17 papers
Accelerated Test-Time Scaling with Model-Free Speculative Sampling
Woomin Song, Saket Dingliwal, Sai Muralidhar Jayanthi +4
Language models have demonstrated remarkable capabilities in reasoning tasks through test-time scaling techniques like best-of-N sampling and tree search. However, these approaches…
Compress, Gather, and Recompute: REFORMing Long-Context Processing in Transformers
Woomin Song, Sai Muralidhar Jayanthi, Srikanth Ronanki +5
As large language models increasingly gain popularity in real-world applications, processing extremely long contexts, often exceeding the model's pre-trained context limits, has em…
Mamba Drafters for Speculative Decoding
Daewon Choi, Seunghyuk Oh, Saket Dingliwal +9
Speculative decoding has emerged as a promising approach to accelerating large language model (LLM) generation using a fast drafter while maintaining alignment with the target mode…
Wanda++: Pruning Large Language Models via Regional Gradients
Yifan Yang, Kai Zhen, Bhavana Ganesh +11
Large Language Models (LLMs) pruning seeks to remove unimportant weights for inference speedup with minimal accuracy impact. However, existing methods often suffer from accuracy de…
Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation
Tharindu Kumarage, Ninareh Mehrabi, Anil Ramakrishna +6
Safety reasoning is a recent paradigm where LLMs reason over safety policies before generating responses, thereby mitigating limitations in existing safety measures such as over-re…
KG-LLM-Bench: A Scalable Benchmark for Evaluating LLM Reasoning on Textualized Knowledge Graphs
Elan Markowitz, Krupa Galiya, Greg Ver Steeg +1
Knowledge graphs have emerged as a popular method for injecting up-to-date, factual knowledge into large language models (LLMs). This is typically achieved by converting the knowle…