Event owner lens
Use this record to benchmark whether a comparable event makes the work after the room visible. The score is 45/100, so the next move is to benchmark the weakest pillars before repeating the format.
lead or directory source agenda analysis
ICML
This lead or directory source in Trade Show / Expo shows 80 visible agenda rows from icml.cc and scores 45/100: 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 impact.... 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 Participation Architecture; the thinnest visible pillars are Follow Through, Network Design, and Evidence Maturity. 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?51
Participation Architecture - 51/100. 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?49
Problem Specificity - 49/100. A clear costly problem, objective, decision, or performance target.
Personalization?47
Personalization - 47/100. Role, path, goal, preparation, or connection tailoring for participants.
Network Design?28
Network Design - 28/100. 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?71
Learning Transfer - 71/100. 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.Missing: Add baseline measurement, comparison logic, tracking, or post-event impact reporting so effectiveness is not inferred only from format.
Future-of-Work Fit?74
Future-of-Work Fit - 74/100. 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 (28/100)
Exercises that strengthen it: Fun Trust-Building Group Game for Team Connection - Izzat... · Exciting Group Trust Activity for Building Confidence... · PFP: September 2005
Personalization (47/100)
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
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 eventSpotlight PostersPoster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from 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 a.mRegistration WestRegistrationLogistics+
Format · LogisticsRegistrationCheck-in and logistics, not agenda content.
Evidence basisOutcome inferred from formatInferred from format
5:30 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
3:00 PMBreakBreakPacing+
Format · LogisticsBreakA pacing or recovery block between sessions.
Evidence basisOutcome inferred from formatInferred from format
all eventCoffee BreakBreakPacing+
Format · LogisticsBreakA pacing or recovery block between sessions.
Evidence basisOutcome inferred from formatInferred from format
all eventDistributed Computing Architectures as a Solution to AI's Energy Crisis: Empirical Analysis of Decentralized 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
6:00 PMMON 14 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 PMRegistration EastRegistrationLogistics+
Format · LogisticsRegistrationCheck-in and logistics, not agenda content.
Evidence basisOutcome inferred from formatInferred from format
3:00 PMICML Lounge AreaPresentationKnowledge 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
10:00 AMTutorialTrainingSkill 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
10:30 AMAffinity 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
5:00 PMExpo DemonstrationDemoShowcase+
Format · Participant workDemoA hands-on or applied walkthrough that invites attendee questions and direct engagement.
Evidence basisOutcome inferred from formatInferred from format
8:00 PM(ends 8:00 PM)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
7:00 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 eventBuilding Production Ready Agentic Systems: Architecture, LLM-based Evaluation, and GRPO 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
6:00 PMReceptionReceptionRelationship building+
Format · LogisticsReceptionA social or hospitality block. Pacing and informal connection, not participant work.
Evidence basisOutcome inferred from formatInferred from format
all eventOpening Remarks and Welcome ReceptionReceptionOrientation+
Format · LogisticsReceptionA social or hospitality block. Pacing and informal connection, not participant work.
