大模型推理能力

BAR Conjecture: the Feasibility of Inference Budget-Constrained LLM Services with Authenticity and Reasoning

Jinan Zhou, Rajat Ghosh, Vaishnavi Bhargava, Debojyoti Dutta, Aryan Singhal

机构 * Nutanix 纠错

专题命中 测试时计算 ：reasoning(title,abstract)；分类 cs.LG

CTR-Driven Ad Text Generation via Online Feedback Preference Optimization

Yanda Chen, Zihui Ren, Qixiang Gao, Jiale Chen, Si Chen, Xubin Li, Tiezheng Ge, Bo Zheng

专题命中 测试时计算 ：reasoning(abstract)；chain-of-thought(abstract)；CoT(abstract)

Comments 13 pages, 7 figures, 8 tables

Scaling Vision Pre-Training to 4K Resolution

Baifeng Shi, Boyi Li, Han Cai, Yao Lu, Sifei Liu, Marco Pavone, Jan Kautz, Song Han, Trevor Darrell, Pavlo Molchanov, Hongxu Yin

机构 * UC Berkeley（加州大学伯克利分校） ； NVIDIA（英伟达） 纠错

专题命中 测试时计算 ：test-time compute(abstract)

Comments CVPR 2025. Project Page: https://nvlabs.github.io/PS3