Event owner lens
Use this record to benchmark whether a comparable event makes the work after the room visible. The score is 41/100, so the next move is to benchmark the weakest pillars before repeating the format.
broadcast-heavy conference agenda analysis
ICML - WCA4Z Platform - Accelerating Legacy Code Modernization Using AI Agents, Deep Program Analysis, and - Workshops - Tiny Titans: The next wave...
This broadcast-heavy conference in Technology / AI / Startup shows 51 visible agenda rows from icml.cc and scores 41/100: 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, 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 a comparison record more than a model to copy: it reads as a broadcast-heavy conference, 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 Personalization. Visible mechanisms include Participant work, Network design, and Learning transfer. The extracted agenda preview includes 98 visible rows. The most common formats are Unknown, Presentation, and Keynote; 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?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?40
Problem Specificity - 40/100. A clear costly problem, objective, decision, or performance target.
Personalization?33
Personalization - 33/100. Role, path, goal, preparation, or connection tailoring for participants.Missing: Create role-based paths, prepared questions, tailored breakouts, or participant-specific next steps.
Network Design?30
Network Design - 30/100. Structured weak ties, bridge-building, mixers, and relationship persistence.Missing: Replace generic networking blocks with designed introductions, ask-offer exchanges, peer groups, or bridge-building rituals.
Learning Transfer?63
Learning Transfer - 63/100. Applied practice, feedback, workplace use, refreshers, and 30-90 day transfer.
Evidence Maturity?45
Evidence Maturity - 45/100. Baseline, comparison, follow-up, isolation, and attribution confidence.
Future-of-Work Fit?67
Future-of-Work Fit - 67/100. 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 (30/100)
Exercises that strengthen it: Fun Trust-Building Group Game for Team Connection - Izzat... · Exciting Group Trust Activity for Building Confidence... · PFP: September 2005
Personalization (33/100)
Exercises that strengthen it: Journey Mapping • WorkshopBank · Group Energiser & Perspective-Changing Exercise - Paradigm... · Photo Storytelling
Agenda Preview
The actual agenda we captured. Every block is classified by format and purpose. Open any block to see how we read it; the colored edge shows whether it is participant work, broadcast, logistics, or a showcase.
Room vs wrapper
13 percent of the 98 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
all eventWorkshopWorkshopParticipant work+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisParticipant work is implied by the formatInferred from format
8:30 AMIntroduction from Organizers Stefanos Laskaridis VideoPresentationKnowledge 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
8:45 AMInvited Keynote #1 Zechun Liu Video LinkKeynoteExpert framing+
Format · BroadcastKeynoteA featured talk from the stage. Builds awareness and energy, produces no participant output on its own.
Evidence basisNo participant output visible from this rowRead from source, no work signal
9:30 AMToo Big to Think: Capacity, Memorization, and Generalization in Pre-Trained Transformers Joshua Barron ⋅ Devin White Video LinkPresentationKnowledge 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
9:45 AMKinetics: Rethinking Test-Time Scaling Laws Ranajoy Sadhukhan ⋅ Zhuoming Chen ⋅ Haizhong Zheng ⋅ Yang Zhou ⋅ Emma Strubell ⋅ Beidi Chen Video LinkPresentationKnowledge 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 AMCoffee breakBreakPacing+
Format · LogisticsBreakA pacing or recovery block between sessions.
Evidence basisOutcome inferred from formatInferred from format
10:15 AMInvited Keynote #2 Dan Alistarh Video LinkKeynoteExpert framing+
Format · BroadcastKeynoteA featured talk from the stage. Builds awareness and energy, produces no participant output on its own.
Evidence basisNo participant output visible from this rowRead from source, no work signal
11:00 AMPreserve then Quantize: Dominant-Subspace Guided Low-Rank Reconstruction Yoonjun Cho ⋅ Dongjae Jeon ⋅ Soeun Kim ⋅ Albert No Video LinkPresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
11:15 AMWhisperKit: On-device Real-time ASR with Billion-Scale Transformers Berkin Durmus ⋅ Arda Okan ⋅ Eduardo Pacheco ⋅ Zach Nagengast ⋅ Atila Orhon Video LinkPresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
11:30 AMInvited Keynote #3 Song Han VideoKeynoteExpert framing+
Format · BroadcastKeynoteA featured talk from the stage. Builds awareness and energy, produces no participant output on its own.
