議程
ICC Sydney。所有時間均為雪梨時間(AEDT,UTC+11)。
略過篩選條件,前往結果
查核日期:2026年11月15日(週日)。研究領域為 QRS 自行分類,並非官方分類。官方議程
無法取得議程
無法載入議程資料。下方的雪梨議程仍可正常使用。
雪梨議程,2026年12月6日(週日)至12月12日(週六)
所有時間均為雪梨時間。查核日期:2026年11月15日(週日)。亞特蘭大與巴黎的資料分別在 events-atlanta.json 與 events-paris.json。
2026年12月6日(週日)
- 11:00–12:00 AI That Optimizes AI: Agentic Kernel and Model Optimization in Production
- 11:00–12:00 Any GPU, Any Cloud: Training on a Planetary Fleet
- 11:00–12:00 CEO Bench: Evaluating frontier agents on real company work
- 11:00–12:00 The Model Is Not the Agent: Building Better Agents from Experience, Systems, and Evaluation
- 11:00–12:00 Training Data Expires Faster Than Ever: Five Shifts in How Frontier Models Learn, 2024–2027
- 11:00–12:00 When Models Optimize: From Automated Red Teaming to Reward Hacking
- 12:00–13:00 A Training-Free Framework for Spatially Grounded 2D Shape and 3D Object Encoding
- 12:00–13:00 Causal Inference has Entered its Foundation Model Era – What Industry Needs to Know
- 12:00–13:00 Continual Learning in Non-Stationary Environments
- 12:00–13:00 Scaling AI Safety & Security
- 12:00–13:00 Tabular Foundation Models Have Taken the Lead: What Changed This Year and How to Use TabPFN
- 12:00–13:00 The Art & Science of Benchmarking Agents
- 12:00–14:00 Agent Harnesses in Practice: From Everyday Tasks to Autonomous Research Teams
- 12:00–14:00 Agent-driven training on Modal
- 12:00–14:00 Beyond “The Robot Moved”: Building VLA Systems That Detect Failure and Recover
- 12:00–14:00 Building High-throughput Top Performing Machine Translation System
- 12:00–14:00 Building Self-Improving User Simulators
- 12:00–14:00 Challenge the Guardrails: Can You Outsmart the Model?
- 12:00–14:00 Closing the Agent Learning Loop: Strands, Amazon Bedrock AgentCore, and Feedback-Aware Post-Training
- 12:00–14:00 CyberStrike: Evaluating whether frontier agents can complete real cybersecurity work
- 12:00–14:00 From Flat Pixels to Editable Layers: A Live Image-to-Layers System at Production Scale
- 12:00–14:00 Inside the RL Stack: Training Open Models with Custom Rewards, Losses, and Code Sandboxes
- 12:00–14:00 LEAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks
- 12:00–14:00 Mirror: Start an Agent Session Anywhere, Never Lose It
- 12:00–14:00 QuLM-ST: Real-Time Speech Translation on Smart Glasses
- 12:00–14:00 Stump the Model: Become an AI Trainer in Five Minutes
- 12:00–14:00 Tangent: Autonomous Auto-Research Agent for ML Pipelines
- 12:00–14:00 When Agents Cannot Guess: Grounded Financial Research Under Regulatory Constraints
- 13:00–14:00 Advancing the Frontiers of On-Device AI: Efficiency, Multimodality, and Emerging Models
- 13:00–14:00 Applying AI to Financial Markets: A Citadel and Citadel Securities Perspective
- 13:00–14:00 Composing Modular Capabilities into One Deployable LLM
- 13:00–14:00 Constructing Data and Rule Ontologies for Enterprise Agents
- 13:00–14:00 Fine-Tuning Small Models on Real Enterprise Tool Use: A Data and Evaluation Pipeline
- 13:00–14:00 One Market, Many Clocks: Domain-Grounded Multimodal Learning in Quantitative Finance
- 14:00–17:00 Compute Efficiency & Scalable System Design (Smart Compute Allocation: High-Throughput, Low-Latency AI Across the Model Lifecycle)
- 14:00–17:00 Forgetting on Purpose: A Hands-on Tutorial on LLM Unlearning
- 14:00–17:00 From Representation to Discovery: A World Model of Protein Biology
- 14:00–17:00 Priorities in AI Safety & Security
- 14:00–17:00 Protective and Creative AI for Creators: Foundation Models, Protection Mechanisms, and Audio-Visual Generation
- 14:00–17:00 RL in the wild: principles of post-training that work in the real world
- 16:30–17:30 咖啡與點心
- 17:00–18:00 Beyond Chat: Always-On Context Engines for Proactive AI Assistants
- 17:00–18:00 Breaking the Bottlenecks of Autoregressive LLM Inference
- 17:00–18:00 Building Enterprise AI for Finance: Structured Models, Adaptive Memory, Trusted Agents, and Scalable Orchestration
- 17:00–18:00 Can We Turn Images into Words—and Back Again? Holistic Visual Descriptions for Understanding and Generation
- 17:00–18:00 Owning the Harness: Durable, Open Infrastructure for Long-Running Agents
- 17:00–18:00 Towards Foundational Robotics Models with 3D Reasoning
- 18:00–19:00 Adapting AI Research to Quantitative Finance
- 18:00–19:00 Agents in Production: Evals, Harnesses, and the Reinvention of Recommendation
- 18:00–19:00 Continual Reinforcement Learning for AI Shopping Assistants
- 18:00–19:00 Environments Are the New Data: Building, Verifying, and Training Agents at Scale.
