works on

From the 1 of 8 linked papers with an AI index.

collaborators

8 papers

cs.AI2026

Explaining Process Control Optimisation Recommendations via GradientSHAP and Implicit Differentiation

Paul Darm, Cem Alpturk, Kenneth Ulrich +3

The paper proposes a method that combines implicit differentiation with GradientSHAP and large language models to generate fast, real-time explanations for industrial process contr…

cs.LG2026

Faster Synchronous On-Policy RL via Straggler-Aware Group Sizing

Azal Ahmad Khan, Ammar Ahmed, Zeshan Fayyaz +3

Synchronous reinforcement learning methods such as Group Relative Policy Optimization (GRPO) provide stable and reproducible on-policy training, but they are highly vulnerable to s…

cs.AI2026

Retrieval-of-Thought: Efficient Reasoning via Reusing Thoughts

Ammar Ahmed, Azal Ahmad Khan, Ayaan Ahmad +3

Large reasoning models improve accuracy by producing long reasoning traces, but this inflates latency and cost, motivating inference-time efficiency. We propose Retrieval-of-Though…

cs.LG2025

Accelerating LLM Reasoning via Early Rejection with Partial Reward Modeling

Seyyed Saeid Cheshmi, Azal Ahmad Khan, Xinran Wang +2

Large Language Models (LLMs) are increasingly relied upon for solving complex reasoning tasks in domains such as mathematics, logic, and multi-step question answering. A growing li…

cs.CL2025

Systematic Evaluation of Optimization Techniques for Long-Context Language Models

Ammar Ahmed, Sheng Di, Franck Cappello +3

Large language models (LLMs) excel across diverse natural language processing tasks but face resource demands and limited context windows. Although techniques like pruning, quantiz…

cs.CL2025

Sem-DPO: Mitigating Semantic Inconsistency in Preference Optimization for Prompt Engineering

Anas Mohamed, Azal Ahmad Khan, Xinran Wang +5

Generative AI can now synthesize strikingly realistic images from text, yet output quality remains highly sensitive to how prompts are phrased. Direct Preference Optimization (DPO)…