Evidence basisOutcome inferred from formatInferred from format
8:00 PMTUE 15 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
5:30 PMInvited 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
10:00 AM(ends 6:00 PM)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
10:00-11:00[10:00] Multi-agent Architecture Search via Agentic SupernetPresentationKnowledge 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
10:00[ ] Multi-agent Architecture Search via Agentic SupernetPresentationKnowledge 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
10:15[ ] Training a Generally Curious AgentTrainingSkill 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
10:30[ ] Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMsPresentationKnowledge 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[ ] CollabLLM: From Passive Responders to Active CollaboratorsWorkshopParticipant 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
10:00-11:00[10:00] Position: The AI Conference Peer Review Crisis Demands Author Feedback and Reviewer RewardsPresentationKnowledge 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
10:00[ ] Position: The AI Conference Peer Review Crisis Demands Author Feedback and Reviewer RewardsPresentationKnowledge 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
10:15[ ] Position: Not All Explanations for Deep Learning Phenomena Are Equally ValuablePresentationKnowledge 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[ ] Position: Certified Robustness Does Not (Yet) Imply Model SecurityPresentationKnowledge 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[ ] Position: Probabilistic Modelling is Sufficient for Causal InferencePresentationKnowledge 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
10:00-11:00[10:00] VideoRoPE: What Makes for Good Video Rotary Position Embedding?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
10:00[ ] VideoRoPE: What Makes for Good Video Rotary Position Embedding?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
10:15[ ] ReferSplat: Referring Segmentation in 3D Gaussian SplattingPresentationKnowledge 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[ ] Orthogonal Subspace Decomposition for Generalizable AI-Generated Image DetectionPresentationKnowledge 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[ ] VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video 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
10:00-11:00[10:00] Algorithm Development in Neural Networks: Insights from the Streaming Parity TaskPresentationKnowledge 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
10:00[ ] Algorithm Development in Neural Networks: Insights from the Streaming Parity TaskPresentationKnowledge 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
10:15[ ] Learning Dynamics in Continual Pre-Training for Large Language 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
10:30[ ] Strategy Coopetition Explains the Emergence and Transience of In-Context 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[ ] Transformative or Conservative? Conservation laws for ResNets and TransformersPresentationKnowledge 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
10:00-11:00[10:00] An analytic theory of creativity in convolutional diffusion 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
10:00[ ] An analytic theory of creativity in convolutional diffusion 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
10:15[ ] Layer by Layer: Uncovering Hidden Representations in Language 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
10:30[ ] Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained 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
10:45[ ] Emergence in non-neural models: grokking modular arithmetic via average gradient outer productPresentationKnowledge 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 eventThe Disparate Benefits of Deep EnsemblesPresentationKnowledge 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 eventRelative Error Fair Clustering in the Weak-Strong Oracle ModelPresentationKnowledge 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 eventFDGen: A Fairness-Aware Graph Generation ModelPresentationKnowledge 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 eventGHOST: Generalizable One-Shot Federated Graph Learning with Proxy-Based Topology Knowledge RetentionPresentationKnowledge 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 eventCAN: Leveraging Clients As Navigators for Generative Replay in Federated Continual 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
all eventTracking The Best Expert PrivatelyPresentationKnowledge 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 eventLayer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language 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
all eventPreference learning made easy: Everything should be understood through win ratePresentationKnowledge 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 eventVision-Language Models Create Cross-Modal Task RepresentationsPresentationKnowledge 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 eventDetecting Strategic Deception with Linear ProbesPresentationKnowledge 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 eventWhich Attention Heads Matter for In-Context Learning?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 eventTensor Product Neural Networks for Functional ANOVA ModelPresentationKnowledge 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 eventFrom Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature SelectionPresentationKnowledge 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 eventFast Estimation of Partial Dependence Functions using TreesPresentationKnowledge 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 eventAxBench: Steering LLMs? Even Simple Baselines Outperform Sparse AutoencodersPresentationKnowledge 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 eventOn the Interplay between Graph Structure and Learning Algorithms in Graph 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
all eventData-driven Design of Randomized Control Trials with Guaranteed Treatment EffectsPresentationKnowledge 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 eventSAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model InterpretabilityPresentationKnowledge 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
all eventTutorialsTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
all eventSpotlight PostersPoster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
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
11 a.mRegistration WestRegistrationLogistics+
Format · LogisticsRegistrationCheck-in and logistics, not agenda content.
Evidence basisMediumRead from source
5:30 PMExpo Talk Panel:PanelDeliberation+
Format · BroadcastPanelExperts discuss while the audience watches. Surfaces perspective but rarely creates participant work.
Evidence basisMediumRead from source
3:00 PMBreak:BreakWellbeing+
Format · LogisticsBreakA pacing or recovery block between sessions.
