorials 1TrainingSkill building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisParticipant work is implied by the formatInferred from format
all eventAffinity WorkshopWorkshopParticipant work+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisParticipant work is implied by the formatInferred from format
04:00 AMMon Jul 13 -- (PDT)PresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
all eventLatinX in AI WorkshopWorkshopParticipant work+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisParticipant work is implied by the formatInferred from format
all eventTutorials 2TrainingSkill building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisParticipant work is implied by the formatInferred from format
all eventTutorials 3TrainingSkill building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisParticipant work is implied by the formatInferred from format
08:00 AMMon Jul 13 -- & Mon Jul 13 -- (PDT) @ VirtualPresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
all eventCoffee BreakBreakPacing+
Format · LogisticsBreakA pacing or recovery block between sessions.
Evidence basisOutcome inferred from formatInferred from format
12:45 AMTue Jul 14 -- (PDT)PresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
05:00 AMTue Jul 14 -- & Tue Jul 14 -- (PDT)PresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
all eventPoster Session 11Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all eventPoster Session 10Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
07:00 AMTue Jul 14 -- & Tue Jul 14 -- (PDT) @ VirtualPresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
all eventPoster Session 1Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all eventLearning the Stein Discrepancy for Training and Evaluating Energy-Based Models without SamplingTrainingSkill building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisParticipant work is implied by the formatInferred from format
all eventPoster Session 12Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all eventFair Learning with Private Demographic DataDemoShowcase+
Format · Participant workDemoA hands-on or applied walkthrough that invites attendee questions and direct engagement.
Evidence basisOutcome inferred from formatInferred from format
all eventDeltaGrad: Rapid retraining of machine learning modelsTrainingSkill building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisParticipant work is implied by the formatInferred from format
all eventTraining Binary Neural Networks through Learning with Noisy SupervisionTrainingSkill building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisParticipant work is implied by the formatInferred from format
all eventPoster Session 13Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all eventPoster Session 2Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all eventPoster Session 3Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
09:00 AMTue Jul 14 -- & Wed Jul 15 -- (PDT)PresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
all eventPoster Session 32Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all eventPoster Session 14Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all eventFeature Quantization Improves GAN TrainingTrainingSkill building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisParticipant work is implied by the formatInferred from format
all eventHow Good is the Bayes Posterior in Deep Neural Networks Really?Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all eventRetrieval Augmented Language Model Pre-TrainingTrainingSkill building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisParticipant work is implied by the formatInferred from format
all eventVariational Imitation Learning with Diverse-quality DemonstrationsDemoShowcase+
Format · Participant workDemoA hands-on or applied walkthrough that invites attendee questions and direct engagement.
Evidence basisOutcome inferred from formatInferred from format
09:00 AMTue Jul 14 -- & Wed Jul 15 -- (PDT) @ VirtualPresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
all eventPoster Session 4Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all eventPoster Session 15Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all eventTrain Big, Then Compress: Rethinking Model Size for Efficient Training and Inference of TransformersTrainingSkill building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisParticipant work is implied by the formatInferred from format
all eventPolicy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement LearningTrainingSkill building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisParticipant work is implied by the formatInferred from format
all eventGenerative Pretraining From PixelsTrainingSkill building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisParticipant work is implied by the formatInferred from format
all eventTraining Deep Energy-Based Models with f-Divergence MinimizationTrainingSkill building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisParticipant work is implied by the formatInferred from format
all eventGenerative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training DataTrainingSkill building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisParticipant work is implied by the formatInferred from format
all eventPoster Session 5Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all eventPoster Session 16Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all eventPoster Session 6Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all eventPoster Session 17Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all eventPoster Session 7Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all eventConfidence-Calibrated Adversarial Training: Generalizing to Unseen AttacksTrainingSkill building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisParticipant work is implied by the formatInferred from format
all eventNatasa Tagasovska · Valérie Chavez-Demoulin · Thibault VatterDemoShowcase+
Format · Participant workDemoA hands-on or applied walkthrough that invites attendee questions and direct engagement.
