Event owner lens
Use this record to benchmark whether a comparable event makes the work after the room visible. The score is 40/100, so the next move is to benchmark the weakest pillars before repeating the format.
lead or directory source agenda analysis
ICML - Understanding Complexity in VideoQA via Visual Program Generation - 2022
This lead or directory source in Technology / AI / Startup shows 80 visible agenda rows from icml.cc and scores 40/100: a moderate design signal with incomplete evidence. The clearest public signals sit in Future-of-Work Fit and Learning Transfer; the main limits are Follow Through and Network Design. Visible mechanisms include Participant work, Feedback, Network design, 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... A practical reading: For a reader, this is mainly a warning or source-evidence record: it reads as a lead or directory source, with the strongest visible signal in future-of-work fit and learning transfer 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 moderate design signal band. The strongest visible pillars are Future-of-Work Fit, Learning Transfer, and Personalization; the thinnest visible pillars are Follow Through, Network Design, and Participation Architecture. Visible mechanisms include Participant work, Feedback, Network design, Learning transfer, and Personalization. The extracted agenda preview includes 145 visible rows. The most common formats are Presentation, Unknown, and Training; the most common inferred purposes are Knowledge Transfer, Unknown, and Skill Building.
Eight-pillar fingerprint
Hover any pillar to see what it measures and, where it scored low, what the agenda is missing.
Participation Architecture?30
Participation Architecture - 30/100. Participant work, contribution, interaction, and alternatives to passive broadcast.Missing: Turn passive airtime into participant work: practice, sensemaking, decisions, critique, or artifact creation.
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?49
Personalization - 49/100. Role, path, goal, preparation, or connection tailoring for participants.
Network Design?22
Network Design - 22/100. 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?70
Future-of-Work Fit - 70/100. 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 (22/100)
Exercises that strengthen it: Fun Trust-Building Group Game for Team Connection - Izzat... · Exciting Group Trust Activity for Building Confidence... · PFP: September 2005
Participation Architecture (30/100)
Exercises that strengthen it: Make A World · Awestruck 3 Minutes · Spectrum Mapping
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
13 percent of the 145 classified blocks put participants to work; the rest broadcast, show, or handle logistics. That mix is what drives the participation score.
Participant workBroadcastShowcaseLogistics
all eventTutorialsTrainingSkill 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 eventWorkshopsWorkshopParticipant 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
11:00 AMRegistration Check-in DeskRegistrationLogistics+
Format · LogisticsRegistrationCheck-in and logistics, not agenda content.
Evidence basisOutcome inferred from formatInferred from format
7:00 PMExpo 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
4:45 PMExpo DemonstrationDemoShowcase+
Format · Participant workDemoA hands-on or applied walkthrough that invites attendee questions and direct engagement.
Evidence basisOutcome inferred from formatInferred from format
3:00 PMExpo 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 eventAmazon SageMaker Model Parallelism: A General and Flexible Framework for Large Model 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 eventEnabling Hand Gesture Customization on Wrist-Worn DevicesPresentationKnowledge 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
3:00 PMCoffee BreakBreakPacing+
Format · LogisticsBreakA pacing or recovery block between sessions.
Evidence basisOutcome inferred from formatInferred from format
5:00 PMOpening Reception - CateredReceptionRelationship building+
Format · LogisticsReceptionA social or hospitality block. Pacing and informal connection, not participant work.
Evidence basisOutcome inferred from formatInferred from format
7:00 PMMON 18 JULPresentationKnowledge 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
6:00 PMAffinity EventPresentationKnowledge 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
4:30 PMTutorialTrainingSkill 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
1:00 PMLunch BreakBreakPacing+
Format · LogisticsBreakA pacing or recovery block between sessions.
Evidence basisOutcome inferred from formatInferred from format
9:00 PMTUE 19 JULPresentationKnowledge 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
6:30 a.mBreakBreakPacing+
Format · LogisticsBreakA pacing or recovery block between sessions.
Evidence basisOutcome inferred from formatInferred from format
9:00 AMInvited TalkPresentationKnowledge 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
10:30[ ] Differentially Private Approximate QuantilesPresentationKnowledge 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
10:35[ ] Fairness Interventions as (Dis)Incentives for Strategic ManipulationPresentationKnowledge 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
10:40[ ] Robust Models Are More Interpretable Because Attributions Look NormalPresentationKnowledge 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
10:45[ ] Sequential Covariate Shift Detection Using Classifier Two-Sample TestsPresentationKnowledge 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
10:50[ ] A Joint Exponential Mechanism For Differentially Private Top-kExhibitionShowcase+
Format · ShowcaseExhibitionA showcase or expo floor. Browsing and light interaction rather than structured participant work.
