6 papers
PETS: A Principled Framework Towards Optimal Trajectory Allocation for Efficient Test-Time Self-Consistency
Zhangyi Liu, Huaizhi Qu, Xiaowei Yin +4
Test-time scaling can improve model performance by aggregating stochastic reasoning trajectories. However, achieving sample-efficient test-time self-consistency under a limited bud…
History-Guided Iterative Visual Reasoning with Self-Correction
Xinglong Yang, Zhilin Peng, Zhanzhan Liu +2
Self-consistency methods are the core technique for improving the reasoning reliability of multimodal large language models (MLLMs). By generating multiple reasoning results throug…
Large Scale Retrieval for the LinkedIn Feed using Causal Language Models
Sudarshan Srinivasa Ramanujam, Antonio Alonso, Saurabh Kataria +20
In large scale recommendation systems like the LinkedIn Feed, the retrieval stage is critical for narrowing hundreds of millions of potential candidates to a manageable subset for…
Intern-S1: A Scientific Multimodal Foundation Model
Lei Bai, Zhongrui Cai, Yuhang Cao +173
In recent years, a plethora of open-source foundation models have emerged, achieving remarkable progress in some widely attended fields, with performance being quite close to that…
Improving physics-informed neural network extrapolation via transfer learning and adaptive activation functions
Athanasios Papastathopoulos-Katsaros, Alexandra Stavrianidi, Zhandong Liu
Physics-Informed Neural Networks (PINNs) are deep learning models that incorporate the governing physical laws of a system into the learning process, making them well-suited for so…
PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models
Shi Qiu, Shaoyang Guo, Zhuo-Yang Song +51
Current benchmarks for evaluating the reasoning capabilities of Large Language Models (LLMs) face significant limitations: task oversimplification, data contamination, and flawed e…