Evidence basisOutcome inferred from formatInferred from format
all eventPoster Session 18Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all eventPoster Session 19Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all eventPoster Session 8Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all eventTraining Neural Networks for and by InterpolationTrainingSkill building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisParticipant work is implied by the formatInferred from format
all eventPoster Session 9Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all eventPoster Session 20Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all eventAttacks Which Do Not Kill Training Make Adversarial Learning StrongerTrainingSkill building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisParticipant work is implied by the formatInferred from format
12:45 AMWed Jul 15 -- (PDT)PresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
05:00 AMWed Jul 15 -- & Wed Jul 15 -- (PDT) @ VirtualPresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
all eventPoster Session 21Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
05:00 AMWed Jul 15 -- & Wed Jul 15 -- (PDT)PresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
all eventPoster Session 30Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all eventPoster Session 31Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all eventPoster Session 22Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all eventPoster Session 33Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all eventUnderstanding Self-Training for Gradual Domain AdaptationTrainingSkill building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisParticipant work is implied by the formatInferred from format
all eventSelect Year: (2020)UnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventSchedule for Unregistered AttendeesUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventCallsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventCall for TutorialsTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
all eventCall for WorkshopsWorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventFinancial AidUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventVolunteer ApplicationUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventOrganizationUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventAbout ICMLUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventExpo DemonstrationDemoShowcase+
Format · Participant workDemoA hands-on or applied walkthrough that invites attendee questions and direct engagement.
Evidence basisMediumRead from source
all eventExpo Talk PanelPanelDeliberation+
Format · BroadcastPanelExperts discuss while the audience watches. Surfaces perspective but rarely creates participant work.
Evidence basisMediumRead from source
all eventPosterPoster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventTutorialTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
all eventWorkshopWorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventToggle Poster VisibilityPoster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
09:45 PMSat Jul 11 -- & Sun Jul 12 -- (PDT)UnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
12:15 AMSun Jul 12 -- & Sun Jul 12 -- (PDT)UnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
all eventMachine Learning for Drug Discovery in the era of SARS-CoV-2. A panel discussionPanelDeliberation+
Format · BroadcastPanelExperts discuss while the audience watches. Surfaces perspective but rarely creates participant work.
Evidence basisMediumRead from source
11:00 PMSun Jul 12 -- (PDT)UnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
01:00 AMMon Jul 13 -- & Mon Jul 13 -- (PDT)UnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
all eventTutorials 1TrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
all eventAffinity WorkshopWorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
04:00 AMMon Jul 13 -- (PDT)UnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
all eventLatinX in AI WorkshopWorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventTutorials 2TrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
all eventTutorials 3TrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
08:00 AMMon Jul 13 -- & Mon Jul 13 -- (PDT) @ VirtualUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
all eventCoffee BreakBreakWellbeing+
Format · LogisticsBreakA pacing or recovery block between sessions.
Evidence basisMediumRead from source
12:45 AMTue Jul 14 -- (PDT)UnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
05:00 AMTue Jul 14 -- & Tue Jul 14 -- (PDT)UnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
all eventPoster Session 11Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventPoster Session 10Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
07:00 AMTue Jul 14 -- & Tue Jul 14 -- (PDT) @ VirtualUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
all eventPoster Session 1Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventLearning the Stein Discrepancy for Training and Evaluating Energy-Based Models without SamplingTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
all eventPoster Session 12Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventFair Learning with Private Demographic DataDemoShowcase+
Format · Participant workDemoA hands-on or applied walkthrough that invites attendee questions and direct engagement.
Evidence basisMediumRead from source
all eventDeltaGrad: Rapid retraining of machine learning modelsTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
all eventTraining Binary Neural Networks through Learning with Noisy SupervisionTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
all eventPoster Session 13Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventPoster Session 2Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventPoster Session 3Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
09:00 AMTue Jul 14 -- & Wed Jul 15 -- (PDT)UnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
all eventPoster Session 32Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventPoster Session 14Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventFeature Quantization Improves GAN TrainingTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
all eventHow Good is the Bayes Posterior in Deep Neural Networks Really?Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventRetrieval Augmented Language Model Pre-TrainingTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
all eventVariational Imitation Learning with Diverse-quality DemonstrationsDemoShowcase+
Format · Participant workDemoA hands-on or applied walkthrough that invites attendee questions and direct engagement.
Evidence basisMediumRead from source
09:00 AMTue Jul 14 -- & Wed Jul 15 -- (PDT) @ VirtualUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
all eventPoster Session 4Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventPoster Session 15Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventTrain Big, Then Compress: Rethinking Model Size for Efficient Training and Inference of TransformersTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
all eventPolicy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement LearningTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
all eventGenerative Pretraining From PixelsTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
all eventTraining Deep Energy-Based Models with f-Divergence MinimizationTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
all eventGenerative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training DataTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
all eventPoster Session 5Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventPoster Session 16Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventPoster Session 6Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventPoster Session 17Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventPoster Session 7Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventConfidence-Calibrated Adversarial Training: Generalizing to Unseen AttacksTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
all eventNatasa Tagasovska · Valérie Chavez-Demoulin · Thibault VatterDemoShowcase+
Format · Participant workDemoA hands-on or applied walkthrough that invites attendee questions and direct engagement.
