collaborators

7 papers

cs.LG2026

Transformer-Based Multi-Agent Reinforcement Learning for Networked Systems with Long-Range Interactions

Vidur Sinha, Muhammed Ustaomeroglu, Guannan Qu

Multi-agent reinforcement learning (MARL) has shown promise for large-scale network control, yet existing methods face two major limitations. First, they typically rely on an expon…

cs.LG2026

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…

cs.LG2026

BLOCK-EM: Preventing Emergent Misalignment via Latent Blocking

Muhammed Ustaomeroglu, Guannan Qu

Emergent misalignment can arise when a language model is fine-tuned on a narrowly scoped supervised objective: the model learns the target behavior, yet also develops undesirable o…

cs.LG2026

Towards Effective Theory of LLMs: A Representation Learning Approach

Muhammed Ustaomeroglu, Guannan Qu

We propose Representational Effective Theory (RET), a framework for describing large language model computation in terms of learned macrostates rather than microscopic details. RET…

cs.LG2026

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…

cs.AI2026

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…