Evidence basisNo participant output visible from this rowRead from source, no work signal
1:00 PMRandomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation for Federated Learning Grigory Malinovsky ⋅ Umberto Michieli ⋅ Hasan Hammoud ⋅ Taha Ceritli ⋅ Hayder Elesedy ⋅ Mete Ozay ⋅ Peter Richtarik LinkPresentationKnowledge 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
1:00 PMUnlocking the Potential of Extremely Low-Bit Sparse Transformers through Adaptive Multi-bit Supermasks and Random Weights Yasuyuki Okoshi ⋅ Hikari Otsuka ⋅ Junnosuke Suzuki ⋅ Daichi Fujiki ⋅ Masato Motomura LinkPresentationKnowledge 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
1:00 PMAddition is almost all you need: Compressing neural networks with double binary factorization Vladimír Boža ⋅ Vladimír Macko LinkPresentationKnowledge 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
1:00 PMCapability Transfer from Large to Small Models with Synthetically-Generated Data Lillian Sun ⋅ Emma Yang ⋅ Arif Dayi LinkPresentationKnowledge 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
1:00 PMTensorSLM: Energy-efficient Embedding Compression of Sub-billion Parameter Language Models on Low-end Devices Mingxue Xu ⋅ Yao Lei Xu ⋅ Danilo Mandic LinkPresentationKnowledge 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
1:00 PMLeveraging Coordinate Momentum in SignSGD and Muon: Memory-Optimized Zero-Order LLM Fine-Tuning Egor Petrov ⋅ Evseev Grigoriy ⋅ Aleksey Antonov ⋅ Andrey Veprikov ⋅ Pavel Plyusnin ⋅ Nikolay Bushkov ⋅ Stanislav Moiseev ⋅ Aleksandr Beznosikov LinkPresentationKnowledge 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
1:00 PMHigher Acceptance Rates for Speculative Decoding with Randomised Drafting William Toner ⋅ Martin Asenov ⋅ Rajkarn Singh ⋅ Artjom Joosen LinkPresentationKnowledge 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
1:00 PMZoop it! Efficient Zero-Order Optimization with Output Perturbation Xixi Hu ⋅ Bo Liu ⋅ qiang liu ⋅ Xiaocong Du ⋅ Bhargav Bhushanam ⋅ Louis Feng ⋅ Chengyue Gong ⋅ Kaizhao Liang LinkPresentationKnowledge 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
1:00 PMMatMuls are Enough for Efficient and Performant Linear-Time Attention Andrew Argatkiny ⋅ Ilya Makarov LinkPresentationKnowledge 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
1:00 PMZeroth-Order Optimization is Secretly Single-Step Policy Optimization Junbin Qiu ⋅ Zhengpeng Xie ⋅ Xiangda Yan ⋅ Yongjie Yang ⋅ Yao Shu LinkPresentationKnowledge 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
1:00 PMSpec-LLaVA: Accelerating Vision-Language Models with Dynamic Tree-Based Speculative Decoding Mingxiao Huo ⋅ Jiayi Zhang ⋅ Hewei Wang ⋅ Jinfeng Xu ⋅ Zheyu Chen ⋅ Huilin Tai ⋅ Ian Chen LinkPresentationKnowledge 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
1:00 PMLoFT: Low-Rank Adaptation That Behaves Like Full Fine-Tuning Nurbek Tastan ⋅ Stefanos Laskaridis ⋅ Martin Takac ⋅ Karthik Nandakumar ⋅ Samuel Horváth LinkPresentationKnowledge 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
1:00 PMFRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training Filipp Zmushko ⋅ Aleksandr Beznosikov ⋅ Martin Takac ⋅ Samuel Horváth LinkWorkshopSkill building+
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
1:00 PMTowards understanding of orthogonalization in Muon Valentyn Boreiko ⋅ Zhiqi Bu ⋅ Sheng Zha LinkPresentationKnowledge 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
1:00 PMPoster Session #1Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
1:30 PMInvited Keynote #4 Fartash Faghri LinkKeynoteExpert framing+
Format · BroadcastKeynoteA featured talk from the stage. Builds awareness and energy, produces no participant output on its own.
