7 papers
Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer
Baris Askin, Muhammed Ustaomeroglu, Anupam Nayak +3
Fine-tuning LLMs on narrow harmful datasets can induce Emergent Misalignment (EM), where models exhibit misaligned behavior far beyond the fine-tuning distribution. We argue that e…
PubSwap: Public-Data Off-Policy Coordination for Federated RLVR
Anupam Nayak, Baris Askin, Muhammed Ustaomeroglu +2
Reasoning post-training with reinforcement learning from verifiable rewards (RLVR) is typically studied in centralized settings, yet many realistic applications involve decentraliz…
Internal Planning in Language Models: Characterizing Horizon and Branch Awareness
Muhammed Ustaomeroglu, Baris Askin, Gauri Joshi +2
The extent to which decoder-only language models (LMs) engage in planning, that is, organizing intermediate computations to support coherent long-range generation, remains an impor…
Ravan: Multi-Head Low-Rank Adaptation for Federated Fine-Tuning
Arian Raje, Baris Askin, Divyansh Jhunjhunwala +1
Large language models (LLMs) have not yet effectively leveraged the vast amounts of edge-device data, and federated learning (FL) offers a promising paradigm to collaboratively fin…
Federate the Router: Learning Language Model Routers with Sparse and Decentralized Evaluations
Baris Askin, Shivam Patel, Anupam Nayak +4
Large language models (LLMs) are increasingly accessed as remotely hosted services by edge and enterprise clients that cannot run frontier models locally. Since models vary widely…
Reviving Stale Updates: Data-Free Knowledge Distillation for Asynchronous Federated Learning
Baris Askin, Holger R. Roth, Zhenyu Sun +3
Federated learning (FL) enables collaborative model training across distributed clients without sharing raw data, yet its scalability is limited by synchronization overhead. Asynch…