Event owner lens
Use this record to benchmark whether a comparable event makes the work after the room visible. The score is 44/100, so the next move is to benchmark the weakest pillars before repeating the format.
action-oriented convening agenda analysis
ICML - WCA4Z Platform - Accelerating Legacy Code Modernization Using AI Agents, Deep Program Analysis, and - 2026 - Workshops - Journal Track Posters
This action-oriented convening in Technology / AI / Startup shows 80 visible agenda rows from icml.cc and scores 44/100: a moderate design signal with incomplete evidence. The clearest public signals sit in Learning Transfer and Personalization; the main limits are Follow Through and Network Design. Visible mechanisms include Participant work, Commitments, Feedback, and Network design. Follow-through or tracking is at least visible enough to inspect, though causal proof still depends on stronger evidence. A practical reading: For a reader, this is a comparison record more than a model to copy: it reads as an action-oriented convening, with the strongest visible signal in learning transfer and personalization 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 Learning Transfer, Personalization, and Problem Specificity; the thinnest visible pillars are Follow Through, Network Design, and Evidence Maturity. Visible mechanisms include Participant work, Commitments, Feedback, Network design, and Learning transfer. The extracted agenda preview includes 153 visible rows. The most common formats are Unknown, Presentation, and Training; the most common inferred purposes are Unknown, Knowledge Transfer, 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?45
Participation Architecture - 45/100. Participant work, contribution, interaction, and alternatives to passive broadcast.
Follow Through?16
Follow Through - 16/100. 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?52
Problem Specificity - 52/100. A clear costly problem, objective, decision, or performance target.
Personalization?61
Personalization - 61/100. Role, path, goal, preparation, or connection tailoring for participants.
Network Design?34
Network Design - 34/100. 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?75
Learning Transfer - 75/100. Applied practice, feedback, workplace use, refreshers, and 30-90 day transfer.
Evidence Maturity?35
Evidence Maturity - 35/100. 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?37
Future-of-Work Fit - 37/100. 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 (16/100)
Exercises that strengthen it: Mental Toughness Workshop • WorkshopBank · 15% Solutions • WorkshopBank · Network Patches
Network Design (34/100)
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 (45/100)
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
14 percent of the 153 classified blocks put participants to work; the rest broadcast, show, or handle logistics. That mix is what drives the participation score.
Participant workBroadcastShowcaseLogistics
all 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 eventPosition Paper 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 eventJournal Track 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
all eventExpo Talks, Demos, and WorkshopsWorkshopParticipant work+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisParticipant work is implied by the formatInferred from format
all eventReasoning-Driven Synthetic Data Generation and EvaluationPresentationKnowledge 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 AM - 12:15 PMJul 7, HALL APresentationKnowledge 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 eventBM^2: Coupled Schrödinger Bridge MatchingPresentationKnowledge 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 PM - 6:45 PMJul 8, HALL APresentationKnowledge 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 eventRepositioning the Subject within ImagePresentationKnowledge 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 PM - 6:45 PMJul 9, HALL APresentationKnowledge 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 eventStethoLM: Audio Language Model for Cardiopulmonary Analysis Across Clinical TasksWorkshopParticipant 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 eventLumiNet: Perception-Driven Knowledge Distillation via Statistical Logit CalibrationPresentationKnowledge 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 eventPruneFuse: Efficient Data Selection via Weight Pruning and Network FusionPresentationKnowledge 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 eventDuFal: Dual-Frequency-Aware Learning for High-Fidelity Extremely Sparse-view CBCT ReconstructionPresentationKnowledge 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 eventMoFO: Momentum-Filtered Optimizer for Mitigating Forgetting in LLM Fine-TuningPresentationKnowledge 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 eventSegmentation From Attention: Training-Free Layer Selection and One-Shot Tuning for Segmentation in VLMsTrainingSkill 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 eventmSOP-765k: A Benchmark For Multi-Modal Structured Output PredictionsPresentationKnowledge 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 eventPrompt Estimation from Prototypes for Federated Prompt Tuning of Vision 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
all eventDesigning a Conditional Prior Distribution for Flow-Based Generative 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 eventG2D2: Gradient-Guided Discrete Diffusion for Inverse Problem SolvingPresentationKnowledge 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 eventCollaborative likelihood-ratio estimation over graphsWorkshopParticipant 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 eventSE3Set: Harnessing Equivariant Hypergraph Neural Networks for Molecular Representation 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 eventProcess Reward Models That ThinkPresentationKnowledge 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 eventToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural PruningPresentationKnowledge 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 eventMixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text SourcesTrainingSkill 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 eventBeyond Accuracy: What Matters in Designing Well-Behaved Image Classification Models?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 eventOptimization Dynamics of Equivariant and Augmented 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 eventThe Choice of Normalization Influences Shrinkage in Regularized RegressionPresentationKnowledge 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 eventUnderstanding Deep Representation Learning via Layerwise Feature Compression and DiscriminationPresentationKnowledge 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 eventMulti-Accurate CATE is Robust to Unknown Covariate ShiftsPresentationKnowledge 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 eventLO-BCQ: Locally Optimal Block Clustered Quantization for 4-bit (W4A4) LLM 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