Evidence basisOutcome inferred from formatInferred from format
11:00[ ] Robust Kernel Density Estimation with Median-of-Means principlePresentationKnowledge 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
11:05-11:25[11:05] Bounding Training Data Reconstruction in Private (Deep) 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
11:05[ ] Bounding Training Data Reconstruction in Private (Deep) 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
11:25[ ] Plug & Play Attacks: Towards Robust and Flexible Model Inversion AttacksPresentationKnowledge 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
11:30[ ] FriendlyCore: Practical Differentially Private AggregationPresentationKnowledge 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
11:35[ ] ViT-NeT: Interpretable Vision Transformers with Neural Tree DecoderPresentationKnowledge 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
11:40[ ] Fishing for User Data in Large-Batch Federated Learning via Gradient MagnificationPresentationKnowledge 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
11:45[ ] Public Data-Assisted Mirror Descent for Private Model 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
11:50[ ] Low-Complexity Deep Convolutional Neural Networks on Fully Homomorphic Encryption Using Multiplexed Parallel ConvolutionsPresentationKnowledge 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
10:30-10:50[10:30] Tackling covariate shift with node-based Bayesian neural networksPresentationKnowledge 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
10:30[ ] Tackling covariate shift with node-based Bayesian neural networksPresentationKnowledge 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
10:50[ ] Why the Rich Get Richer? On the Balancedness of Random Partition ModelsPresentationKnowledge 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
10:55[ ] A Completely Tuning-Free and Robust Approach to Sparse Precision Matrix EstimationPresentationKnowledge 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
11:00[ ] Markov Chain Monte Carlo for Continuous-Time Switching Dynamical SystemsPresentationKnowledge 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
11:05[ ] Calibrated Learning to Defer with One-vs-All ClassifiersPresentationKnowledge 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
11:10-11:30[11:10] Tractable Uncertainty for Structure LearningPresentationKnowledge 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
11:10[ ] Tractable Uncertainty for Structure LearningPresentationKnowledge 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
11:30[ ] DNA: Domain Generalization with Diversified Neural AveragingPresentationKnowledge 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
11:35[ ] Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous SpacesPresentationKnowledge 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
11:40[ ] DynaMixer: A Vision MLP Architecture with Dynamic MixingPresentationKnowledge 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
11:45[ ] Channel Importance Matters in Few-Shot Image ClassificationPresentationKnowledge 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
11:50[ ] Fishr: Invariant Gradient Variances for Out-of-Distribution GeneralizationPresentationKnowledge 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
10:30[ ] Dynamic Regret of Online Markov Decision ProcessesPresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisSession topic references decisions or metrics; event-level follow-through is not shownRead from source
10:35[ ] On the Impossibility of Learning to Cooperate with Adaptive Partner Strategies in Repeated GamesPresentationKnowledge 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
10:40[ ] Distributional Hamilton-Jacobi-Bellman Equations for Continuous-Time Reinforcement LearningPresentationKnowledge 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
10:45[ ] Provable Reinforcement Learning with a Short-Term MemoryPresentationKnowledge 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
10:50[ ] Optimistic Linear Support and Successor Features as a Basis for Optimal Policy TransferPresentationKnowledge 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
10:55[ ] Mirror Learning: A Unifying Framework of Policy OptimisationPresentationKnowledge 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
11:00-11:20[11:00] Improved No-Regret Algorithms for Stochastic Shortest Path with Linear MDPPresentationKnowledge 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
11:00[ ] Improved No-Regret Algorithms for Stochastic Shortest Path with Linear MDPPresentationKnowledge 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
11:20[ ] Learning Infinite-horizon Average-reward Markov Decision Process with ConstraintsPresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisSession topic references decisions or metrics; event-level follow-through is not shownRead from source
11:25[ ] A State-Distribution Matching Approach to Non-Episodic Reinforcement LearningPresentationKnowledge 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
11:30[ ] Langevin Monte Carlo for Contextual BanditsPresentationKnowledge 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
11:35[ ] Prompting Decision Transformer for Few-Shot Policy GeneralizationPresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisSession topic references decisions or metrics; event-level follow-through is not shownRead from source
11:40[ ] Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement LearningPresentationKnowledge 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
11:45[ ] Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function ApproximationPresentationKnowledge 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
10:30-10:50[10:30] Detecting Adversarial Examples Is (Nearly) As Hard As Classifying ThemPresentationKnowledge 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
10:30[ ] Detecting Adversarial Examples Is (Nearly) As Hard As Classifying ThemPresentationKnowledge 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
10:50[ ] ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural NetworksPresentationKnowledge 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
10:55[ ] Provably Adversarially Robust Nearest Prototype ClassifiersPresentationKnowledge 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
11:00[ ] Certifying Out-of-Domain Generalization for Blackbox FunctionsPresentationKnowledge 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
11:05[ ] Intriguing Properties of Input-Dependent Randomized SmoothingPresentationKnowledge 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
11:10-11:30[11:10] To Smooth or Not? When Label Smoothing Meets Noisy LabelsWorkshopParticipant 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 eventTutorialsTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
all eventWorkshopsWorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventAffinity Event Award Break Expo Demonstration Expo Talk Panel Expo Workshop Invited Talk Reception Registration Desk Remarks Session Social Tutorial WorkshopPanelDeliberation+
Format · BroadcastPanelExperts discuss while the audience watches. Surfaces perspective but rarely creates participant work.
