collaborators

7 papers

cs.CL2026

Global PIQA: Evaluating Commonsense Reasoning Across 100+ Languages and Cultures

Tyler A. Chang, Catherine Arnett, Abdelrahman Sadallah +377

To date, there exist almost no culturally-specific evaluation benchmarks for large language models (LLMs) that cover a large number of languages and cultures. In this paper, we pre…

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

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.LG2026

Not All Turns Are Equally Hard: Adaptive Thinking Budgets For Efficient Multi-Turn Reasoning in Agents

Neharika Jali, Anupam Nayak, Gauri Joshi

As LLM reasoning performance plateaus, improving inference-time compute efficiency is crucial to mitigate overthinking and long thinking traces even for simple queries. Prior appro…

cs.LG2026

Achieving Logarithmic Regret in KL-Regularized Zero-Sum Markov Games

Anupam Nayak, Tong Yang, Osman Yagan +2

Reverse Kullback-Leibler (KL) divergence-based regularization with respect to a fixed reference policy is widely used in modern reinforcement learning to preserve the desired trait…

cs.LG2026

MELINOE: Fine-Tuning Enables Memory-Efficient Inference for Mixture-of-Experts Models

Arian Raje, Anupam Nayak, Gauri Joshi

Mixture-of-Experts (MoE) model architectures can significantly reduce the number of activated parameters per token, enabling computationally efficient training and inference. Howev…