all eventReinforcement Learning from Human Feedback with Active QueriesPresentationKnowledge 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 eventUCB Exploration for Fixed-Budget Bayesian Best Arm IdentificationPresentationKnowledge 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 eventLearning multi-modal generative models with permutation-invariant encoders and tighter variational objectivesPresentationKnowledge 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 eventPhysics-Aware Spatiotemporal Causal Graph Network for Forecasting with Limited DataPresentationKnowledge 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 eventBiSSL: Enhancing the Alignment Between Self-Supervised Pretraining and Downstream Fine-Tuning via Bilevel OptimizationTrainingSkill 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 eventHierarchical Filtering and Refinement Classification for Few-Shot Class-Incremental 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 eventExpert Routing with Synthetic Data for Domain Incremental 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 eventProbabilistic Pretraining for Improved Neural RegressionTrainingSkill 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 eventRetrospective Feature Estimation for 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 eventRethinking Memory in Continual Learning: Beyond a Monolithic Store of the PastPresentationKnowledge 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 eventInvestigating Continual Pretraining in Large Language Models: Insights and ImplicationsTrainingSkill 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 eventLocalize-and-Stitch: Efficient Model Merging via Sparse Task ArithmeticPresentationKnowledge 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 eventA novel statistical approach to analyze 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
all eventOptimization with Access to Auxiliary InformationPresentationKnowledge 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 eventRouteFinder: Towards Foundation Models for Vehicle Routing ProblemsPresentationKnowledge 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 event(De)-regularized Maximum Mean Discrepancy Gradient FlowPresentationKnowledge 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 Convergence of Adaptive Gradient Methods for Nonconvex OptimizationPresentationKnowledge 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 eventExploiting Hankel-Toeplitz Structures for Fast Computation of Kernel Precision MatricesPresentationKnowledge 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 eventPyPop7: A Pure-Python Library for Population-Based Black-Box OptimizationPresentationKnowledge 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 eventExtending Mean-Field Variational Inference via Entropic Regularization: Theory and ComputationPresentationKnowledge 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 eventZono-Conformal Prediction: Zonotope-Based Uncertainty Quantification for Regression and Classification TasksPresentationKnowledge 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 eventDiffusion posterior sampling for simulation-based inference in tall data settingsPoster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all eventEfficient and Unbiased Sampling from Boltzmann Distributions via Variance-Tuned 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
all eventDemystifying MaskGIT Sampler and Beyond: Adaptive Order Selection in Masked DiffusionPresentationKnowledge 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 eventNot All Rollouts are Useful: Down-Sampling Rollouts in LLM 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
all eventComparing Deterministic and Soft Policy Gradients for Optimizing Gaussian Mixture ActorsPresentationKnowledge 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 eventReinforcement Learning from Bagged RewardPresentationKnowledge 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 eventSynthesizing world models for bilevel planningPresentationKnowledge 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 eventOptimizing Return Distributions with Distributional Dynamic ProgrammingPresentationKnowledge 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 eventWikipedia in the Era of LLMs: Evolution and RisksPresentationKnowledge 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 eventSelective Concept Bottleneck Models Without Predefined ConceptsPresentationKnowledge 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 eventFedLog: Personalized Federated Classification with Less Communication and More FlexibilityPresentationKnowledge 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 eventRandom Erasing vs. Model Inversion: A Promising Defense or a False Hope?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 eventDifferentially Private and Scalable Estimation of the Network Principal ComponentWorkshopParticipant 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 eventDecoding Safety Feedback from Diverse Raters: A Data-driven Lens on Responsiveness to SeverityPresentationKnowledge 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 eventEarly Directional Convergence in Deep Homogeneous Neural Networks for Small InitializationsPresentationKnowledge 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 eventStatistical Impossibility and Possibility of Aligning LLMs with Human Preferences: From Condorcet Paradox to Nash EquilibriumPresentationKnowledge 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 eventStatistical-Computational Trade-offs for Recursive Adaptive Partitioning EstimatorsPresentationKnowledge 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 eventMeta-Learning with Generalized Ridge Regression: High-dimensional Asymptotics, Optimality and Hyper-covariance 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
