Cohere videos Cohere-video's
Browse every published Cohere video in a focused overview with thumbnails, dates, and direct access to each watch page. Bekijk alle gepubliceerde Cohere-video's in een duidelijk overzicht met thumbnails, datums en directe toegang tot elke kijkpagina.
Shuo Li Liu - Coherence in RLHF Preference Data Shuo Li Liu - Coherence in RLHF Preference Data
RLHF usually learn from pairwise comparisons, often through Bradley-Terry-style models. I will discuss what coherence requirements, such as Weak Stochastic Transitivity and the Weak Axiom of Revealed Preference, mean for preference trained... RLHF usually learn from pairwise comparisons, often through Bradley-Terry-style models. I will discuss what coherence requirements, such as Weak Stochastic Transitivity and the Weak Axiom of Revealed Preference, mean for preference trained...
Uploads from Cohere
Jiafei Duan - Building Robotics Foundation Model with Reasoning in the loop Jiafei Duan - Building Robotics Foundation Model with Reasoning in the loop
Scaling alone won’t unlock general-purpose robotics. Integrating reasoning directly into robot learning (spatial, temporal, and failure-based) so robots can learn more from limited data and continuously self-improve is the path forward. Ji... Scaling alone won’t unlock general-purpose robotics. Integrating reasoning directly into robot learning (spatial, temporal, and failure-based) so robots can learn more from limited data and continuously self-improve is the path forward. Ji...
Uploads from Cohere
Aashish Rai - Video Native Representations for 4D Gaussian Scenes Aashish Rai - Video Native Representations for 4D Gaussian Scenes
Volumetric videos offer immersive 4D experiences, but remain difficult to reconstruct, store, and stream at scale. Existing Gaussian Splatting based methods achieve high-quality reconstruction but break down on long sequences, temporal inco... Volumetric videos offer immersive 4D experiences, but remain difficult to reconstruct, store, and stream at scale. Existing Gaussian Splatting based methods achieve high-quality reconstruction but break down on long sequences, temporal inco...
Uploads from Cohere
Ekdeep Singh Lubana - From Probes to Rewards Using Interpretability to Shape Training Ekdeep Singh Lubana - From Probes to Rewards Using Interpretability to Shape Training
Ekdeep Singh Lubana — Guest Speaker @ Cohere Labs AI Safety & Alignment Reading Group Ekdeep is MTS at Goodfire, previously research fellow at Harvard's Center for Brain Science. His recent work addresses some core issues with how we extra... Ekdeep Singh Lubana — Guest Speaker @ Cohere Labs AI Safety & Alignment Reading Group Ekdeep is MTS at Goodfire, previously research fellow at Harvard's Center for Brain Science. His recent work addresses some core issues with how we extra...
Uploads from Cohere
Zifeng Liu - Human–AI Collaboration in Educational Assessment Evaluating AI Generated Distractors Zifeng Liu - Human–AI Collaboration in Educational Assessment Evaluating AI Generated Distractors
In this talk, Zifeng will discuss the emerging role of generative AI in educational assessment, with a focus on the automatic generation and evaluation of multiple-choice distractors and feedback in computing and AI education. While large l... In this talk, Zifeng will discuss the emerging role of generative AI in educational assessment, with a focus on the automatic generation and evaluation of multiple-choice distractors and feedback in computing and AI education. While large l...
Uploads from Cohere
Juan Sebastian Rojas - A Differential Perspective on Risk Aware Reinforcement Learning Juan Sebastian Rojas - A Differential Perspective on Risk Aware Reinforcement Learning
The field of reinforcement learning has long been dominated by discounted methods, wherein a decision-making agent aims to optimize a potentially-discounted sum of rewards over time. In this talk, we explore a fundamentally different and un... The field of reinforcement learning has long been dominated by discounted methods, wherein a decision-making agent aims to optimize a potentially-discounted sum of rewards over time. In this talk, we explore a fundamentally different and un...
Uploads from Cohere
Niloofar Mireshghallah - Contextual Integrity in LLMs Benchmarking Niloofar Mireshghallah - Contextual Integrity in LLMs Benchmarking
Abstract: As large language models integrate into daily workflows—from personal assistants to workplace tools—they handle sensitive information from multiple sources yet struggle to reason about what to share, with whom, and when. In this t... Abstract: As large language models integrate into daily workflows—from personal assistants to workplace tools—they handle sensitive information from multiple sources yet struggle to reason about what to share, with whom, and when. In this t...
Uploads from Cohere
Yasser Benigmin - Domain Adaptation in the Era of Foundation Models Yasser Benigmin - Domain Adaptation in the Era of Foundation Models
In this presentation, we address domain adaptation in semantic segmentation, where deep learning models rely heavily on large labeled datasets and struggle with domain shift, limiting real-world generalization. We show how Foundation Models... In this presentation, we address domain adaptation in semantic segmentation, where deep learning models rely heavily on large labeled datasets and struggle with domain shift, limiting real-world generalization. We show how Foundation Models...
Uploads from Cohere
Debjyoti Paul - Learning to Act Reinforcement Learning for Agentic LLM Systems Debjyoti Paul - Learning to Act Reinforcement Learning for Agentic LLM Systems
Large Language Models (LLMs) have demonstrated impressive reasoning and generation abilities, but building agentic systems—AI that can plan, use tools, interact with environments, and achieve goals autonomously—requires more than prompting.... Large Language Models (LLMs) have demonstrated impressive reasoning and generation abilities, but building agentic systems—AI that can plan, use tools, interact with environments, and achieve goals autonomously—requires more than prompting....
Uploads from Cohere
MingYang Deng - Generative Modeling via Drifting MingYang Deng - Generative Modeling via Drifting
Generative modeling can be formulated as learning a mapping f such that its pushforward distribution matches the data distribution. The pushforward behavior can be carried out iteratively at inference time, for example in diffusion and flow... Generative modeling can be formulated as learning a mapping f such that its pushforward distribution matches the data distribution. The pushforward behavior can be carried out iteratively at inference time, for example in diffusion and flow...
Uploads from Cohere
Mansi Maheshwari - Addressing the Plasticity Stability Dilemma in Reinforcement Learning Mansi Maheshwari - Addressing the Plasticity Stability Dilemma in Reinforcement Learning
Neural networks have shown remarkable success in supervised learning when trained on a single task using a fixed dataset. However, when neural networks are trained on a reinforcement learning task, their ability to continue learning from ne... Neural networks have shown remarkable success in supervised learning when trained on a single task using a fixed dataset. However, when neural networks are trained on a reinforcement learning task, their ability to continue learning from ne...
Uploads from Cohere
Diego Fajardo - No single test is enough Diego Fajardo - No single test is enough
How do we know a model is actually ready for high-stakes use? In healthcare and life sciences, that question gets complicated fast. A model can look strong on one task, weak on another, and still surprise you when the stakes become real. Th... How do we know a model is actually ready for high-stakes use? In healthcare and life sciences, that question gets complicated fast. A model can look strong on one task, weak on another, and still surprise you when the stakes become real. Th...
Uploads from Cohere
Showing 1 to 12 of 12 videos. Je bekijkt 1 tot 12 van 12 video's.