- 18:00–19:00 From Research to Industry: Building Scalable Production Systems and Teams
- 18:00–19:00 Turning Academic AI Research into Trusted Real-World Impact
2026年12月7日(週一)
- 08:00–09:00 咖啡與點心
- 08:00–17:00 GlobalSouthAI
- 08:00–17:00 LatinX in AI
- 08:00–17:00 Muslims in ML
- 08:30–16:30 教育議程軌
- 09:00–12:00 Empirical Design in Reinforcement Learning for Physical AI
- 09:00–12:00 From Scores to Evidence: Robust Evaluation of Foundation Models
- 09:00–12:00 Multi-Objective Optimization for Modern Machine Learning: Foundations, Recent Advances, and Emerging Applications
- 09:00–12:00 The Principles of Diffusion Models: Toward Fast and Scalable Diffusion LLMs
- 09:00–12:00 Three Geometric Lenses on Graph Machine Learning
- 09:00–12:00 Uncertainty Quantification: From Detecting LLM Hallucinations to Strengthening Reasoning and AI Agents
- 12:00–14:00 午餐自理
- 13:00–17:00 Indigenous in AI
- 14:00–17:00 Causal Representation Learning
- 14:00–17:00 Distilling Reasoning: From Chain-of-Thought to Agentic Capabilities in Smaller Models
- 14:00–17:00 Formal Guarantees for Frontier AI Systems
- 14:00–17:00 From Heuristics to Guarantees: Bandit and RL Blueprint for Reliable Agentic-AI
- 14:00–17:00 Neuro-Symbolic Learning in the Era of Large Language Models
- 14:00–17:00 Principles of Deep Representation Learning via Low-Dimensional Models
- 15:00–15:30 咖啡與點心
- 17:00–17:30 歡迎致詞
- 17:30–19:00 歡迎酒會
2026年12月8日(週二)
- 08:00–17:00 WiML
- 08:30–09:00 咖啡
- 09:00–10:00 Scaling Experience in the Wild: Building the Industrial Learning Loop
- 10:00–10:30 咖啡與點心
- 10:00–13:00 Sydney Poster Session 1
- 11:00–14:00 Creative AI Session 1
- 12:00–14:00 午餐自理
- 13:30–14:00 時間檢驗獎(Test of Time Award)
- 13:30–16:30 Affinity Joint Poster Session
- 13:30–16:30 Affinity Support Pilot Program
- 14:00–15:00 Barbara Engelhardt
- 15:00–15:30 咖啡
- 15:30–17:00 Orals 1A Multimodal & Visual Reasoning
- 15:30–17:00 Orals 1B Interpretability & Analysis of Neural Networks
- 15:30–17:00 Orals 1C Embodied Agents & Robotics
- 15:30–17:00 Orals 1D Computational Neuroscience & Brain Decoding
- 15:30–17:00 Orals 1E Exploration, Intrinsic Motivation & Multi-Agent RL
- 16:30–19:30 Creative AI Session 2
- 17:00–18:00 咖啡與點心
- 17:00–18:00 Science Communication Training Session 1
- 17:00–20:00 Sydney Poster Session 2
- 19:00–21:00 AI Infra Builders Social: Bridging Open Source, Research, and Production
- 19:00–21:00 Building Multilingual and Multiregional Safety Datasets: A Roundtable on Data Collection Methodology
- 19:00–21:00 Generative AI and the Creator Economy
- 19:00–21:00 Lost in Translation, Found in Interdisciplinarity
- 19:00–21:00 Muslims in ML Social
2026年12月9日(週三)
- 08:30–09:00 咖啡
- 09:00–10:00 The Better AIngels of our Future
- 09:00–17:00 Queer in AI and {Dis}Ability in AI Workshop at NeurIPS 2026
- 10:00–10:30 咖啡與點心
- 10:00–13:00 Sydney Poster Session 3
- 11:00–14:00 Creative AI Session 3
- 12:00–14:00 午餐自理
- 14:00–15:00 To score or not to score
- 15:00–15:30 咖啡
- 15:30–17:00 Orals 2A LLM Training, Scaling & Efficient Reasoning
- 15:30–17:00 Orals 2B 3D Reconstruction & Behavior Understanding