all eventPrecise Asymptotics of Bagging Regularized M-estimatorsPresentationKnowledge 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 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 eventPosition Paper PostersPoster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventJournal Track 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
all eventExpo Talks, Demos, and WorkshopsWorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventReasoning-Driven Synthetic Data Generation and EvaluationUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
10:30 AM - 12:15 PMJul 7, HALL AUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
all eventView full detailsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventBM^2: Coupled Schrödinger Bridge MatchingUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
5:00 PM - 6:45 PMJul 8, HALL AUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
all eventA Schrödinger bridge establishes a dynamic transport map between two target distributions via a reference process, simultaneously solving an associated entropic optimal transport problem. We consider the setting where samples from the target distributions are available, and the reference diffusion process admits tractable dynamics. We thus introduce Coupled Bridge Matching (BM2), a simple \emph{non-iterative} approach for learning Schrödinger bridges with neural networks. A preliminary theoretical analysis of the convergence properties of BM2 is carried out, supported by numerical experiments that demonstrate the effectiveness of our proposal.DemoShowcase+
Format · Participant workDemoA hands-on or applied walkthrough that invites attendee questions and direct engagement.
Evidence basisMediumRead from source
all eventRepositioning the Subject within ImageUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
5:00 PM - 6:45 PMJul 9, HALL AUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
all eventStethoLM: Audio Language Model for Cardiopulmonary Analysis Across Clinical TasksWorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventTimeAutoDiff: A Unified Framework for Generation, Imputation, Forecasting, and Time-Varying Metadata Conditioning of Heterogeneous Time Series Tabular DataUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventLumiNet: Perception-Driven Knowledge Distillation via Statistical Logit CalibrationUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventPruneFuse: Efficient Data Selection via Weight Pruning and Network FusionUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventDuFal: Dual-Frequency-Aware Learning for High-Fidelity Extremely Sparse-view CBCT ReconstructionUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventMoFO: Momentum-Filtered Optimizer for Mitigating Forgetting in LLM Fine-TuningUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventSegmentation From Attention: Training-Free Layer Selection and One-Shot Tuning for Segmentation in VLMsTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
all eventmSOP-765k: A Benchmark For Multi-Modal Structured Output PredictionsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventPrompt Estimation from Prototypes for Federated Prompt Tuning of Vision TransformersUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventDesigning a Conditional Prior Distribution for Flow-Based Generative ModelsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventG2D2: Gradient-Guided Discrete Diffusion for Inverse Problem SolvingUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventCollaborative likelihood-ratio estimation over graphsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventSE3Set: Harnessing Equivariant Hypergraph Neural Networks for Molecular Representation LearningPresentationKnowledge Transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisMediumRead from source
all eventProcess Reward Models That ThinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventSEM-CTRL: Semantically Controlled DecodingUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural PruningUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventMixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text SourcesTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
all eventBeyond Accuracy: What Matters in Designing Well-Behaved Image Classification Models?UnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventOptimization Dynamics of Equivariant and Augmented Neural NetworksUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventThe Choice of Normalization Influences Shrinkage in Regularized RegressionUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventUnderstanding Deep Representation Learning via Layerwise Feature Compression and DiscriminationPresentationKnowledge Transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisMediumRead from source
all eventMulti-Accurate CATE is Robust to Unknown Covariate ShiftsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventLO-BCQ: Locally Optimal Block Clustered Quantization for 4-bit (W4A4) LLM InferenceUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventReinforcement Learning from Human Feedback with Active QueriesUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventUCB Exploration for Fixed-Budget Bayesian Best Arm IdentificationUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventLearning multi-modal generative models with permutation-invariant encoders and tighter variational objectivesUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventRiemannian Generative DecoderUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventPhysics-Aware Spatiotemporal Causal Graph Network for Forecasting with Limited DataUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventBiSSL: Enhancing the Alignment Between Self-Supervised Pretraining and Downstream Fine-Tuning via Bilevel OptimizationTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
all eventHierarchical Filtering and Refinement Classification for Few-Shot Class-Incremental LearningUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventExpert Routing with Synthetic Data for Domain Incremental LearningUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventProbabilistic Pretraining for Improved Neural RegressionTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
