
Explore tectogrammatical sentence representation, a linguistic approach for analyzing sentence structure and meaning, presented by Jan Hajic in 2001.

Explore a feature-based model of human lexical access, delving into the intricacies of language processing and speech recognition.

Explore OLMo, an open-source language model initiative, and its impact on accelerating research in natural language processing and machine learning.

Explore innovative approaches to language extension and their impact on linguistic analysis, with insights on balancing intentions and outcomes.

Explore cutting-edge research in speech recognition, generation, and privacy. Learn about self-training algorithms, error correction models, joint text-to-speech modeling, and privacy-preserving techniques in speech processing.

Explore opponent-shaping and interference in general-sum games, delving into multi-agent reinforcement learning and its applications in AI research.

Explore a theory of appropriateness in AI, focusing on complex cognitive behaviors, evaluation methods, and modeling processes like cumulative culture in human intelligence.

Explore fairness in AI decision-making, addressing efficiency, elicitation, and incentives. Learn theoretical foundations for fairness in voting, resource allocation, and machine learning.

Explore AI strategies for cooperation and competition through self-play, featuring insights from poker AI breakthroughs and their broader implications.

Explore normative intelligence and its implications for AI governance, safety, and societal impact with insights from law, economics, and technology.

Explore emergent computation and learning in neural assemblies with Dr. Santosh Vempala's insightful seminar on cutting-edge neuroscience research.

Explore mathematical frameworks for robust AI perception, focusing on Lie theory to model hierarchical structures and transformations in real-world object recognition.

Explore data-driven approaches revolutionizing composite manufacturing, transforming traditional methods into adaptable, efficient, and scalable systems.

Explore data-efficient neurosymbolic generative models for molecular generation using learnable graph grammars, optimized for small datasets and physically synthesizable molecules.

Explore neural surrogates for program optimization, including case studies on CPU simulators and techniques like the Renamer and Turaco for constructing efficient program surrogates.

Explore program synthesis evolution as a learning tool, from early data-driven models to modern neurosymbolic algorithms.

Explore symbolic structure inference from visual data using neuro-symbolic methods. Learn to leverage natural supervision for discovering repetitive patterns, object intrinsics, and grounded visual concepts.

Explore probabilistic programming fundamentals and applications with MIT expert Vikash Mansinghka in this comprehensive tutorial.

Explore techniques to enhance LLM performance, scale models in production, and improve structured outputs. Learn from experts about information extraction, scaling challenges, and innovative programming approaches for better AI results.

Explore robust optimization's history and its modern machine learning applications, focusing on performance certification and practical challenges in ML systems.

Explore diverse Python topics in rapid-fire talks, from matrix arithmetic and 3D modeling to garbage collection and presentation skills. Gain insights from experts in this engaging lightning talk session.