- 15:30–17:00 Orals 2C Security, Privacy & Model Protection
- 15:30–17:00 Orals 2D Molecular & Biological Foundation Models
- 15:30–17:00 Orals 2E Unlearning, Alignment & Model Auditing
- 15:30–17:00 Orals 2F Optimization & Online Learning Theory
- 16:30–19:30 Creative AI Session 4
- 17:00–18:00 咖啡與點心
- 17:00–18:00 Science Communication Training Session 2
- 17:00–20:00 Sydney Poster Session 4
- 19:00–21:00 Finding Your Path in AI Safety & Security Research
- 19:00–21:00 In Silico, In Vitro, In Vivo: The Protein Design Social
- 19:00–21:00 Multimodal AI Studio: Create Your Virtual Idol
- 19:00–21:00 The Human Context of AI: Whose Perspective Counts?
2026年12月10日(週四)
- 08:00–17:00 MLRC 2026
- 08:30–09:00 咖啡
- 09:00–10:00 The Knowledge Box: AI and Epistemic Dispossession
- 10:00–10:30 咖啡與點心
- 10:00–13:00 Sydney Poster Session 5
- 12:00–14:00 午餐自理
- 13:30–14:00 Sejnowski - Hinton Award
- 14:00–15:00 The Future of AI Evaluation
- 15:00–15:30 咖啡
- 15:30–17:00 Orals 3A LLM Agents & Program Synthesis
- 15:30–17:00 Orals 3B Diffusion & Generative Modeling
- 15:30–17:00 Orals 3C Evaluation & Benchmarking
- 15:30–17:00 Orals 3D Time Series, Earth & Climate Modeling
- 15:30–17:00 Orals 3E Uncertainty Quantification & Calibration
- 15:30–17:00 Orals 3F Graphs, Sketching & Scalable Algorithms
- 17:00–18:00 咖啡與點心
- 17:00–18:00 Town Hall
- 17:00–20:00 Sydney Poster Session 6
2026年12月11日(週五)
- 08:00–10:15 Learn2Design 2026: A physics experiment design competition for gravitational wave detectors
- 08:00–10:15 Predictive AI Evaluation Competition
- 08:00–17:00 AI at Scale for Clinical Impact (ASCI): Cancer Pathology Foundation Models
- 08:00–17:00 AI for Drug Discovery: Bridging the Translation Gap
- 08:00–17:00 AI for Stochastic Dynamics: From Theoretical Foundations to Scientific Applications
- 08:00–17:00 Agentic AI Benchmark and Application for Enterprise Tasks
- 08:00–17:00 Agentic AI for Biological Discovery: Toward Closed-Loop Life-Science Intelligence
- 08:00–17:00 AgenticOS: Co-designing Systems and ML Foundations of an OS Layer for Agentic AI
- 08:00–17:00 Collaborative, Open, and Decentralized Training of Foundation Models
- 08:00–17:00 Diffusion Language Models: Foundations, Efficiency, and Reasoning
- 08:00–17:00 Foundation Models for Temporal Systems: From Forecasting to World Modeling
- 08:00–17:00 Grounded and Faithful Vision-Language Models for Real-World Deployment
- 08:00–17:00 I Can’t Believe It’s Not Better (ICBINB): Failure Modes of AI in Biology
- 08:00–17:00 Interpretability as a Science: Toward Rigorous Foundations for Understanding LLMs
- 08:00–17:00 Machine Learning for Simulations in Biology and Chemistry - The 2nd SIMBIOCHEM Workshop
- 08:00–17:00 Managing Agents that Manage Agents: Workshop on Responsible Use of Meta-Agents that Build, Optimize, and Supervise Other Agents
- 08:00–17:00 NEmo: Neuro-Symbolic Embodied Intelligence
- 08:00–17:00 NeurIPS 2026 Workshop on Dynamic Alignment in Human-AI Coupled Systems
- 08:00–17:00 NeurIPS 2026 Workshop on Tackling Climate Change with Machine Learning
- 08:00–17:00 OPT 2026: Optimization for Machine Learning
