6 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…
Think Clearly: Improving Reasoning via Redundant Token Pruning
Daewon Choi, Jimin Lee, Jihoon Tack +7
Recent large language models have shown promising capabilities in long-form reasoning, following structured chains of thought before arriving at a final answer. However, we observe…
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…
The Amazon Nova Family of Models: Technical Report and Model Card
Amazon AGI, Aaron Langford, Aayush Shah +783
We present Amazon Nova, a new generation of state-of-the-art foundation models that deliver frontier intelligence and industry-leading price performance. Amazon Nova Pro is a highl…
Adaptive Video Understanding Agent: Enhancing efficiency with dynamic frame sampling and feedback-driven reasoning
Sullam Jeoung, Goeric Huybrechts, Bhavana Ganesh +2
Understanding long-form video content presents significant challenges due to its temporal complexity and the substantial computational resources required. In this work, we propose…
SeRA: Self-Reviewing and Alignment of Large Language Models using Implicit Reward Margins
Jongwoo Ko, Saket Dingliwal, Bhavana Ganesh +3
Direct alignment algorithms (DAAs), such as direct preference optimization (DPO), have become popular alternatives for Reinforcement Learning from Human Feedback (RLHF) due to thei…