Evidence basisMediumRead from source
all eventCoffee BreakBreakWellbeing+
Format · LogisticsBreakA pacing or recovery block between sessions.
Evidence basisMediumRead from source
all eventDistributed Computing Architectures as a Solution to AI's Energy Crisis: Empirical Analysis of Decentralized TrainingTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
6:00 PMMON 14 JULUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
6:00 PMRegistration EastRegistrationLogistics+
Format · LogisticsRegistrationCheck-in and logistics, not agenda content.
Evidence basisMediumRead from source
3:00 PMICML Lounge Area:UnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:00 AMTutorial:TrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
10:30 AMAffinity Event:UnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
5:00 PMExpo Demonstration:DemoShowcase+
Format · Participant workDemoA hands-on or applied walkthrough that invites attendee questions and direct engagement.
Evidence basisMediumRead from source
8:00 PM(ends 8:00 PM)UnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
7:00 PMExpo Workshop:WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventBuilding Production Ready Agentic Systems: Architecture, LLM-based Evaluation, and GRPO TrainingTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
6:00 PMReception:ReceptionRelationship Building+
Format · LogisticsReceptionA social or hospitality block. Pacing and informal connection, not participant work.
Evidence basisMediumRead from source
all eventOpening Remarks and Welcome ReceptionOpening RemarksOrientation+
Format · BroadcastOpening RemarksFraming or welcome from the stage. Orients the room, not participatory.
Evidence basisMediumRead from source
8:00 PMTUE 15 JULUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
5:30 PMInvited Talk:PresentationKnowledge Transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisMediumRead from source
10:00 AM(ends 6:00 PM)UnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
6:00 PM[Oral 1A Alignment and Agents [10:00-11:00] ](https://icml.cc/virtual/2025/session/46894)PresentationKnowledge Transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisMediumRead from source
10:00-11:00[Oral 1A Alignment and Agents [ ] ](https://icml.cc/virtual/2025/session/46894)PresentationKnowledge Transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisMediumRead from source
10:00-11:00[10:00] Multi-agent Architecture Search via Agentic SupernetUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:00[ ] Multi-agent Architecture Search via Agentic SupernetUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:15[ ] Training a Generally Curious AgentTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
10:30[ ] Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:45[ ] CollabLLM: From Passive Responders to Active CollaboratorsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:00 AM[Oral 1B Positions: Better Ways to Do Machine Learning [10:00-11:00] ](https://icml.cc/virtual/2025/session/46895)PresentationKnowledge Transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisMediumRead from source
10:00-11:00[Oral 1B Positions: Better Ways to Do Machine Learning [ ] ](https://icml.cc/virtual/2025/session/46895)PresentationKnowledge Transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisMediumRead from source
10:00-11:00[10:00] Position: The AI Conference Peer Review Crisis Demands Author Feedback and Reviewer RewardsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:00[ ] Position: The AI Conference Peer Review Crisis Demands Author Feedback and Reviewer RewardsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:15[ ] Position: Not All Explanations for Deep Learning Phenomena Are Equally ValuableUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:30[ ] Position: Certified Robustness Does Not (Yet) Imply Model SecurityUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:45[ ] Position: Probabilistic Modelling is Sufficient for Causal InferenceUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:00 AM[Oral 1C Applications in Computer Vision [10:00-11:00] ](https://icml.cc/virtual/2025/session/46896)PresentationKnowledge Transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisMediumRead from source
10:00-11:00[Oral 1C Applications in Computer Vision [ ] ](https://icml.cc/virtual/2025/session/46896)PresentationKnowledge Transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisMediumRead from source
10:00-11:00[10:00] VideoRoPE: What Makes for Good Video Rotary Position Embedding?UnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:00[ ] VideoRoPE: What Makes for Good Video Rotary Position Embedding?UnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:15[ ] ReferSplat: Referring Segmentation in 3D Gaussian SplattingUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:30[ ] Orthogonal Subspace Decomposition for Generalizable AI-Generated Image DetectionUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:45[ ] VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video ModelsPresentationKnowledge Transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisMediumRead from source
11:00 AM[Oral 1D Learning Dynamics 1 [10:00-11:00] ](https://icml.cc/virtual/2025/session/46897)PresentationKnowledge Transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisMediumRead from source
10:00-11:00[Oral 1D Learning Dynamics 1 [ ] ](https://icml.cc/virtual/2025/session/46897)PresentationKnowledge Transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisMediumRead from source