Evidence basisNo participant output visible from this rowRead from source, no work signal
2:15 PMOffloaded Reasoning: Efficient Inference for Large Language Models via Modular Reasoning and Refinement Ishan Jindal ⋅ Jayant Taneja ⋅ Badrinath chandana ⋅ Vikas Kapur ⋅ SACHIN SHARMA LinkPresentationKnowledge 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
2:30 PMEnhancing Reasoning Capabilities of Small Language Models with Blueprints and Prompt Template Search Dongge Han ⋅ Menglin Xia ⋅ Daniel Madrigal ⋅ Samuel Kessler ⋅ Ankur Mallick ⋅ Xuchao Zhang ⋅ Mirian Hipolito Garcia ⋅ Jin Xu ⋅ Victor Ruehle ⋅ Saravan...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
3:00 PMFGFP: A Fractional Gaussian Filter and Pruning for Deep Neural Networks Compression Kuan-Ting Tu ⋅ Po-Hsien Yu ⋅ Yu-Syuan Tseng ⋅ Shao-Yi Chien LinkPresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
3:00 PMGatekeeper: Improving Model Cascades Through Confidence Tuning Stephan Rabanser ⋅ Nathalie Rauschmayr ⋅ Achin Kulshrestha ⋅ Petra Poklukar ⋅ Wittawat Jitkrittum ⋅ Sean Augenstein ⋅ Congchao Wang ⋅ Federico Tombari LinkPresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
3:00 PMDiffusionBlocks: Continuous-Time Blockwise Training Through Score-Based Diffusion Models Makoto Shing ⋅ Takuya Akiba LinkTrainingSkill 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
3:00 PMCompression of Large Language Models by Neuron Summary Yancheng Wang ⋅ Dongfang Sun ⋅ Yingzhen Yang LinkPresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
3:00 PMPredictive Scheduling for Efficient Inference-Time Reasoning in Large Language Models Katrina Brown ⋅ Aneesh Muppidi ⋅ Rana Shahout LinkPresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
3:00 PMFAST: Federated Active Learning with Foundation Models for Communication-efficient Sampling and Training Haoyuan Li ⋅ Mathias Funk ⋅ Jindong Wang ⋅ Aaqib Saeed LinkTrainingSkill 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
3:00 PMOvercoming label shift in targeted federated learning Adam Breitholtz ⋅ Edvin Listo Zec ⋅ Fredrik Johansson LinkWorkshopParticipant 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
3:00 PMToken-Efficient RL for LLM Reasoning Alan Lee ⋅ Harry Tong LinkPresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
3:00 PMDynamic Guardian Models: Realtime Content Moderation With User-Defined Policies Monte Hoover ⋅ Vatsal Baherwani ⋅ Neel Jain ⋅ Khalid Saifullah ⋅ Joseph Vincent ⋅ Chirag Jain ⋅ Melissa Rad ⋅ C. Bayan Bruss ⋅ Ashwinee Panda ⋅ Tom Goldstein LinkPresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
3:00 PMFirst Provable Guarantees for Practical Private FL: Beyond Restrictive Assumptions Egor Shulgin ⋅ Grigory Malinovsky ⋅ Sarit Khirirat ⋅ Peter Richtarik LinkPresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
3:00 PMLion Cub: Minimizing Communication Overhead in Distributed Lion Satoki Ishikawa ⋅ Tal Ben-Nun ⋅ Brian Van Essen ⋅ Rio Yokota ⋅ Nikoli Dryden LinkPresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
3:00 PMSPAM: Stochastic Proximal Point Method with Momentum Variance Reduction for Non-convex Cross-Device Federated Learning Avetik Karagulyan ⋅ Egor Shulgin ⋅ Abdurakhmon Sadiev ⋅ Peter Richtarik LinkPresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
3:00 PMPoster Session #2Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
3:30 PMInvited Keynote #5 Kangwook Lee Video LinkKeynoteExpert framing+
Format · BroadcastKeynoteA featured talk from the stage. Builds awareness and energy, produces no participant output on its own.