Evidence basisMediumRead from source
9 a.mSocial:UnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:00 AMRegistration Check-in DeskRegistrationLogistics+
Format · LogisticsRegistrationCheck-in and logistics, not agenda content.
Evidence basisMediumRead from source
7:00 PMExpo Talk Panel:PanelDeliberation+
Format · BroadcastPanelExperts discuss while the audience watches. Surfaces perspective but rarely creates participant work.
Evidence basisMediumRead from source
4:45 PMExpo Demonstration:DemoShowcase+
Format · Participant workDemoA hands-on or applied walkthrough that invites attendee questions and direct engagement.
Evidence basisMediumRead from source
3:00 PMExpo Workshop:WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
2:20 PMCancelled:UnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
all eventAmazon SageMaker Model Parallelism: A General and Flexible Framework for Large Model TrainingTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
all eventEnabling Hand Gesture Customization on Wrist-Worn DevicesUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
3:00 PMCoffee Break:BreakWellbeing+
Format · LogisticsBreakA pacing or recovery block between sessions.
Evidence basisMediumRead from source
5:00 PMOpening Reception - Catered:ReceptionRelationship Building+
Format · LogisticsReceptionA social or hospitality block. Pacing and informal connection, not participant work.
Evidence basisMediumRead from source
7:00 PMMON 18 JULUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
6:00 PMAffinity Event:UnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
4:30 PMTutorial:TrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
1:00 PMLunch Break:MealWellbeing+
Format · LogisticsMealA pacing block. Can carry unstructured networking, not scored as participant work.
Evidence basisMediumRead from source
9:00 PMTUE 19 JULUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
6:30 a.mBreak:BreakWellbeing+
Format · LogisticsBreakA pacing or recovery block between sessions.
Evidence basisMediumRead from source
7:00 PMRemarks:UnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
9:00 AMInvited Talk:PresentationKnowledge Transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisMediumRead from source
10:30 AM[Social Aspects [10:30-12:00] ](https://icml.cc/virtual/2022/session/20045)PresentationKnowledge Transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisMediumRead from source
10:30-12:00[Social Aspects [ ] ](https://icml.cc/virtual/2022/session/20045)PresentationKnowledge Transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisMediumRead from source
10:30-11:05SpotlightsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:30[ ] Differentially Private Approximate QuantilesUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:35[ ] Fairness Interventions as (Dis)Incentives for Strategic ManipulationUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:40[ ] Robust Models Are More Interpretable Because Attributions Look NormalUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:45[ ] Sequential Covariate Shift Detection Using Classifier Two-Sample TestsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:50[ ] A Joint Exponential Mechanism For Differentially Private Top-kExhibitionShowcase+
Format · ShowcaseExhibitionA showcase or expo floor. Browsing and light interaction rather than structured participant work.
Evidence basisMediumRead from source
10:55[ ] Transfer Learning In Differential Privacy's Hybrid-ModelUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:00[ ] Robust Kernel Density Estimation with Median-of-Means principleUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:05-11:25[11:05] Bounding Training Data Reconstruction in Private (Deep) LearningTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
11:05[ ] Bounding Training Data Reconstruction in Private (Deep) LearningTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
11:25[ ] Plug & Play Attacks: Towards Robust and Flexible Model Inversion AttacksUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:30[ ] FriendlyCore: Practical Differentially Private AggregationUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:35[ ] ViT-NeT: Interpretable Vision Transformers with Neural Tree DecoderUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:40[ ] Fishing for User Data in Large-Batch Federated Learning via Gradient MagnificationUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:45[ ] Public Data-Assisted Mirror Descent for Private Model TrainingTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
11:50[ ] Low-Complexity Deep Convolutional Neural Networks on Fully Homomorphic Encryption Using Multiplexed Parallel ConvolutionsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:55[ ] Robin Hood and Matthew Effects: Differential Privacy Has Disparate Impact on Synthetic DataUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
12:00 PM[Probabilistic Methods/Applications [10:30-12:00] ](https://icml.cc/virtual/2022/session/20046)PresentationKnowledge Transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisMediumRead from source
10:30-12:00[Probabilistic Methods/Applications [ ] ](https://icml.cc/virtual/2022/session/20046)PresentationKnowledge Transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisMediumRead from source
10:30-10:50[10:30] Tackling covariate shift with node-based Bayesian neural networksUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:30[ ] Tackling covariate shift with node-based Bayesian neural networksUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:50[ ] Why the Rich Get Richer? On the Balancedness of Random Partition ModelsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:55[ ] A Completely Tuning-Free and Robust Approach to Sparse Precision Matrix EstimationUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:00[ ] Markov Chain Monte Carlo for Continuous-Time Switching Dynamical SystemsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:05[ ] Calibrated Learning to Defer with One-vs-All ClassifiersUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:10-11:30[11:10] Tractable Uncertainty for Structure LearningUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:10[ ] Tractable Uncertainty for Structure LearningUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:30[ ] DNA: Domain Generalization with Diversified Neural AveragingUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:35[ ] Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous SpacesUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:40[ ] DynaMixer: A Vision MLP Architecture with Dynamic MixingUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:45[ ] Channel Importance Matters in Few-Shot Image ClassificationUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:50[ ] Fishr: Invariant Gradient Variances for Out-of-Distribution GeneralizationUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