10:00-11:00[10:00] Algorithm Development in Neural Networks: Insights from the Streaming Parity TaskUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:00[ ] Algorithm Development in Neural Networks: Insights from the Streaming Parity TaskUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:15[ ] Learning Dynamics in Continual Pre-Training for Large Language ModelsTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
10:30[ ] Strategy Coopetition Explains the Emergence and Transience of In-Context LearningUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:45[ ] Transformative or Conservative? Conservation laws for ResNets and TransformersUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:00 AM[Oral 1E Theory and Phenomenology [10:00-11:00] ](https://icml.cc/virtual/2025/session/46898)PresentationKnowledge Transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisMediumRead from source
10:00-11:00[Oral 1E Theory and Phenomenology [ ] ](https://icml.cc/virtual/2025/session/46898)PresentationKnowledge Transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisMediumRead from source
10:00-11:00[10:00] An analytic theory of creativity in convolutional diffusion modelsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:00[ ] An analytic theory of creativity in convolutional diffusion modelsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:15[ ] Layer by Layer: Uncovering Hidden Representations in Language ModelsPresentationKnowledge Transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisMediumRead from source
10:30[ ] Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural NetworksUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:45[ ] Emergence in non-neural models: grokking modular arithmetic via average gradient outer productUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:00 AM[Poster Session 1 East [11:00-1:30] ](https://icml.cc/virtual/2025/session/50263)Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
11:00-1:30[Poster Session 1 East [ ] ](https://icml.cc/virtual/2025/session/50263)Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventThe Disparate Benefits of Deep EnsemblesUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventRelative Error Fair Clustering in the Weak-Strong Oracle ModelUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventFDGen: A Fairness-Aware Graph Generation ModelUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventGHOST: Generalizable One-Shot Federated Graph Learning with Proxy-Based Topology Knowledge RetentionUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventCAN: Leveraging Clients As Navigators for Generative Replay in Federated Continual LearningUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventCape: Context-Aware Prompt Perturbation Mechanism with Differential PrivacyUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventPrivacy Amplification by Structured Subsampling for Deep Differentially Private Time Series ForecastingUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventTracking The Best Expert PrivatelyUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventPrivacy Amplification Through Synthetic Data: Insights from Linear RegressionUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventLayer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language ModelsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventPreference learning made easy: Everything should be understood through win rateUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventVision-Language Models Create Cross-Modal Task RepresentationsPresentationKnowledge Transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisMediumRead from source
all eventDetecting Strategic Deception with Linear ProbesUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventWhich Attention Heads Matter for In-Context Learning?UnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventTensor Product Neural Networks for Functional ANOVA ModelUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventFrom Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature SelectionUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventFast Estimation of Partial Dependence Functions using TreesUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventAxBench: Steering LLMs? Even Simple Baselines Outperform Sparse AutoencodersUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventOn the Interplay between Graph Structure and Learning Algorithms in Graph Neural NetworksUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventData-driven Design of Randomized Control Trials with Guaranteed Treatment EffectsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventSAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model InterpretabilityUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
The Full Reading
Why It Ranks This Way +
Calibrated from GES design 46/100 and verified 45/100, 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 Participation Architecture. Weakest signals: Follow Through, Network Design, and Evidence Maturity.
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.
- Add baseline measurement, comparison logic, tracking, or post-event impact reporting so effectiveness is not inferred only from format.
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.
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 Trade Show / Expo events scored on the same eight pillars.