- 08:00–17:00 Physical Understanding for Decision-Making: Bridging Foundation Models and Reliable Agents
- 08:00–17:00 Robot Learning with World Models: Capabilities, Frontiers, and Challenges
- 08:00–17:00 Symmetry and Geometry in Neural Representations NeurIPS Workshops 2026
- 08:00–17:00 The Third Workshop on Agents in the Wild: Safety, Security, and Beyond
- 08:00–17:00 Workshop for Autonomous Machine Learning Research
- 08:00–17:00 World Models in Physical AI
- 09:00–09:30 咖啡與點心
- 10:30–12:45 RoboSynChallenge: Mastering Real-World Dexterity via Generalizing Synthesized Manipulation Skills
- 12:00–13:00 自理午餐
- 13:00–15:15 NeurIPS 2026 RealPDE Competition: Scientific ML for Real-world Physical Systems
- 15:00–15:30 咖啡與點心
- 15:30–17:45 Speech Accessibility Project Challenge 2
- 17:30–19:30 工作坊交流酒會
2026年12月12日(週六)
- 08:00–10:15 AMP Challenge: A Benchmark for Generative AI in Antimicrobial Peptide Design
- 08:00–17:00 2nd Embodied Spatial Reasoning (ESR) Workshop
- 08:00–17:00 8th Robot Learning Workshop: Is Physical AI Going Zero-Shot?
- 08:00–17:00 AI Foundations for Power Grids: From Models to Deployment at Scale
- 08:00–17:00 AI for Science: Verification in the Age of AI Scientists
- 08:00–17:00 AI4Mat-NeurIPS-2026: NeurIPS-2026 Workshop on AI for Accelerated Materials Design
- 08:00–17:00 ATTRIB: Workshop on Data Attribution and Provenance
- 08:00–17:00 Beyond Next Token Prediction: Diffusion and Flow Models for Next-Generation Decoding
- 08:00–17:00 Beyond Private Training: The New Landscape of AI Privacy
- 08:00–17:00 Can We Trust AI Evaluation? Robustness, Causality, and Risk in Modern AI Assessment
- 08:00–17:00 Continual Learning in the Era of Foundation Models and Embodied Agents
- 08:00–17:00 Continual World Models
- 08:00–17:00 Foundation Models for the Brain and Body
- 08:00–17:00 Interpreting Agent Behavior (IAB): Human-Centered Interpretation for Understanding Agents, Humans, and Interaction
- 08:00–17:00 ML for Systems
- 08:00–17:00 On-Device Intelligence: Foundation Models under Real-World Constraints
- 08:00–17:00 PTA: From Pretrained Representations to Acting Agents -- Bridging Pretraining, Planning, and Test-Time Decision Making
- 08:00–17:00 Real-Time Conversational Agents: Toward Natural Multimodal Interaction
- 08:00–17:00 Responsible Communication of Machine Learning Research in Biomedicine
- 08:00–17:00 Self-Evolving Diversity-Driven Search for Robust AI Systems
- 08:00–17:00 The Third Workshop on GenAI for Health: Agentic Systems, Clinical Trust, and Future Potential
- 08:00–17:00 Transitioning from Pre-training to Post-training
- 08:00–17:00 Who Verifies the Agents? Toward Reliable Agent Development
- 08:00–17:00 Workshop on the Linguistic Principles for Foundation Models
- 08:00–17:00 XAI4science: Knowledge Discovery and Trust through Interpretable Foundation Models
- 09:00–09:30 咖啡與點心
- 10:30–12:45 SimulacraBench
- 12:00–13:00 自理午餐
- 13:00–15:15 QuantiPhy Challenge: Quantitative Physical Reasoning for VLMs
- 15:00–15:30 咖啡與點心
- 15:30–17:45 RoCo-Spring: The Robust Correspondence Challenge