Algorithms for finetuning foundation models, robustness/reliability, understanding representation
State space models, network architectures, audio models
Multimodal learning, Human-AI Collaboration, LLM Evaluation
Hardware algorithms, long context generation, FMs for new material
LLM pretraining, retrieval-augmentation, data-centric LLMs, embedding models
Foundation models for music
Pragmatics of language, context, generating/following instructions, code models, interfaces, multimodal dialog
Generative language models for coherent and engaging narratives, leveraging models as creative tools
Vision language models, long-tailed recognition, image generation
Efficiency of LLMs, computation, data, applications outside CS
System support for LLMs, pretraining, finetuning, federated learning, private inference, acceleration, Vicuna model, AI for science
Finetuning LLMs for neuro-symbolic reasoning, autonomous scientific research, robotics
Evaluation/verification of LLM outputs, LM training methods, retrieval-based LLMs, LLMs with external tools
LLMs for molecular and cell biology, Single-cell genomics, AI for biomedicine
Large Language Models, Multilingual NLP, AI for Science
Ethical risks, LLM limitations w.r.t. reasoning, social intelligence
LLMs in safety/privacy risk situations, code verification, neuro-symbolic methods
LLM understanding, neuro-symbolic architectures, reliability
Multimodal models, visual language reasoning
LLMs for math and theorem proving, inference algorithms
Intersection of HCI and NLP, model mapping to use cases
Foundation models for speech
Responsible AI, Interactive learning, Economic aspects of machine learning
System support for ML, LLMs on local devices, scaling open language models
Multiagent systems, ethics, societal implication
Privacy, robustness, finetuning, LLM validation, federated learning
Language for robots, LLM-based planning, other signals
NLP in medicine, decision support, evaluation outside labeled datasets, robustness
Support for LLMs, computational efficiency, speculative execution, GPU memory
Robustness and AI Security, VLM training, few/zero-shot classifier evaluation, equilibrium models