Evidence basisNo participant output visible from this rowRead from source, no work signal
4:15 PMBest Paper/Poster Awards Samuel Horváth VideoPoster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
4:30 PMPanel Session Kangwook Lee ⋅ Zechun Liu ⋅ Fartash Faghri VideoPanelDiscussion+
Format · BroadcastPanelExperts discuss while the audience watches. Surfaces perspective but rarely creates participant work.
Evidence basisNo participant output visible from this rowRead from source, no work signal
all eventTutorialsTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
all eventMain ConferenceUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead 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
all eventCommunityUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventRocketChat Desktop ClientUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventWorkshopWorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventTimezone: America/LosAngelesUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
8:30 AMIntroduction from Organizers Stefanos Laskaridis VideoUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
8:45 AMInvited Keynote #1 Zechun Liu Video LinkKeynoteThought Leadership+
Format · BroadcastKeynoteA featured talk from the stage. Builds awareness and energy, produces no participant output on its own.
Evidence basisMediumRead from source
9:30 AMToo Big to Think: Capacity, Memorization, and Generalization in Pre-Trained Transformers Joshua Barron ⋅ Devin White Video LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
9:45 AMKinetics: Rethinking Test-Time Scaling Laws Ranajoy Sadhukhan ⋅ Zhuoming Chen ⋅ Haizhong Zheng ⋅ Yang Zhou ⋅ Emma Strubell ⋅ Beidi Chen Video LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
10:00 AMCoffee breakBreakWellbeing+
Format · LogisticsBreakA pacing or recovery block between sessions.
Evidence basisMediumRead from source
10:15 AMInvited Keynote #2 Dan Alistarh Video LinkKeynoteThought Leadership+
Format · BroadcastKeynoteA featured talk from the stage. Builds awareness and energy, produces no participant output on its own.
Evidence basisMediumRead from source
11:00 AMPreserve then Quantize: Dominant-Subspace Guided Low-Rank Reconstruction Yoonjun Cho ⋅ Dongjae Jeon ⋅ Soeun Kim ⋅ Albert No Video LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:15 AMWhisperKit: On-device Real-time ASR with Billion-Scale Transformers Berkin Durmus ⋅ Arda Okan ⋅ Eduardo Pacheco ⋅ Zach Nagengast ⋅ Atila Orhon Video LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
11:30 AMInvited Keynote #3 Song Han VideoKeynoteThought Leadership+
Format · BroadcastKeynoteA featured talk from the stage. Builds awareness and energy, produces no participant output on its own.
Evidence basisMediumRead from source
1:00 PMRandomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation for Federated Learning Grigory Malinovsky ⋅ Umberto Michieli ⋅ Hasan Hammoud ⋅ Taha Ceritli ⋅ Hayder Elesedy ⋅ Mete Ozay ⋅ Peter Richtarik LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
1:00 PMUnlocking the Potential of Extremely Low-Bit Sparse Transformers through Adaptive Multi-bit Supermasks and Random Weights Yasuyuki Okoshi ⋅ Hikari Otsuka ⋅ Junnosuke Suzuki ⋅ Daichi Fujiki ⋅ Masato Motomura LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
1:00 PMAddition is almost all you need: Compressing neural networks with double binary factorization Vladimír Boža ⋅ Vladimír Macko LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
1:00 PMCapability Transfer from Large to Small Models with Synthetically-Generated Data Lillian Sun ⋅ Emma Yang ⋅ Arif Dayi LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
1:00 PMTensorSLM: Energy-efficient Embedding Compression of Sub-billion Parameter Language Models on Low-end Devices Mingxue Xu ⋅ Yao Lei Xu ⋅ Danilo Mandic LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
