11 papers
Can Transformers Really Do It All? On the Compatibility of Inductive Biases Across Tasks
Damien Teney, Liangze Jiang, Hemanth Saratchandran +1
Transformers are remarkably versatile and their design is largely consistent across a variety of applications. But are they optimal for any given task or dataset? The answer may be…
Multi-Hypothesis Test-Time Adaptation to Mitigate Underspecification
Afshar Shamsi, Xiao-Yu Guo, Hamid Alinejad-Rokny +3
Test-Time Adaptation (TTA) seeks to improve model robustness under distribution shifts by adapting parameters using unlabeled target data. However, in the absence of supervision, e…
How does the optimizer implicitly bias the model merging loss landscape?
Chenxiang Zhang, Alexander Theus, Damien Teney +3
Model merging combines independent solutions with different capabilities into a single one while maintaining the same inference cost. Two popular approaches are linear interpolatio…
Meta-RL Induces Exploration in Language Agents
Yulun Jiang, Liangze Jiang, Damien Teney +2
Reinforcement learning (RL) has enabled the training of large language model (LLM) agents to interact with the environment and to solve multi-turn long-horizon tasks. However, the…
AugGen: Synthetic Augmentation using Diffusion Models Can Improve Recognition
Parsa Rahimi, Damien Teney, Sebastien Marcel
The increasing reliance on large-scale datasets in machine learning poses significant privacy and ethical challenges, particularly in sensitive domains such as face recognition. Sy…
Mysteries of the Deep: Role of Intermediate Representations in Out of Distribution Detection
I. M. De la Jara, C. Rodriguez-Opazo, D. Teney +2
Out-of-distribution (OOD) detection is essential for reliably deploying machine learning models in the wild. Yet, most methods treat large pre-trained models as monolithic encoders…