English
Related papers

Related papers: Training-Trajectory-Aware Token Selection

200 papers

On-policy self-distillation, where a student is pulled toward a copy of itself conditioned on privileged context (e.g., a verified solution or feedback), offers a promising direction for advancing reasoning capability without a stronger…

Machine Learning · Computer Science 2026-05-13 Guobin Shen , Xiang Cheng , Chenxiao Zhao , Lei Huang , Jindong Li , Dongcheng Zhao , Xing Yu

On-policy distillation is pivotal for transferring reasoning capabilities to capacity-constrained models, yet remains prone to instability and negative transfer. We show that on-policy distillation can be interpreted, both theoretically and…

Machine Learning · Computer Science 2026-03-13 Jongwoo Ko , Sara Abdali , Young Jin Kim , Tianyi Chen , Pashmina Cameron

Large language models have recently enabled a generative paradigm for query expansion, but their high inference cost makes direct deployment difficult in practical retrieval systems. To address this issue, a retrieval-feedback-driven…

Information Retrieval · Computer Science 2026-03-17 Minghan Li , Guodong Zhou

Distillation enables compact Vision-Language Models (VLMs) to obtain strong reasoning capabilities, yet the prompts driving this process are typically chosen via simple heuristics or aggregated from off-the-shelf datasets. We reveal a…

Machine Learning · Computer Science 2026-05-20 Jaehun Jung , Hyunwoo Kim , Brandon Cui , Ximing Lu , David Acuna , Prithviraj Ammanabrolu , Yejin Choi

On-policy self-distillation has become a strong recipe for LLM reasoning, where a privileged teacher supervises the student's own rollouts while conditioning on the reference solution. A design choice shared by nearly all such methods,…

Artificial Intelligence · Computer Science 2026-05-28 Zihao Han , Tiangang Zhang , Huaibin Wang , Yilun Sun

Recently, research efforts have been concentrated on revealing how pre-trained model makes a difference in neural network performance. Self-supervision and semi-supervised learning technologies have been extensively explored by the…

Computer Vision and Pattern Recognition · Computer Science 2021-03-11 Cheng Cui , Ruoyu Guo , Yuning Du , Dongliang He , Fu Li , Zewu Wu , Qiwen Liu , Shilei Wen , Jizhou Huang , Xiaoguang Hu , Dianhai Yu , Errui Ding , Yanjun Ma

The ultimate goal of Dataset Distillation is to synthesize a small synthetic dataset such that a model trained on this synthetic set will perform equally well as a model trained on the full, real dataset. Until now, no method of Dataset…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Ziyao Guo , Kai Wang , George Cazenavette , Hui Li , Kaipeng Zhang , Yang You

Knowledge distillation from large language models (LLMs) assumes that the teacher's output distribution is a high-quality training signal. On reasoning tasks, this assumption is frequently violated. A model's intermediate representations…

Computation and Language · Computer Science 2026-03-16 Ryan Brown , Chris Russell

Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-thought reasoning large language models (LLMs), but the high inference cost of such models motivates distillation into smaller students. Most…

Machine Learning · Computer Science 2026-04-13 Zhaoyang Zhang , Shuli Jiang , Yantao Shen , Yuting Zhang , Dhananjay Ram , Shuo Yang , Zhuowen Tu , Wei Xia , Stefano Soatto

Knowledge distillation is a powerful technique for transferring knowledge from a pre-trained teacher model to a student model. However, the true potential of knowledge transfer has not been fully explored. Existing approaches primarily…

Machine Learning · Computer Science 2023-06-23 Shuoxi Zhang , Hanpeng Liu , Kun He

Large Language Models exhibit impressive reasoning capabilities across diverse tasks, motivating efforts to distill these capabilities into smaller models through generated reasoning data. However, direct training on such synthesized…

Computation and Language · Computer Science 2025-02-05 Shengmin Piao , Sanghyun Park

Recent think-answer approaches in VLMs, such as Qwen3-VL-Thinking, boost reasoning performance by leveraging intermediate thinking steps before the final answer, but their computational cost becomes substantial, especially for larger VLMs.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Seonghoon Yu , Dongjun Nam , Byung-Kwan Lee , Jeany Son

Foundation models have significantly enhanced 2D task performance, and recent works like Bridge3D have successfully applied these models to improve 3D scene understanding through knowledge distillation, marking considerable advancements.…

Computer Vision and Pattern Recognition · Computer Science 2024-10-18 Zhimin Chen , Liang Yang , Yingwei Li , Longlong Jing , Bing Li

Recent advances in text-to-speech (TTS) have enabled models to clone arbitrary unseen speakers and synthesize high-quality, natural-sounding speech. However, evaluation methods lag behind: typical mean opinion score (MOS) estimators perform…

Audio and Speech Processing · Electrical Eng. & Systems 2025-11-25 Guansu Wang , Peijie Sun

Data-centric distillation, including data augmentation, selection, and mixing, offers a promising path to creating smaller, more efficient student Large Language Models (LLMs) that retain strong reasoning abilities. However, there still…

Artificial Intelligence · Computer Science 2026-02-09 Ruichen Zhang , Rana Muhammad Shahroz Khan , Zhen Tan , Dawei Li , Song Wang , Tianlong Chen

Autonomous driving is an important and safety-critical task, and recent advances in LLMs/VLMs have opened new possibilities for reasoning and planning in this domain. However, large models demand substantial GPU memory and exhibit high…

Data quality plays a critical role in enhancing supervised fine-tuning (SFT) for large language models (LLMs), and token-level data selection has emerged as a promising direction for its fine-grained nature. Despite their strong empirical…

Artificial Intelligence · Computer Science 2025-10-22 Xiaohan Qin , Xiaoxing Wang , Ning Liao , Cancheng Zhang , Xiangdong Zhang , Mingquan Feng , Jingzhi Wang , Junchi Yan

Knowledge distillation, the technique of transferring knowledge from large, complex models to smaller ones, marks a pivotal step towards efficient AI deployment. Distilling Step-by-Step~(DSS), a novel method utilizing chain-of-thought~(CoT)…

Computation and Language · Computer Science 2024-06-11 Xin Chen , Hanxian Huang , Yanjun Gao , Yi Wang , Jishen Zhao , Ke Ding

In language reasoning, longer chains of thought consistently yield better performance, which naturally suggests that visual latent reasoning may likewise benefit from longer latent sequences. However, we discover a counterintuitive…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Chenfeng Wang , Wei He , Xuhan Zhu , Chunpeng Zhou , Qizhen Li , Song Yan , Yufei Zheng , Chengjun Yu , Fan Lu , Wei Zhai , Yang Cao , Pengfei Yu , Zheng-Jun Zha

We analyze reasoning in language models during task-specific fine-tuning and draws parallel between reasoning tokens--intermediate steps generated while solving problem and the human working memory. Drawing from cognitive science, we align…

Computation and Language · Computer Science 2025-12-01 Mukul Singh , Ananya Singha , Arjun Radhakrishna , Sumit Gulwani
‹ Prev 1 4 5 6 7 8 10 Next ›