David Daniel Cox
8 papers · 2018–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π£ Hot Topic Early Bird π Academic Marathon Β· Sprint π Conference Polyglot Β· Bronze π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (19)
π₯
Mega-Team Β· Squad
π
Conference Pioneer
Top co-authors
Research topics
Artificial Intelligence
(6)
Core AI
(6)
Machine Learning
(4)
Deep Learning
(2)
Natural Language Processing
(2)
Learning Types Β· Machine Learning
(2)
Resources & Methods
(2)
Computer Vision
(1)
Reinforcement Learning
(1)
Architectures
(1)
Core Methods
(1)
Domain-Specific
(1)
Learning Types Β· Deep Learning
(1)
Methods
(1)
Optimization & Theory
(1)
Keywords
reinforcement learning
(1)
stochastic gradient descent
(1)
multi-task learning
(1)
adversarial robustness
(1)
information bottleneck
(1)
object recognition
(1)
instruction following
(1)
model merging
(1)
language model alignment
(1)
synthetic data generation
(1)
reinforcement learning from human feedback
(1)
robot manipulation
(1)
deep neural network
(1)
reward model
(1)
mixture of expert
(1)
tool use
(1)
parameter initialization
(1)
transformer training
(1)
expert routing
(1)
representation learning
(1)
Papers
Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search
ICML 2025
Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts
ICLR 2025
Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Tasks
EMNLP 2024
SALMON: Self-Alignment with Instructable Reward Models
ICLR 2024
Aligning Model and Macaque Inferior Temporal Cortex Representations Improves Model-to-Human Behavioral Alignment and Adversarial Robustness
ICLR 2023
Learning to Grow Pretrained Models for Efficient Transformer Training
ICLR 2023
Embodied Concept Learner: Self-supervised Learning of Concepts and Mapping through Instruction Following
CoRL 2022
On the Information Bottleneck Theory of Deep Learning
ICLR 2018