Education
Private Online Learning via Lazy Algorithms
We study the problem of private online learning, focusing on online prediction from experts (OPE) and online convex optimization (OCO).
WizardArena: Post-training Large Language Models via Simulated Offline Chatbot Arena
Recent work demonstrates that, post-training large language models with open-domain instruction following data have achieved colossal success.
Random Function Descent
Classical worst-case optimization theory neither explains the success of optimization in machine learning, nor does it help with step size selection.
Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning
Accurate emotion perception is crucial for various applications, including human-computer interaction, education, and counseling.
Skill-aware Mutual Information Optimisation for Generalisation in Reinforcement Learning
Reinforcement Learning (RL) agents often learn policies that do not generalise across tasks in which the environmental features and optimal skills are different [des Combes et al., 2018, Garcin et al., 2024].
Semantics and Spatiality of Emergent Communication Rotem Ben Zion
When artificial agents are jointly trained to perform collaborative tasks using a communication channel, they develop opaque goal-oriented communication protocols.
VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation
A well-known dilemma in large vision-language models ( e.g., GPT -4, LLaV A) is that while increasing the number of vision tokens generally enhances visual
Generalizing Consistency Policy to Visual RL with Prioritized Proximal Experience Regularization
With high-dimensional state spaces, visual reinforcement learning (RL) faces significant challenges in exploitation and exploration, resulting in low sample efficiency and training stability.