This FITML workshop aims to contribute to the recent radical paradigm shift for fine-tuning in modern machine learning, theoretically, computationally, and systematically.

It encourages researchers to push forward the frontiers of theoretical understanding of fine-tuning, devising expeditious and resource-efficient inference and fine-tuning methods in machine learning systems, enabling their deployment within constrained computational resources.

Website: https://sites.google.com/view/neurips2024-ftw

This workshop plans to gather researchers working in neural algorithmic learning, multimodal reasoning, and cognitive models of intelligence to showcase their cutting-edge research, discuss the latest challenges, as well as bring to the forefront problems in perception and language modeling that are often overlooked but are pivotal in achieving true artificial general intelligence. An emphasis of this workshop is on the emerging topic of multimodal algorithmic reasoning, where a reasoning agent is required to automatically deduce new algorithms/procedures for solving real-world tasks, e.g., algorithms that use multimodal foundational models for analysis, synthesis, and planning, new approaches towards solving challenging vision-and-language mathematical (Olympiad type) reasoning problems, deriving winning strategies in multimodal games, procedures for using tools in robotic manipulation, etc.

Website: https://marworkshop.github.io/neurips24/

The Table Representation Learning (TRL) workshop is the premier venue in this emerging research area and has three main goals:

• Motivate tables as a primary modality for representation and generative models and advance the area further.
• Showcase impactful applications of pretrained table models and identify open challenges for future research, with a particular focus on industry insights in 2024.
• Foster discussion and collaboration across the ML, NLP, IR and DB communities.

Website: https://table-representation-learning.github.io/

This workshop aims to bring together researchers from various fields to discuss emerging topics about reasoning and decision-making in open-world environments. This topic can be overly broad, but we are particularly interested in synergizing reasoning and decision-making, i.e., open-world agents that can simultaneously perform reasoning (e.g., QA, dialogue) and decision-making (e.g., planning and control), and how such unification helps tackle the challenges brought by the open world to both parties. To this end, the related fields are not limited to interleaved reasoning with decision-making, reasoning in embodied learning agents, LLM tool usage, reinforcement learning in open-world environments, open vocabulary learning, continued learning, multi-agent learning, and emerging ethical considerations in open-world environments. The objective is to foster collaboration and insights into addressing the scientific questions about developing open-world reasoning and decision-making agents.

Website: https://sites.google.com/view/open-world-agents/home

Website: https://advml-frontier.github.io/

Website: https://neurips2024-enlsp.github.io/

The workshop aims to gather machine learning researchers and healthcare/medicine experts from both academia and industry to explore the transformative potential of GenAI for health. It will delve into the trustworthiness risks and mitigation of cutting-edge GenAI technologies applicable in health applications, such as LLMs, and multi-modality large models. By fostering multidisciplinary communication with experts in government policies, this workshop seeks to advance the integration of GenAI in healthcare, ensuring safe, effective, ethical, and policy-compliant deployment to enhance patient outcomes and clinical research.

Website: https://genai4health.github.io/

This workshop aims to bring together researchers from different but closely related areas, including Bayesian optimization, active learning, uncertainty quantification, Gaussian processes, spatiotemporal modeling, and sequential experimental design. It seeks to foster a vibrant exchange of ideas, showcase successful applications, and prompt fruitful discussion to collaboratively tackle the emerging challenges and shape the future directions of Bayesian decision-making and uncertainty in the new era of ML and AI.

Website: https://gp-seminar-series.github.io/neurips-2024/

Many in the ML community wish to take action on climate change, but are unsure of the pathways through which they can have the most impact. This workshop highlights work that demonstrates that, while no silver bullet, ML can be an invaluable tool in reducing greenhouse gas emissions and in helping society adapt to the effects of climate change. Climate change is a complex problem, for which action takes many forms - from theoretical advances to deployment of new technology. Many of these actions represent high-impact opportunities for real-world change, and are simultaneously interesting academic research problems.

This workshop is part of the “Tackling Climate Change with Machine Learning” workshop series, which aims to bring together those applying ML to climate change challenges and facilitate cross-pollination between ML researchers and experts in climate-relevant fields.

Website: https://www.climatechange.ai/events/neurips2024

Website: https://safegenaiworkshop.github.io/

Website: https://neurips.cc/virtual/2024/workshop/84749

Website: https://neurips-time-series-workshop.github.io/

Website: https://imol-workshop.github.io/

December 10, 2:00-2:30pm
December 11, 4:30-5:00pm
December 12, 9:30-10:00am

We will showcase the Neuron SDK custom kernel library called NKI

December 10, 2:30-3:00pm
December 10, 3:00-3:30pm
December 11, 11:00-11:30am

We will showcase interactive immersive experiences for creating, transferring, and customizing makeup looks.

December 10, 3:30-4:00pm
December 10, 4:00-4:30pm
December 11, 9:30-10:00am
December 11, 10:00-10:30am

We will showcase Llama\PixART inference working with Trainium2 and the latest Stable Diffusion model working with Inferentia.

December 11, 10:30-11:00am
December 11, 3:30-4:00pm

We will showcase Quartz, the Reliability Maintenance Engineering Cognitive Assistant, and its combined capability of query generation and document intelligence that helps RME Field teams across Amazon's facilities

December 11, 11:30-12:00pm
December 11, 4:00-4:30pm

We describe the main challenges behind the foundation time series models. Specifically, we will focus on demand forecasting and explain why it is difficult to build such models even with huge amount of data available.

December 12, 10:00-10:30am

We will showcase AI and CVML based colutions deployed in the fields of sports.

December 12, 10:30-11:00am

We will showcase long-llava-qwen-7b, an open source multimodal LLM that can understand text, image, and video, released by AWS.

December 12, 11:00-11:30am
December 12, 11:30-12:00pm

We will showcase genAI for creative Ads, including image generation and video generation