English
Related papers

Related papers: What should post-training optimize? A test-time sc…

200 papers

Scaling laws are used to plan multi-million-dollar training runs, but fitting those laws can itself cost millions. In modern large-scale workflows, assembling a sufficiently informative set of pilot experiments is already a major…

Machine Learning · Computer Science 2026-04-27 Sijie Li , Shanda Li , Haowei Lin , Weiwei Sun , Ameet Talwalkar , Yiming Yang

Object frequency in the real world often follows a power law, leading to a mismatch between datasets with long-tailed class distributions seen by a machine learning model and our expectation of the model to perform well on all classes. We…

Computer Vision and Pattern Recognition · Computer Science 2020-03-25 Muhammad Abdullah Jamal , Matthew Brown , Ming-Hsuan Yang , Liqiang Wang , Boqing Gong

This paper proposes a novel formulation for reinforcement learning (RL) with large language models, explaining why and under what conditions the true sequence-level reward can be optimized via a surrogate token-level objective in policy…

Machine Learning · Computer Science 2025-12-04 Chujie Zheng , Kai Dang , Bowen Yu , Mingze Li , Huiqiang Jiang , Junrong Lin , Yuqiong Liu , Hao Lin , Chencan Wu , Feng Hu , An Yang , Jingren Zhou , Junyang Lin

Post-training alignment of large language models (LLMs) is a critical challenge, as not all tokens contribute equally to model performance. This paper introduces a selective alignment strategy that prioritizes high-impact tokens within…

Computation and Language · Computer Science 2025-07-11 Zhijin Dong

Neural scaling laws have driven the field's ever-expanding exponential growth in parameters, data and compute. While scaling behaviors for pretraining losses and discriminative benchmarks are well established, generative benchmarks such as…

Machine Learning · Computer Science 2026-02-03 Rylan Schaeffer , Noam Levi , Brando Miranda , Sanmi Koyejo

Large Language Models (LLMs) demonstrate strong capabilities in general coding tasks but encounter two key challenges when optimizing code: (i) the complexity of writing optimized code (such as performant CUDA kernels and competition-level…

Machine Learning · Computer Science 2026-01-12 Jiefu Ou , Sapana Chaudhary , Kaj Bostrom , Nathaniel Weir , Shuai Zhang , Huzefa Rangwala , George Karypis

Inference-time alignment enables large language models (LLMs) to generate outputs aligned with end-user preferences without further training. Recent post-training methods achieve this by using small guidance models to modify token…

Artificial Intelligence · Computer Science 2025-11-14 Sarat Chandra Bobbili , Ujwal Dinesha , Dheeraj Narasimha , Srinivas Shakkottai

Given a fixed budget for total model size, one must choose between training a single large model or combining the predictions of multiple smaller models. We investigate this trade-off for ensembles of random-feature ridge regression models…

Machine Learning · Computer Science 2025-10-28 Benjamin S. Ruben , William L. Tong , Hamza Tahir Chaudhry , Cengiz Pehlevan

This paper introduces a model-based approach for training feedback controllers for an autonomous agent operating in a highly nonlinear (albeit deterministic) environment. We desire the trained policy to ensure that the agent satisfies…

Systems and Control · Electrical Eng. & Systems 2024-08-29 Navid Hashemi , Bardh Hoxha , Danil Prokhorov , Georgios Fainekos , Jyotirmoy Deshmukh

Kaplan et al. [2020] (`Kaplan') and Hoffmann et al. [2022] (`Chinchilla') studied the scaling behavior of transformers trained on next-token language prediction. These studies produced different estimates for how the number of parameters…

Machine Learning · Computer Science 2024-11-22 Tim Pearce , Jinyeop Song

Reward-model-based fine-tuning is a central paradigm in aligning Large Language Models with human preferences. However, such approaches critically rely on the assumption that proxy reward models accurately reflect intended supervision, a…

Computation and Language · Computer Science 2026-01-21 Zixuan Liu , Siavash H. Khajavi , Guangkai Jiang , Xinru Liu

Prompt optimization improves the reasoning abilities of large language models (LLMs) without requiring parameter updates to the target model. Following heuristic-based "Think step by step" approaches, the field has evolved in two main…

Computation and Language · Computer Science 2025-07-25 Andreea Nica , Ivan Zakazov , Nicolas Mario Baldwin , Saibo Geng , Robert West

Reward models (RMs) play a crucial role in reinforcement learning from human feedback (RLHF), aligning model behavior with human preferences. However, existing benchmarks for reward models show a weak correlation with the performance of…

Machine Learning · Computer Science 2025-05-20 Sunghwan Kim , Dongjin Kang , Taeyoon Kwon , Hyungjoo Chae , Dongha Lee , Jinyoung Yeo

How can we train models whose post-trained capabilities survive subsequent fine-tuning? Rather than focusing on downstream interventions to mitigate forgetting of upstream capabilities, we study how upstream training choices - that is, the…

Machine Learning · Computer Science 2026-05-14 Lawrence Feng , Gaurav R. Ghosal , Jacob Mitchell Springer , Ziqian Zhong , Aditi Raghunathan

Open-ended post-training benefits from rewards that make prompt-specific success conditions explicit, rather than relying only on post-hoc scalar scores. In instruction following, writing, and decision-support tasks, response quality…

Computation and Language · Computer Science 2026-05-29 Zijun Weng , Xiaohui Hu , Shuangyong Song , Yongxiang Li , Kaidong Yu , Xuanjing Huang

Reasoning is a key component of language understanding in Large Language Models. While Chain-of-Thought prompting enhances performance via explicit intermediate steps, it suffers from sufficient token overhead and a fixed reasoning…

Computation and Language · Computer Science 2025-11-18 Xinyuan Wang , Dongjie Wang , Wangyang Ying , Haoyue Bai , Nanxu Gong , Sixun Dong , Kunpeng Liu , Yanjie Fu

Enabling LLMs to improve their outputs by using more test-time computation is a critical step towards building generally self-improving agents that can operate on open-ended natural language. In this paper, we study the scaling of…

Machine Learning · Computer Science 2024-08-07 Charlie Snell , Jaehoon Lee , Kelvin Xu , Aviral Kumar

This paper studies post-training large language models (LLMs) using preference feedback from a powerful oracle to help a model iteratively improve over itself. The typical approach for post-training LLMs involves Reinforcement Learning from…

Machine Learning · Computer Science 2024-04-08 Corby Rosset , Ching-An Cheng , Arindam Mitra , Michael Santacroce , Ahmed Awadallah , Tengyang Xie

Understanding real-world videos with complex semantics and long temporal dependencies remains a fundamental challenge in computer vision. Recent progress in multimodal large language models (MLLMs) has demonstrated strong capabilities in…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Hongyu Li , Songhao Han , Yue Liao , Junfeng Luo , Jialin Gao , Shuicheng Yan , Si Liu

The recent rapid progress in pre-training Large Language Models has relied on using self-supervised language modeling objectives like next token prediction or span corruption. On the other hand, Machine Translation Systems are mostly…

Computation and Language · Computer Science 2023-05-22 Andrea Schioppa , Xavier Garcia , Orhan Firat