English
Related papers

Related papers: NITP: Next Implicit Token Prediction for LLM Pre-t…

200 papers

Machine learning interatomic potentials (MLIPs) enable efficient molecular dynamics (MD) simulations with ab initio accuracy and have been applied across various domains in physical science. However, their performance often relies on…

Computational Physics · Physics 2025-07-29 Taoyong Cui , Zhongyao Wang , Dongzhan Zhou , Yuqiang Li , Lei Bai , Wanli Ouyang , Mao Su , Shufei Zhang

Large Language Models (LLMs) have achieved impressive performance across a range of natural language processing tasks. However, recent advances demonstrate that further gains particularly in complex reasoning tasks require more than merely…

Computation and Language · Computer Science 2025-09-09 Wei Huang , Yizhe Xiong , Xin Ye , Zhijie Deng , Hui Chen , Zijia Lin , Guiguang Ding

In standard large vision-language models (LVLMs) pre-training, the model typically maximizes the joint probability of the caption conditioned on the image via next-token prediction (NTP); however, since only a small subset of caption tokens…

Computer Vision and Pattern Recognition · Computer Science 2025-05-15 Yangyi Chen , Hao Peng , Tong Zhang , Heng Ji

Neural symbolic processing aims to combine the generalization of logical learning approaches and the performance of neural networks. The Neural Theorem Proving (NTP) model by Rocktaschel et al (2017) learns embeddings for concepts and…

Machine Learning · Computer Science 2019-06-18 Michiel de Jong , Fei Sha

Formally verifying the correctness of mathematical proofs is more accessible than ever, however, the learning curve remains steep for many of the state-of-the-art interactive theorem provers (ITP). Deriving the most appropriate subsequent…

Logic in Computer Science · Computer Science 2024-11-05 Liao Zhang , David M. Cerna , Cezary Kaliszyk

Prompt learning has become one of the most efficient paradigms for adapting large pre-trained vision-language models to downstream tasks. Current state-of-the-art methods, like CoOp and ProDA, tend to adopt soft prompts to learn an…

Computer Vision and Pattern Recognition · Computer Science 2023-03-31 Sifan Long , Zhen Zhao , Junkun Yuan , Zichang Tan , Jiangjiang Liu , Luping Zhou , Shengsheng Wang , Jingdong Wang

Vision-language models such as CLIP achieve strong visual-textual alignment, but often suffer from overfitting and limited interpretability when adapted through continuous prompt learning. While discrete prompt optimization improves…

Computer Vision and Pattern Recognition · Computer Science 2026-05-07 Yating Wang , Yaqi Zhao , Yongshun Gong , Yilong Yin , Haoliang Sun

We study the evolution of latent space in fine-tuned NLP models. Different from the commonly used probing-framework, we opt for an unsupervised method to analyze representations. More specifically, we discover latent concepts in the…

Computation and Language · Computer Science 2022-10-25 Nadir Durrani , Hassan Sajjad , Fahim Dalvi , Firoj Alam

Next token prediction has been the standard training objective used in large language model pretraining. Representations are learned as a result of optimizing for token-level perplexity. We propose Continuous Concept Mixing (CoCoMix), a…

Machine Learning · Computer Science 2025-02-13 Jihoon Tack , Jack Lanchantin , Jane Yu , Andrew Cohen , Ilia Kulikov , Janice Lan , Shibo Hao , Yuandong Tian , Jason Weston , Xian Li

Recent empirical evidence shows that LLM representations encode human-interpretable concepts. Nevertheless, the mechanisms by which these representations emerge remain largely unexplored. To shed further light on this, we introduce a novel…

Machine Learning · Computer Science 2026-03-03 Yuhang Liu , Dong Gong , Yichao Cai , Erdun Gao , Zhen Zhang , Biwei Huang , Mingming Gong , Anton van den Hengel , Javen Qinfeng Shi

Detecting when a neural sequence model does "interesting" computation is an open problem. The next token prediction loss is a poor indicator: Low loss can stem from trivially predictable sequences that are uninteresting, while high loss may…

Machine Learning · Computer Science 2025-03-18 Vincent Herrmann , Róbert Csordás , Jürgen Schmidhuber

One of the current trends in robotics is to employ large language models (LLMs) to provide non-predefined command execution and natural human-robot interaction. It is useful to have an environment map together with its language…

Robotics · Computer Science 2025-01-09 Evgenii Kruzhkov , Sven Behnke

Trajectory prediction is a fundamental task for autonomous systems, requiring complex reasoning about multi-agent interactions and intents. Large language models (LLMs) have recently been adopted for this task, as they provide strong…

Artificial Intelligence · Computer Science 2026-05-29 Mincheol Kang , Hyunjin Lim , Bomin Kang , Daehee Park

The efficient computation of parametric solution sensitivities is a key challenge in the integration of learning-enhanced methods with nonlinear model predictive control (MPC), as their availability is crucial for many learning algorithms.…

Representations of the world environment play a crucial role in artificial intelligence. It is often inefficient to conduct reasoning and inference directly in the space of raw sensory representations, such as pixel values of images.…

Machine Learning · Computer Science 2022-04-12 Kenji Kawaguchi , Linjun Zhang , Zhun Deng

Linear text segmentation is a long-standing problem in natural language processing (NLP), focused on dividing continuous text into coherent and semantically meaningful units. Despite its importance, the task remains challenging due to the…

Computation and Language · Computer Science 2026-02-12 José Isidro , Filipe Cunha , Purificação Silvano , Alípio Jorge , Nuno Guimarães , Sérgio Nunes , Ricardo Campos

Fast weight architectures offer a promising alternative to attention-based transformers for long-context modeling by maintaining constant memory overhead regardless of context length. However, their potential is limited by the next-token…

Computation and Language · Computer Science 2026-02-19 Hee Seung Hwang , Xindi Wu , Sanghyuk Chun , Olga Russakovsky

Large-scale cross-modal pre-training paradigms have recently shown ubiquitous success on a wide range of downstream tasks, e.g., zero-shot classification, retrieval and image captioning. However, their successes highly rely on the scale and…

Computer Vision and Pattern Recognition · Computer Science 2023-01-05 Runhui Huang , Yanxin Long , Jianhua Han , Hang Xu , Xiwen Liang , Chunjing Xu , Xiaodan Liang

Multi-layer perceptrons (MLP) have proven to be effective scene encoders when combined with higher-dimensional projections of the input, commonly referred to as \textit{positional encoding}. However, scenes with a wide frequency spectrum…

Computer Vision and Pattern Recognition · Computer Science 2022-06-20 Zoe Landgraf , Alexander Sorkine Hornung , Ricardo Silveira Cabral

Large language models such as GPT and Llama are trained with a next-token prediction loss. In this work, we suggest that training language models to predict multiple future tokens at once results in higher sample efficiency. More…

Computation and Language · Computer Science 2024-05-01 Fabian Gloeckle , Badr Youbi Idrissi , Baptiste Rozière , David Lopez-Paz , Gabriel Synnaeve