Related papers: COLA: Consistent Learning with Opponent-Learning A…
Contrastive self-supervised learning (CSL) has managed to match or surpass the performance of supervised learning in image and video classification. However, it is still largely unknown if the nature of the representations induced by the…
Parameter-efficient continual learning has emerged as a promising approach for large language models (LLMs) to mitigate catastrophic forgetting while enabling adaptation to new tasks. Current Low-Rank Adaptation (LoRA) continual learning…
There has been much recent interest in understanding the continuum from adversarial to stochastic settings in online learning, with various frameworks including smoothed settings proposed to bridge this gap. We consider the more general and…
One of the objectives of continual learning is to prevent catastrophic forgetting in learning multiple tasks sequentially, and the existing solutions have been driven by the conceptualization of the plasticity-stability dilemma. However,…
Recent unsupervised multi-object detection models have shown impressive performance improvements, largely attributed to novel architectural inductive biases. Unfortunately, they may produce suboptimal object encodings for downstream tasks.…
Most existing works focus on direct perturbations to the victim's state/action or the underlying transition dynamics to demonstrate the vulnerability of reinforcement learning agents to adversarial attacks. However, such direct…
This paper extends the notion of learning equilibrium in game theory from matrix games to stochastic games. We introduce Foolproof Cooperative Learning (FCL), an algorithm that converges to a Tit-for-Tat behavior. It allows cooperative…
Continual learning aims to learn on non-stationary data streams without catastrophically forgetting previous knowledge. Prevalent replay-based methods address this challenge by rehearsing on a small buffer holding the seen data, for which a…
We address the question of how to successively add new knowledge to an LLM whilst retaining previously-added knowledge. We consider two settings, semi-cooperative and fully-cooperative. Overall, LoRA performs better in most cases than…
Recent work using pretrained transformers has shown impressive performance when fine-tuned with data from the downstream problem of interest. However, they struggle to retain that performance when the data characteristics changes. In this…
We propose Searching with Opponent-Awareness (SOA), an approach to leverage opponent-aware planning without explicit or a priori opponent models for improving performance and social welfare in multi-agent systems. To this end, we develop an…
Low-Rank Adaptation (LoRA) is a parameter-efficient technique for rapidly fine-tuning foundation models. In standard LoRA training dynamics, models tend to quickly converge to a local optimum near the initialization. However, this local…
Online prediction for streaming time series data has practical use for many real-world applications where downstream decisions depend on accurate forecasts for the future. Deployment in dynamic environments requires models to adapt quickly…
Vision-Language-Action (VLA) models exhibit strong generalization in robotic manipulation, yet reinforcement learning (RL) fine-tuning often degrades robustness under spatial distribution shifts. For flow-matching VLA policies, this…
Securing coordination between AI agent and teammates (human players or AI agents) in contexts involving unfamiliar humans continues to pose a significant challenge in Zero-Shot Coordination. The issue of cooperative incompatibility becomes…
Learning in a multi-agent system is challenging because agents are simultaneously learning and the environment is not stationary, undermining convergence guarantees. To address this challenge, this paper presents a new gradient-based…
Consistency models imitate the multi-step sampling of score-based diffusion in a single forward pass of a neural network. They can be learned in two ways: consistency distillation and consistency training. The former relies on the true…
Modern transformer attention is internally multi-agent -- heads compete and coordinate -- yet we train it as if it were a monolithic optimizer. We formalize this gap: cross-entropy training induces an implicit potential game among heads,…
Federated learning is a distributed learning paradigm where multiple agents, each only with access to local data, jointly learn a global model. There has recently been an explosion of research aiming not only to improve the accuracy rates…
Deep learning is built on the foundational guarantee that gradient descent on an objective function converges to local minima. Unfortunately, this guarantee fails in settings, such as generative adversarial nets, that exhibit multiple…