Parallel test-time scaling, which generates multiple candidate solutions for a single problem, is a powerful technique for improving large language model performance. However, it is hindered by two key bottlenecks: accurately selecting the correct solution from the candidate pool, and the high inference latency from generating many full solutions. We argue that both challenges are fundamentally linked to verifier calibration, as a well-calibrated verifier improves answer selection and enables early-stopping strategies to reduce latency. However, existing non-generative verifiers are limited as they score each candidate in isolation, overlooking rich contextual information across the set of candidates. To address this, we introduce the Multi-Sequence Verifier (MSV), a lightweight verifier that predicts each candidate's correctness conditioned on the full sampled set. MSV achieves improved calibration, which directly enhances best-of-N selection performance and empowers a novel early-stopping framework. Across challenging mathematical reasoning benchmarks, MSV improves best-of-64 accuracy by up to 6\% relative to strong baselines, and in the early-stopping setting reaches the same accuracy as baselines with less than half the latency.
Probing the effectiveness of World Models for Spatial Reasoning through Test-time Scaling
MILA – Quebec AI Institute(魁北克人工智能研究所);Polytechnique Montréal(蒙特利尔理工学院);MIT CSAIL(麻省理工学院计算机科学与人工智能实验室);Institute for Machine Learning, Johannes Kepler University Linz(林茨约瑟夫·夫兰克大学机器学习研究所);Nankai University(南开大学)
Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification
Meta FAIR;Center for Data Science, New York University(纽约大学数据科学中心);Courant Institue of Mathematical Sciences, New York University(纽约大学柯朗数学科学研究所);School of Mathematical Sciences, Peking University(北京大学数学科学学院)
VIA-SD: Verification via Intra-Model Routing for Speculative Decoding
ReLER, The State Key Lab of Brain Machine Intelligence, Zhejiang University(脑机智能国家重点实验室,浙江大学);College of Artificial Intelligence, Zhejiang University(人工智能学院,浙江大学);CFAR, Agency for Science, Technology and Research, Singapore(科学与技术研究局,新加坡);National University of Singapore(新加坡国立大学)
Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis
University of YYY(YYY大学);Institute of WWW(WWW研究所);The Hong Kong University of Science and Technology(香港科技大学);Northwestern Polytechnical University(西北工业大学);University of Science and Technology Beijing(北京科技大学);Hong Kong Baptist University(香港浸会大学);Chinese University of Hong Kong(香港中文大学);Shanghai Mobvoi Information Technology Co., Ltd(上海小问信息技术有限公司);University of Rochester(罗切斯特大学);University of Surrey(萨里大学)
From Unaligned to Aligned: Scaling Multilingual LLMs with Multi-Way Parallel Corpora
Department of Computer Science and Technology, Tsinghua University(清华大学计算机科学与技术系);Technical University of Munich(慕尼黑技术大学);Munich Center for Machine Learning(慕尼黑机器学习中心);Minzu University of China(民族大学);Institute for AI, Tsinghua University(清华大学人工智能研究院)