6 papers
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…
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…
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…
From Code to Compliance: Assessing ChatGPT's Utility in Designing an Accessible Webpage -- A Case Study
Ammar Ahmed, Margarida Fresco, Fredrik Forsberg +1
Web accessibility ensures that individuals with disabilities can access and interact with digital content without barriers, yet a significant majority of most used websites fail to…
MeanCache: User-Centric Semantic Caching for LLM Web Services
Waris Gill, Mohamed Elidrisi, Pallavi Kalapatapu +3
Large Language Models (LLMs) like ChatGPT and Llama have revolutionized natural language processing and search engine dynamics. However, these models incur exceptionally high compu…
MAP: Multi-Human-Value Alignment Palette
Xinran Wang, Qi Le, Ammar Ahmed +5
Ensuring that generative AI systems align with human values is essential but challenging, especially when considering multiple human values and their potential trade-offs. Since hu…