12:00 PM[Reinforcement Learning [10:30-12:00] ](https://icml.cc/virtual/2022/session/20047)PresentationKnowledge Transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisMediumRead from source
10:30-12:00[Reinforcement Learning [ ] ](https://icml.cc/virtual/2022/session/20047)PresentationKnowledge Transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisMediumRead from source
10:30[ ] Dynamic Regret of Online Markov Decision ProcessesUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:35[ ] On the Impossibility of Learning to Cooperate with Adaptive Partner Strategies in Repeated GamesUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:40[ ] Distributional Hamilton-Jacobi-Bellman Equations for Continuous-Time Reinforcement LearningUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:45[ ] Provable Reinforcement Learning with a Short-Term MemoryUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:50[ ] Optimistic Linear Support and Successor Features as a Basis for Optimal Policy TransferUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:55[ ] Mirror Learning: A Unifying Framework of Policy OptimisationUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:00-11:20[11:00] Improved No-Regret Algorithms for Stochastic Shortest Path with Linear MDPUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:00[ ] Improved No-Regret Algorithms for Stochastic Shortest Path with Linear MDPUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:20[ ] Learning Infinite-horizon Average-reward Markov Decision Process with ConstraintsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:25[ ] A State-Distribution Matching Approach to Non-Episodic Reinforcement LearningUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:30[ ] Langevin Monte Carlo for Contextual BanditsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:35[ ] Prompting Decision Transformer for Few-Shot Policy GeneralizationUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:40[ ] Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement LearningUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:45[ ] Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function ApproximationUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
12:00 PM[Deep Learning: Robustness [10:30-12:00] ](https://icml.cc/virtual/2022/session/20048)PresentationKnowledge Transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisMediumRead from source
10:30-12:00[Deep Learning: Robustness [ ] ](https://icml.cc/virtual/2022/session/20048)PresentationKnowledge Transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisMediumRead from source
10:30-10:50[10:30] Detecting Adversarial Examples Is (Nearly) As Hard As Classifying ThemUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:30[ ] Detecting Adversarial Examples Is (Nearly) As Hard As Classifying ThemUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:50[ ] ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural NetworksUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:55[ ] Provably Adversarially Robust Nearest Prototype ClassifiersUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:00[ ] Certifying Out-of-Domain Generalization for Blackbox FunctionsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:05[ ] Intriguing Properties of Input-Dependent Randomized SmoothingUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:10-11:30[11:10] To Smooth or Not? When Label Smoothing Meets Noisy LabelsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
The Full Reading
Why It Ranks This Way +
Calibrated from GES design 41/100 and verified 41/100, then capped for source appears to be a guide, directory, calendar, or ancillary page rather than a source agenda.
Reader Takeaway. For a reader, this is mainly a warning or source-evidence record: it reads as a lead or directory source, with the strongest visible signal in future-of-work fit and learning transfer 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: Future-of-Work Fit, Learning Transfer, and Personalization. Weakest signals: Follow Through, Network Design, and Participation Architecture.
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.
- Turn passive airtime into participant work: practice, sensemaking, decisions, critique, or artifact creation.
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 look for structured introductions, buyer-seller fit, and relationship persistence.
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 keep it as lead evidence unless a direct agenda source is also available 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, Network design, Learning transfer, Personalization.
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.
- Passive stage formats dominate the visible agenda.
- No baseline measurement is visible.
Score caps
- 28: Source appears to be a guide, directory, calendar, or ancillary page rather than a source agenda.
Review flags
- Fourth-loop score cap: Source appears to be a guide, directory, calendar, or ancillary page rather than a source agenda.
- URL path looks like an event calendar, directory, or list.
- Agenda is useful as a source record but weak as evidence of gathering effectiveness.
- 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.
Where To Go Next
Compare this agenda against other Technology / AI / Startup events scored on the same eight pillars.