Evidence basisMediumRead from source
all eventPoster Session 18Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventPoster Session 19Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventPoster Session 8Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventTraining Neural Networks for and by InterpolationTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
all eventPoster Session 9Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventPoster Session 20Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventAttacks Which Do Not Kill Training Make Adversarial Learning StrongerTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
12:45 AMWed Jul 15 -- (PDT)UnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
05:00 AMWed Jul 15 -- & Wed Jul 15 -- (PDT) @ VirtualUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
all eventPoster Session 21Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
05:00 AMWed Jul 15 -- & Wed Jul 15 -- (PDT)UnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
all eventPoster Session 30Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventPoster Session 31Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventPoster Session 22Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventPoster Session 33Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventUnderstanding Self-Training for Gradual Domain AdaptationTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
The Full Reading
Why It Ranks This Way +
Calibrated from GES design 39/100 and verified 39/100 with no fourth-loop cap.
Reader Takeaway. For a reader, this is a comparison record more than a model to copy: it reads as an applied learning or working session, with the strongest visible signal in learning transfer and participation architecture and the biggest open question around follow through and network design. The practical test is whether the published agenda connects the room to post-event continuation and evidence.
Strongest signals: Learning Transfer, Participation Architecture, and Future-of-Work Fit. Weakest signals: Follow Through, Network Design, and Personalization.
How This Agenda Could Improve +
- Add named owners, dates, implementation checkpoints, and a visible post-event continuation path.
- Replace generic networking blocks with designed introductions, ask-offer exchanges, peer groups, or bridge-building rituals.
- Create role-based paths, prepared questions, tailored breakouts, or participant-specific next steps.
Fastest next move: Add named owners, dated next steps, and a visible continuation path before treating the event as outcome-ready.
Role-Specific Reading +
Sponsor lens
Look beyond exposure. Strong sponsor value would show qualified interaction, problem work, buyer learning, customer evidence, or follow-up. The practical sponsor move is to ask for qualified interaction and post-event proof, not only reach.
Designer lens
The agenda is useful as a pattern sample from icml.cc. Redesign attention should go first to the lowest-scoring pillars; in practice, turn the thinnest agenda blocks into participant work.
Executive lens
Treat the visible agenda as an operating plan. The executive move is to require owners, dates, and evidence before treating the event as strategic. If owners, proof, and follow-through are not visible, the public record does not yet prove strategic movement.
Aggregator lens
Treat the source URL as evidence, not decoration. The data-product move is to label the source boundary clearly before ranking the record before ranking or syndicating the record.
What GES Means Here +
The Gathering Effectiveness Score is a strict 0-100 public-evidence reading of the agenda across eight pillars. It rewards visible participant work, follow-through, transfer, network design, and proof mechanisms more than polish, speaker fame, attendance, or satisfaction.
Visible mechanisms: Participant work, Feedback, Learning transfer.
Evidence boundary: Scores reflect visible agenda/source evidence and should not be read as proof of causal event impact.
Limitations, Score Caps, and Review Flags +
Limitations
- No visible follow-up, progress monitoring, or longitudinal tracking.
- No baseline measurement is visible.
Score caps
- No fourth-loop score cap applied.
Review flags
- No source-backed follow-up, validation, baseline, tracking, or impact evidence.
- No tracking, validation, feedback, or impact measurement found in the visible source text.
- Original category was unknown; publication category is inferred.
Is this proof the event worked? +
No. This is a strict public-evidence reading of the agenda. Proof would require baseline, comparison, follow-up, attribution, and impact evidence beyond the listing.
What should a reader inspect first? +
Start with the source URL, then compare the eight pillar scores against the agenda rows. The biggest opportunities usually sit in follow-through, evidence maturity, and participant work.
Why publish weak records? +
Weak records are part of the map. They show where public agendas still describe sessions and speakers more often than outcomes, commitments, transfer, or proof.
How should I use the rows? +
Read the agenda rows as the visible design trace: formats, purposes, and evidence labels show what the public source made inspectable, not everything that happened in the room. This is a source-grounded interpretation of the public agenda record, not a copy of the source, and not an endorsement of the event.
Embed the verified badge +
This record is in the hand-verified gold set. Copy the snippet below to embed the verified badge on your own site.
<a href="https://unitedwetransform.com/events/evt_2020_icml_self_improving_language_models_for_evolutionary_program_synthesis_a_ca_1d2814"><img src="https://unitedwetransform.com/badge/ges-verified.svg" alt="GES verified by United We Transform" height="40"></a>Where To Go Next
Compare this agenda against other Academic / Research / Science events scored on the same eight pillars.