19 papers
Accurate and Resource-Efficient Federated Continual Learning
Jebacyril Arockiaraj, Dhruv Parikh, Jayashree Adivarahan +2
Federated continual learning (FCL) must learn from distributed task streams under limited resources, such as communication, computation, memory, and label availability. Existing FC…
Can Graphs Help Vision SSMs See Better?
Dhruv Parikh, Anvitha Ramachandran, Haoyang Fan +3
Vision state space models inherit the efficiency and long-range modeling ability of Mamba-style selective scans. However, their performance depends critically on the representation…
TypeBandit: Type-Level Context Allocation and Reweighting for Effective Attribute Completion in Heterogeneous Graph Neural Networks
Ta-Yang Wang, Rajgopal Kannan, Viktor Prasanna
Heterogeneous graphs are widely used to model multi-relational systems, but missing node attributes remain a major bottleneck for downstream learning. In this paper, we identify an…
Action-Graph Policies: Learning Action Co-dependencies in Multi-Agent Reinforcement Learning
Nikunj Gupta, James Zachary Hare, Jesse Milzman +2
Coordinating actions is the most fundamental form of cooperation in multi-agent reinforcement learning (MARL). Successful decentralized decision-making often depends not only on go…
Deep Meta Coordination Graphs for Multi-agent Reinforcement Learning
Nikunj Gupta, James Zachary Hare, Jesse Milzman +2
This paper presents deep meta coordination graphs (DMCG) for learning cooperative policies in multi-agent reinforcement learning (MARL). Coordination graph formulations encode loca…
ConsensusDrop: Fusing Visual and Cross-Modal Saliency for Efficient Vision Language Models
Dhruv Parikh, Haoyang Fan, Rajgopal Kannan +1
Vision-Language Models (VLMs) are expensive because the LLM processes hundreds of largely redundant visual tokens. Existing token reduction methods typically exploit \textit{either…