1:00 PMLeveraging Coordinate Momentum in SignSGD and Muon: Memory-Optimized Zero-Order LLM Fine-Tuning Egor Petrov ⋅ Evseev Grigoriy ⋅ Aleksey Antonov ⋅ Andrey Veprikov ⋅ Pavel Plyusnin ⋅ Nikolay Bushkov ⋅ Stanislav Moiseev ⋅ Aleksandr Beznosikov LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
1:00 PMHigher Acceptance Rates for Speculative Decoding with Randomised Drafting William Toner ⋅ Martin Asenov ⋅ Rajkarn Singh ⋅ Artjom Joosen LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
1:00 PMZoop it! Efficient Zero-Order Optimization with Output Perturbation Xixi Hu ⋅ Bo Liu ⋅ qiang liu ⋅ Xiaocong Du ⋅ Bhargav Bhushanam ⋅ Louis Feng ⋅ Chengyue Gong ⋅ Kaizhao Liang LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
1:00 PMMatMuls are Enough for Efficient and Performant Linear-Time Attention Andrew Argatkiny ⋅ Ilya Makarov LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
1:00 PMZeroth-Order Optimization is Secretly Single-Step Policy Optimization Junbin Qiu ⋅ Zhengpeng Xie ⋅ Xiangda Yan ⋅ Yongjie Yang ⋅ Yao Shu LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
1:00 PMSpec-LLaVA: Accelerating Vision-Language Models with Dynamic Tree-Based Speculative Decoding Mingxiao Huo ⋅ Jiayi Zhang ⋅ Hewei Wang ⋅ Jinfeng Xu ⋅ Zheyu Chen ⋅ Huilin Tai ⋅ Ian Chen LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
1:00 PMLoFT: Low-Rank Adaptation That Behaves Like Full Fine-Tuning Nurbek Tastan ⋅ Stefanos Laskaridis ⋅ Martin Takac ⋅ Karthik Nandakumar ⋅ Samuel Horváth LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
1:00 PMFRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training Filipp Zmushko ⋅ Aleksandr Beznosikov ⋅ Martin Takac ⋅ Samuel Horváth LinkTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
1:00 PMTowards understanding of orthogonalization in Muon Valentyn Boreiko ⋅ Zhiqi Bu ⋅ Sheng Zha LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
1:00 PMPoster Session #1Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
1:30 PMInvited Keynote #4 Fartash Faghri LinkKeynoteThought Leadership+
Format · BroadcastKeynoteA featured talk from the stage. Builds awareness and energy, produces no participant output on its own.
Evidence basisMediumRead from source
2:15 PMOffloaded Reasoning: Efficient Inference for Large Language Models via Modular Reasoning and Refinement Ishan Jindal ⋅ Jayant Taneja ⋅ Badrinath chandana ⋅ Vikas Kapur ⋅ SACHIN SHARMA LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
2:30 PMEnhancing Reasoning Capabilities of Small Language Models with Blueprints and Prompt Template Search Dongge Han ⋅ Menglin Xia ⋅ Daniel Madrigal ⋅ Samuel Kessler ⋅ Ankur Mallick ⋅ Xuchao Zhang ⋅ Mirian Hipolito Garcia ⋅ Jin Xu ⋅ Victor Ruehle ⋅ Saravan Rajmohan Video LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
3:00 PMFGFP: A Fractional Gaussian Filter and Pruning for Deep Neural Networks Compression Kuan-Ting Tu ⋅ Po-Hsien Yu ⋅ Yu-Syuan Tseng ⋅ Shao-Yi Chien LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
3:00 PMGatekeeper: Improving Model Cascades Through Confidence Tuning Stephan Rabanser ⋅ Nathalie Rauschmayr ⋅ Achin Kulshrestha ⋅ Petra Poklukar ⋅ Wittawat Jitkrittum ⋅ Sean Augenstein ⋅ Congchao Wang ⋅ Federico Tombari LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
3:00 PMDiffusionBlocks: Continuous-Time Blockwise Training Through Score-Based Diffusion Models Makoto Shing ⋅ Takuya Akiba LinkTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
3:00 PMCompression of Large Language Models by Neuron Summary Yancheng Wang ⋅ Dongfang Sun ⋅ Yingzhen Yang LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
3:00 PMPredictive Scheduling for Efficient Inference-Time Reasoning in Large Language Models Katrina Brown ⋅ Aneesh Muppidi ⋅ Rana Shahout LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
3:00 PMFAST: Federated Active Learning with Foundation Models for Communication-efficient Sampling and Training Haoyuan Li ⋅ Mathias Funk ⋅ Jindong Wang ⋅ Aaqib Saeed LinkTrainingSkill Building+
Format · Participant workTrainingGuided skill building where participants practice. Counts as participant work and learning transfer.
