English
Related papers

Related papers: Escaping Mode Collapse in LLM Generation via Geome…

200 papers

Unified Multimodal Models (UMMs) exhibit strong understanding, yet this capability often fails to effectively guide generation. We identify this as a Cognitive Gap: the model lacks the understanding of how to enhance its own generation…

Artificial Intelligence · Computer Science 2026-01-29 Zhenchen Tang , Songlin Yang , Zichuan Wang , Bo Peng , Yang Li , Beibei Dong , Jing Dong

While existing code large language models (code LLMs) exhibit impressive capabilities in code generation, their autoregressive sequential generation inherently lacks reversibility. This limitation hinders them from timely correcting…

Computation and Language · Computer Science 2024-09-26 Mouxiang Chen , Hao Tian , Zhongxin Liu , Xiaoxue Ren , Jianling Sun

Whether machines can originate novel content has been debated for nearly two centuries, from Lovelace's assertion that no engine can "originate anything" to Turing's question of whether a machine can amplify ideas brought in from outside.…

Multiagent Systems · Computer Science 2026-05-19 Weiyi Kong , Shiyang Lai , Jinghua Piao , James Evans

Large Language Models (LLMs) are increasingly used to automate software generation in embedded machine learning workflows, yet their outputs often fail silently or behave unpredictably. This article presents an empirical investigation of…

Software Engineering · Computer Science 2025-09-16 Roberto Morabito , Guanghan Wu

Reinforcement learning with verifiable rewards (RLVR) enables large language models to acquire slow, multi-step reasoning from sparse final-answer signals. We provide a statistical-physics picture of this emergence. We show that an…

Artificial Intelligence · Computer Science 2026-05-08 Sihan Hu , Xiansheng Cai , Yuan Huang , Zhiyuan Yao , Linfeng Zhang , Pan Zhang , Youjin Deng , Kun Chen

Reinforcement learning (RL), particularly GRPO, improves image generation quality significantly by comparing the relative performance of images generated within the same group. However, in the later stages of training, the model tends to…

Computer Vision and Pattern Recognition · Computer Science 2025-12-29 Henglin Liu , Huijuan Huang , Jing Wang , Chang Liu , Xiu Li , Xiangyang Ji

Model collapse, the progressive degradation of LLMs trained on their own outputs, has been characterized statistically but lacks a linguistic explanation for which structures degrade, in what order, and why. We show that iterated learning…

Computation and Language · Computer Science 2026-05-25 Dongxin Guo , Jikun Wu , Siu Ming Yiu

Although recent deep learning methods, especially generative models, have shown good performance in fast magnetic resonance imaging, there is still much room for improvement in high-dimensional generation. Considering that internal…

Computer Vision and Pattern Recognition · Computer Science 2022-12-13 Wei Zhang , Zengwei Xiao , Hui Tao , Minghui Zhang , Xiaoling Xu , Qiegen Liu

Large Language Models (LLMs) are widely used across multiple domains but continue to raise concerns regarding security and fairness. Beyond known attack vectors such as data poisoning and prompt injection, LLMs are also vulnerable to…

Artificial Intelligence · Computer Science 2025-10-01 Matheus Vinicius da Silva de Oliveira , Jonathan de Andrade Silva , Awdren de Lima Fontao

The dominant approach to generating from language models subject to some constraint is locally constrained decoding (LCD), incrementally sampling tokens at each time step such that the constraint is never violated. Typically, this is…

ReParameterization (RP) Policy Gradient Methods (PGMs) have been widely adopted for continuous control tasks in robotics and computer graphics. However, recent studies have revealed that, when applied to long-term reinforcement learning…

Machine Learning · Computer Science 2023-11-01 Shenao Zhang , Boyi Liu , Zhaoran Wang , Tuo Zhao

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge to generate a response within a context with improved accuracy and reduced hallucinations. However, multi-modal RAG systems face…

Machine Learning · Computer Science 2025-01-09 Matin Mortaheb , Mohammad A. Amir Khojastepour , Srimat T. Chakradhar , Sennur Ulukus

Reinforcement learning (RL) has emerged as a powerful paradigm for fine-tuning Large Language Models (LLMs) for text generation. In particular, recent LLMs such as ChatGPT and GPT-4 can engage in fluent conversations with users after…

Machine Learning · Computer Science 2023-11-14 Jonathan D. Chang , Kiante Brantley , Rajkumar Ramamurthy , Dipendra Misra , Wen Sun

Large language models (LLMs) have achieved impressive performance in code generation recently, offering programmers revolutionary assistance in software development. However, due to the auto-regressive nature of LLMs, they are susceptible…

Software Engineering · Computer Science 2025-03-25 Xue Jiang , Yihong Dong , Yongding Tao , Huanyu Liu , Zhi Jin , Wenpin Jiao , Ge Li

The massive adoption of large language models (LLMs) demands efficient deployment strategies. However, the auto-regressive decoding process, which is fundamental to how most LLMs generate text, poses challenges to achieve efficient serving.…

Computation and Language · Computer Science 2024-01-15 Mingdao Liu , Aohan Zeng , Bowen Wang , Peng Zhang , Jie Tang , Yuxiao Dong

An important function of autonomous microrobots is the ability to perform robust movement over terrain. This paper explores an edge ML approach to microrobot locomotion, allowing for on-device, lower latency control under compute, memory,…

Robotics · Computer Science 2026-01-01 Yichen Liu , Kesava Viswanadha , Zhongyu Li , Nelson Lojo , Kristofer S. J. Pister

Large language models (LLMs) have shown remarkable abilities in logical reasoning, in-context learning, and code generation. However, translating natural language instructions into effective robotic control policies remains a significant…

Machine Learning · Computer Science 2025-08-28 Utsav Singh , Pramit Bhattacharyya , Vinay P. Namboodiri

Routing has emerged as a promising strategy for balancing performance and cost in large language model (LLM) systems that combine lightweight models with powerful but expensive large models. Recent studies show that \emph{probe routing},…

Artificial Intelligence · Computer Science 2026-03-27 Yaopei Zeng , Congchao Wang , Blake JianHang Chen , Lu Lin

In this work we perform full-state LQR feedback control of fluid flows using non-intrusive data-driven reduced-order models. We propose a model reduction method called low-rank Dynamic Mode Decomposition (lrDMD) that solves for a…

Fluid Dynamics · Physics 2020-01-08 Palash Sashittal , Daniel J. Bodony

While Large Language Models (LLMs) can generate fluent text, producing high-quality creative stories remains challenging. Reinforcement Learning (RL) offers a promising solution but faces two critical obstacles: designing reliable reward…

Artificial Intelligence · Computer Science 2026-01-13 Zhaoyan Li , Hang Lei , Yujia Wang , Lanbo Liu , Hao Liu , Liang Yu