all eventRetrospective Feature Estimation for Continual LearningUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventRethinking Memory in Continual Learning: Beyond a Monolithic Store of the PastUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventInvestigating Continual Pretraining in Large Language Models: Insights and ImplicationsTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
all eventLocalize-and-Stitch: Efficient Model Merging via Sparse Task ArithmeticUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventA novel statistical approach to analyze image classificationUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventOptimization with Access to Auxiliary InformationUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventRouteFinder: Towards Foundation Models for Vehicle Routing ProblemsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all event(De)-regularized Maximum Mean Discrepancy Gradient FlowUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventOn the Convergence of Adaptive Gradient Methods for Nonconvex OptimizationUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventExploiting Hankel-Toeplitz Structures for Fast Computation of Kernel Precision MatricesUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventPyPop7: A Pure-Python Library for Population-Based Black-Box OptimizationUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventExtending Mean-Field Variational Inference via Entropic Regularization: Theory and ComputationUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventZono-Conformal Prediction: Zonotope-Based Uncertainty Quantification for Regression and Classification TasksUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventDiffusion posterior sampling for simulation-based inference in tall data settingsPoster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventEfficient and Unbiased Sampling from Boltzmann Distributions via Variance-Tuned Diffusion ModelsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventDemystifying MaskGIT Sampler and Beyond: Adaptive Order Selection in Masked DiffusionUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventNot All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement LearningUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventComparing Deterministic and Soft Policy Gradients for Optimizing Gaussian Mixture ActorsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventReinforcement Learning from Bagged RewardUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventReturn-Aligned Decision TransformerUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventSynthesizing world models for bilevel planningUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventOptimizing Return Distributions with Distributional Dynamic ProgrammingUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventPreserving Expert-Level Privacy in Offline Reinforcement LearningUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventWikipedia in the Era of LLMs: Evolution and RisksUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventSelective Concept Bottleneck Models Without Predefined ConceptsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventFedLog: Personalized Federated Classification with Less Communication and More FlexibilityUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventRandom Erasing vs. Model Inversion: A Promising Defense or a False Hope?UnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventDifferentially Private and Scalable Estimation of the Network Principal ComponentUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventDecoding Safety Feedback from Diverse Raters: A Data-driven Lens on Responsiveness to SeverityUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventEarly Directional Convergence in Deep Homogeneous Neural Networks for Small InitializationsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventStatistical Impossibility and Possibility of Aligning LLMs with Human Preferences: From Condorcet Paradox to Nash EquilibriumUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventStatistical-Computational Trade-offs for Recursive Adaptive Partitioning EstimatorsUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventMeta-Learning with Generalized Ridge Regression: High-dimensional Asymptotics, Optimality and Hyper-covariance EstimationUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventPrecise Asymptotics of Bagging Regularized M-estimatorsUnknownUnknown+
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 45/100 and verified 44/100 with no fourth-loop cap.
Reader Takeaway. For a reader, this is a comparison record more than a model to copy: it reads as an action-oriented convening, with the strongest visible signal in learning transfer and personalization and the biggest open question around follow through and network design. The practical test is whether the published agenda connects the room to post-event continuation and evidence.
Strongest signals: Learning Transfer, Personalization, and Problem Specificity. 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 label the source boundary clearly before ranking the record before ranking or syndicating the record.
What GES Means Here +
The Gathering Effectiveness Score is a strict 0-100 public-evidence reading of the agenda across eight pillars. It rewards visible participant work, follow-through, transfer, network design, and proof mechanisms more than polish, speaker fame, attendance, or satisfaction.
Visible mechanisms: Participant work, Commitments, 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
- Passive stage formats dominate the visible agenda.
- No baseline measurement is visible.
Score caps
- No fourth-loop score cap applied.
Review flags
- Satisfaction/NPS signal found, but it is excluded from effectiveness scoring.
- 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.
Embed the verified badge +
This record is in the hand-verified gold set. Copy the snippet below to embed the verified badge on your own site.
<a href="https://unitedwetransform.com/events/evt_2026_icml_wca4z_platform_accelerating_legacy_code_modernization_using_ai_agents_b117ef"><img src="https://unitedwetransform.com/badge/ges-verified.svg" alt="GES verified by United We Transform" height="40"></a>Where To Go Next
Compare this agenda against other Technology / AI / Startup events scored on the same eight pillars.