Evidence basisMediumRead from source
3:00 PMOvercoming label shift in targeted federated learning Adam Breitholtz ⋅ Edvin Listo Zec ⋅ Fredrik Johansson LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
3:00 PMToken-Efficient RL for LLM Reasoning Alan Lee ⋅ Harry Tong LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
3:00 PMDynamic Guardian Models: Realtime Content Moderation With User-Defined Policies Monte Hoover ⋅ Vatsal Baherwani ⋅ Neel Jain ⋅ Khalid Saifullah ⋅ Joseph Vincent ⋅ Chirag Jain ⋅ Melissa Rad ⋅ C. Bayan Bruss ⋅ Ashwinee Panda ⋅ Tom Goldstein LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
3:00 PMFirst Provable Guarantees for Practical Private FL: Beyond Restrictive Assumptions Egor Shulgin ⋅ Grigory Malinovsky ⋅ Sarit Khirirat ⋅ Peter Richtarik LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
3:00 PMLion Cub: Minimizing Communication Overhead in Distributed Lion Satoki Ishikawa ⋅ Tal Ben-Nun ⋅ Brian Van Essen ⋅ Rio Yokota ⋅ Nikoli Dryden LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
3:00 PMSPAM: Stochastic Proximal Point Method with Momentum Variance Reduction for Non-convex Cross-Device Federated Learning Avetik Karagulyan ⋅ Egor Shulgin ⋅ Abdurakhmon Sadiev ⋅ Peter Richtarik LinkUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
3:00 PMPoster Session #2Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
3:30 PMInvited Keynote #5 Kangwook Lee Video LinkKeynoteThought Leadership+
Format · BroadcastKeynoteA featured talk from the stage. Builds awareness and energy, produces no participant output on its own.
Evidence basisMediumRead from source
4:15 PMBest Paper/Poster Awards Samuel Horváth VideoPoster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
4:30 PMPanel Session Kangwook Lee ⋅ Zechun Liu ⋅ Fartash Faghri VideoPanelDeliberation+
Format · BroadcastPanelExperts discuss while the audience watches. Surfaces perspective but rarely creates participant work.
Evidence basisMediumRead from source
The Full Reading
Why It Ranks This Way +
Calibrated from GES design 42/100 and verified 42/100, then capped for agenda is mostly passive without visible outcome mechanics.
Reader Takeaway. For a reader, this is a comparison record more than a model to copy: it reads as a broadcast-heavy conference, 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 Personalization.
How This Agenda Could Improve +
- Add named owners, dates, implementation checkpoints, and a visible post-event continuation path.
- Replace generic networking blocks with designed introductions, ask-offer exchanges, peer groups, or bridge-building rituals.
- Create role-based paths, prepared questions, tailored breakouts, or participant-specific next steps.
Fastest next move: Add named owners, dated next steps, and a visible continuation path before treating the event as outcome-ready.
Role-Specific Reading +
Sponsor lens
Look beyond exposure. Strong sponsor value would show qualified interaction, problem work, buyer learning, customer evidence, or follow-up. The practical sponsor move is to 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, Network design, Learning transfer.
Evidence boundary: Scores reflect visible agenda/source evidence and should not be read as proof of causal event impact.
Limitations, Score Caps, and Review Flags +
Limitations
- No visible follow-up, progress monitoring, or longitudinal tracking.
- Passive stage formats dominate the visible agenda.
- No baseline measurement is visible.
Score caps
- 34: Agenda is mostly passive without visible outcome mechanics.
Review flags
- Fourth-loop score cap: Agenda is mostly passive without visible outcome mechanics.
- 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.
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_2025_icml_wca4z_platform_accelerating_legacy_code_modernization_using_ai_agents_e55a1a"><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.