English
Related papers

Related papers: Geometry-Aware Decoding with Wasserstein-Regulariz…

200 papers

We consider the problem of sampling from a distribution governed by a potential function. This work proposes an explicit score based MCMC method that is deterministic, resulting in a deterministic evolution for particles rather than a…

Machine Learning · Statistics 2023-10-03 Hong Ye Tan , Stanley Osher , Wuchen Li

Autoregressive (AR) architectures have achieved significant successes in LLMs, inspiring explorations for video generation. In LLMs, top-p/top-k sampling strategies work exceptionally well: language tokens have high semantic density and low…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Yizhao Han , Tianxing Shi , Zhao Wang , Zifan Xu , Zhiyuan Pu , Mingxiao Li , Qian Zhang , Wei Yin , Xiao-Xiao Long

Modeling latent representations in a hyperspherical space has proven effective for capturing directional similarities in high-dimensional text data, benefiting topic modeling. Variational autoencoder-based neural topic models (VAE-NTMs)…

Computation and Language · Computer Science 2025-08-18 Suman Adhya , Debarshi Kumar Sanyal

Large Language Models (LLMs) have demonstrated impressive performance on multiple-choice question answering (MCQA) benchmarks, yet they remain highly vulnerable to minor input perturbations. In this paper, we introduce and evaluate Token…

Computation and Language · Computer Science 2025-06-12 Jui-Ming Yao , Hao-Yuan Chen , Zi-Xian Tang , Bing-Jia Tan , Sheng-Wei Peng , Bing-Cheng Xie , Shun-Feng Su

The strong performance of large language models (LLMs) raises extensive discussion on their application to code generation. Recent research suggests continuous program refinements through visible tests to improve code generation accuracy in…

Software Engineering · Computer Science 2025-05-26 Chao Lei , Yanchuan Chang , Nir Lipovetzky , Krista A. Ehinger

Language models (LMs) are trained on billions of tokens in an attempt to recover the true language distribution. Still, vanilla random sampling from LMs yields low quality generations. Decoding algorithms attempt to restrict the LM…

Machine Learning · Computer Science 2026-01-06 Kareem Ahmed , Sameer Singh

Tree-Sliced methods have recently emerged as an alternative to the traditional Sliced Wasserstein (SW) distance, replacing one-dimensional lines with tree-based metric spaces and incorporating a splitting mechanism for projecting measures.…

Machine Learning · Computer Science 2025-06-10 Thanh Tran , Viet-Hoang Tran , Thanh Chu , Trang Pham , Laurent El Ghaoui , Tam Le , Tan M. Nguyen

Recent reasoning Large Language Models (LLMs) demonstrate remarkable problem-solving abilities but often generate long thinking traces whose utility is unclear. Our work aims to improve their efficiency, enabling them to reach high…

Computation and Language · Computer Science 2026-05-11 Xiang Liu , Xuming Hu , Xiaowen Chu , Eunsol Choi

Optimal transport and the Wasserstein distance $\mathcal{W}_p$ have recently seen a number of applications in the fields of statistics, machine learning, data science, and the physical sciences. These applications are however severely…

Statistics Theory · Mathematics 2024-05-24 Ruiyu Han , Cynthia Rush , Johannes Wiesel

Large Language Models (LLMs) apply uniform computation to all tokens, despite language exhibiting highly non-uniform information density. This token-uniform regime wastes capacity on locally predictable spans while under-allocating…

Hyperparameter transfer allows extrapolating optimal optimization hyperparameters from small to large scales, making it critical for training large language models (LLMs). This is done either by fitting a scaling law to the hyperparameters…

Machine Learning · Computer Science 2026-05-21 Dayal Singh Kalra , Maissam Barkeshli

High-quality quadrilateral mesh generation is a fundamental challenge in computer graphics. Traditional optimization-based methods are often constrained by the topological quality of input meshes and suffer from severe efficiency…

Graphics · Computer Science 2026-03-12 Yuguang Chen , Xinhai Liu , Xiangyu Zhu , Yiling Zhu , Zhuo Chen , Dongyu Zhang , Chunchao Guo

Solving tabular math word problems (TMWPs) has become a critical role in evaluating the mathematical reasoning ability of large language models (LLMs), where large-scale TMWP samples are commonly required for LLM fine-tuning. Since the…

Computation and Language · Computer Science 2024-12-23 Xiaoqiang Kang , Zimu Wang , Xiaobo Jin , Wei Wang , Kaizhu Huang , Qiufeng Wang

Text-to-CAD code generation is a long-horizon task that translates textual instructions into long sequences of interdependent operations. Existing methods typically decode text directly into executable code (e.g., bpy) without explicitly…

Artificial Intelligence · Computer Science 2026-04-14 Shengjie Gong , Wenjie Peng , Hongyuan Chen , Gangyu Zhang , Yunqing Hu , Huiyuan Zhang , Shuangping Huang , Tianshui Chen

We study the interaction between entropy and Wasserstein distance in free probability theory. In particular, we give lower bounds for several versions of free entropy dimension along Wasserstein geodesics, as well as study their topological…

Operator Algebras · Mathematics 2025-07-08 David Jekel

The prevailing assumption of an exponential decay in large language model (LLM) reliability with sequence length, predicated on independent per-token error probabilities, posits an inherent limitation for long autoregressive outputs. Our…

Computation and Language · Computer Science 2026-05-07 Mikhail L. Arbuzov , Sisong Bei , Ziwei Dong , Dmitri Kalaev , Alexey A. Shvets

The prohibitive sizes of Large Language Models (LLMs) today make it difficult to deploy them on memory-constrained edge devices. This work introduces $\rm CALDERA$ -- a new post-training LLM compression algorithm that harnesses the inherent…

Machine Learning · Computer Science 2024-11-05 Rajarshi Saha , Naomi Sagan , Varun Srivastava , Andrea J. Goldsmith , Mert Pilanci

Making sense of Wasserstein distances between discrete measures in high-dimensional settings remains a challenge. Recent work has advocated a two-step approach to improve robustness and facilitate the computation of optimal transport, using…

Machine Learning · Computer Science 2019-09-04 François-Pierre Paty , Marco Cuturi

This work studies the widely adopted ancestral sampling algorithms for auto-regressive language models, which is not widely studied in the literature. We use the quality-diversity (Q-D) trade-off to investigate three popular sampling…

Computation and Language · Computer Science 2020-09-16 Moin Nadeem , Tianxing He , Kyunghyun Cho , James Glass

Cross-lingual or cross-domain correspondences play key roles in tasks ranging from machine translation to transfer learning. Recently, purely unsupervised methods operating on monolingual embeddings have become effective alignment tools.…

Computation and Language · Computer Science 2018-09-05 David Alvarez-Melis , Tommi S. Jaakkola
‹ Prev 1 8 9 10 Next ›