Education
A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits
OFUGLB outperforms or is at par with prior algorithms for logistic bandits.
The Power of Extrapolation in Federated Learning
In our work, we focus on smooth convex or strongly convex problems in the interpolation regime.
SimPO: Simple Preference Optimization with a Reference-Free Reward Y u Meng
Additionally, we introduce a target reward margin to the Bradley-Terry objective to encourage a larger margin between the winning and losing responses, further improving the algorithm's performance.
Not Just Object, But State: Compositional Incremental Learning without Forgetting
Since the lack of suitable benchmarks, we re-organize two existing datasets and make them tailored for composition-IL.
MetaCURL: Non-stationary Concave Utility Reinforcement Learning Bianca Marin Moreno Inria
We explore online learning in episodic Markov decision processes on non-stationary environments (changing losses and probability transitions).
Towards Neuron Attributions in Multimodal Large Language Models
As Large Language Models (LLMs) demonstrate impressive capabilities, demys-tifying their internal mechanisms becomes increasingly vital.
Non-Asymptotic Uncertainty Quantification in High-Dimensional Learning
Uncertainty quantification (UQ) is a crucial but challenging task in many high-dimensional learning problems to increase the confidence of a given predictor.
Stronger Than You Think: Benchmarking Weak Supervision on Realistic Tasks
Existing evaluation suites tend to be limited, focusing on particular components or specialized use cases.
EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models
Our experiments with extensive data indicate that the model trained on generated data of the advanced model can approximate its generation capability. However, it requires large-scale samples of 10 million or more.