English
Related papers

Related papers: Flexible Realignment of Language Models

200 papers

Accurate multi-turn intent classification is essential for advancing conversational AI systems. However, challenges such as the scarcity of comprehensive datasets and the complexity of contextual dependencies across dialogue turns hinder…

Computation and Language · Computer Science 2024-11-20 Junhua Liu , Yong Keat Tan , Bin Fu , Kwan Hui Lim

This paper introduces KunLunBaizeRAG, a reinforcement learning-driven reasoning framework designed to enhance the reasoning capabilities of large language models (LLMs) in complex multi-hop question-answering tasks. The framework addresses…

Artificial Intelligence · Computer Science 2025-06-30 Cheng Li , Jiexiong Liu , Yixuan Chen , Qihang Zhou , KunLun Meta

Reinforcement learning (RL) for large language model reasoning is frequently hindered by signal loss, a phenomenon where standard uniform sampling with small group sizes fails to uncover informative learning signals for difficult prompts.…

Machine Learning · Computer Science 2025-12-08 Wei Xiong , Chenlu Ye , Baohao Liao , Hanze Dong , Xinxing Xu , Christof Monz , Jiang Bian , Nan Jiang , Tong Zhang

Large reasoning models (LRMs) excel on complex problems but face a critical barrier to efficiency: reinforcement learning (RL) training requires long rollouts for outcome-based rewards, where autoregressive decoding dominates time and…

Machine Learning · Computer Science 2026-02-20 Zeliang Zhang , Xiaodong Liu , Hao Cheng , Hao Sun , Chenliang Xu , Jianfeng Gao

Recent Vision-Language-Action (VLA) models show strong generalization capabilities, yet they lack introspective mechanisms for anticipating failures and requesting help from a human supervisor. We present \textbf{INSIGHT}, a learning…

Robotics · Computer Science 2026-05-26 Ulas Berk Karli , Ziyao Shangguan , Tesca FItzgerald

This study investigates the effectiveness of reinforcement learning (RL) fine-tuning techniques on a compact language model (Qwen2.5-0.5B Base) for two challenging tasks: instruction following and mathematical reasoning. We compare…

Computation and Language · Computer Science 2025-07-29 Yifu Han , Geo Zhang

Masked diffusion language models (MDLMs) have emerged as a promising alternative to dominant autoregressive approaches. Although they achieve competitive performance on several tasks, a substantial gap remains in open-ended text generation.…

Computation and Language · Computer Science 2026-02-02 Mengyu Ye , Ryosuke Takahashi , Keito Kudo , Jun Suzuki

Large language models exhibit systematic vulnerabilities to adversarial attacks despite extensive safety alignment. We provide a mechanistic analysis revealing that position-dependent gradient weakening during autoregressive training…

Machine Learning · Computer Science 2025-11-18 Thong Bach , Dung Nguyen , Thao Minh Le , Truyen Tran

As Low-Rank Adaptation (LoRA) becomes the standard approach for efficiently fine-tuning large language models (LLMs), shared clusters increasingly execute many concurrent LoRA training jobs over the same frozen backbone. While recent…

Machine Learning · Computer Science 2026-02-16 Kevin Li , Dibyadeep Saha , Avni Kanodia , Fan Lai

Speculative decoding accelerates inference in large language models (LLMs) by generating multiple draft tokens simultaneously. However, existing methods often struggle with token misalignment between the training and decoding phases,…

Computation and Language · Computer Science 2025-10-21 Shijing Hu , Jingyang Li , Xingyu Xie , Zhihui Lu , Kim-Chuan Toh , Pan Zhou

The training and fine-tuning of large language models (LLMs) often involve diverse textual data from multiple sources, which poses challenges due to conflicting gradient directions, hindering optimization and specialization. These…

Computation and Language · Computer Science 2025-02-04 Yinghao Li , Vianne Gao , Chao Zhang , MohamadAli Torkamani

Reinforcement learning has been applied in operation research and has shown promise in solving large combinatorial optimization problems. However, existing works focus on developing neural network architectures for certain problems. These…

Optimization and Control · Mathematics 2023-03-24 Ching Pui Wan , Tung Li , Jason Min Wang

Recent studies have shown that the denoising process in (generative) diffusion models can induce meaningful (discriminative) representations inside the model, though the quality of these representations still lags behind those learned…

Computer Vision and Pattern Recognition · Computer Science 2025-06-19 Sihyun Yu , Sangkyung Kwak , Huiwon Jang , Jongheon Jeong , Jonathan Huang , Jinwoo Shin , Saining Xie

Token-level adaptive computation seeks to reduce inference cost by allocating more computation to harder tokens and less to easier ones. However, prior work is primarily evaluated on natural-language benchmarks using task-level metrics,…

Computation and Language · Computer Science 2026-02-10 Ibraheem Muhammad Moosa , Suhas Lohit , Ye Wang , Moitreya Chatterjee , Wenpeng Yin

Recently, deep reasoning large language models(LLMs) like DeepSeek-R1 have made significant progress in tasks such as mathematics and coding. Inspired by this, several studies have employed reinforcement learning(RL) to enhance models' deep…

Computation and Language · Computer Science 2025-05-28 Zheng Li , Mao Zheng , Mingyang Song , Wenjie Yang

The integration of Vision-Language-Action (VLA) models into autonomous driving systems offers a unified framework for interpreting complex scenes and executing control commands. However, the necessity to incorporate historical multi-view…

Robotics · Computer Science 2026-03-30 Yiru Wang , Anqing Jiang , Shuo Wang , Yuwen Heng , Zichong Gu , Hao Sun

Small Language Models (SLMs) enable cost-effective, on-device and latency-sensitive AI applications, yet their deployment in Traditional Chinese (TC) remains hindered by token-level instability - models unpredictably emit non-TC characters…

Computation and Language · Computer Science 2025-10-03 Yu-Cheng Chih , Ming-Tao Duan , Yong-Hao Hou

Existing methods for extracting reward signals in Reinforcement Learning typically rely on labeled data and dedicated training splits, a setup that contrasts with how humans learn directly from their environment. In this work, we propose…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Akshit Singh , Shyam Marjit , Wei Lin , Paul Gavrikov , Serena Yeung-Levy , Hilde Kuehne , Rogerio Feris , Sivan Doveh , James Glass , M. Jehanzeb Mirza

General-purpose large language models (LLMs) are increasingly deployed in verticals such as telecommunications, where adaptation is hindered by scarce, low-information-density corpora and tight mobile/edge constraints. We propose Data…

Machine Learning · Computer Science 2025-11-11 Zhicheng Zhou , Jing Li , Suming Qiu , Junjie Huang , Linyuan Qiu , Zhijie Sun

The ability of Large Language Models (LLMs) to solve complex tasks has made them crucial in the development of AI-based applications. However, the high computational requirements to fine-tune these LLMs on downstream tasks pose significant…

Computation and Language · Computer Science 2025-09-08 Raul Singh , Nicolo Brunello , Vincenzo Scotti , Mark James Carman
‹ Prev 1 4 5 6 7 8 10 Next ›