English
Related papers

Related papers: Training-Trajectory-Aware Token Selection

200 papers

Lipreading has witnessed a lot of progress due to the resurgence of neural networks. Recent works have placed emphasis on aspects such as improving performance by finding the optimal architecture or improving generalization. However, there…

Computer Vision and Pattern Recognition · Computer Science 2021-06-03 Pingchuan Ma , Brais Martinez , Stavros Petridis , Maja Pantic

Converting a pretrained Transformer into a more efficient hybrid model through distillation offers a promising approach to reducing inference costs. However, achieving high-quality generation in distilled models requires careful joint…

Computation and Language · Computer Science 2026-03-30 Juan Gabriel Kostelec , Xiang Wang , Axel Laborieux , Christos Sourmpis , Qinghai Guo

While multi-view 3D reconstruction has shifted toward large-scale foundation models capable of inferring globally consistent geometry, their reliance on massive computational clusters for training has created a significant barrier to entry…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Brandon Leblanc , Charalambos Poullis

Diffusion Transformers (DiTs) achieve superior image generation quality but suffer from quadratic computational complexity relative to token count. While various token reduction (TR) methods have been proposed to mitigate this cost, they…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Hangyeol Lee , Hyojeong Lee , Joo-Young Kim

The push to compress and impart the proficiency of Large Language Models (LLMs) into more deployable and efficient Small Language Models (SLMs) has benefited from improvements in knowledge distillation (KD) techniques. These techniques…

Artificial Intelligence · Computer Science 2025-07-02 Shreyansh Padarha

Trajectory prediction remains a critical yet challenging component in autonomous driving systems, requiring sophisticated reasoning capabilities while meeting strict real-time deployment constraints. While knowledge distillation has…

Artificial Intelligence · Computer Science 2026-04-14 Wenchang Duan

Diffusion models have emerged as the mainstream approach for visual generation. However, these models typically suffer from sample inefficiency and high training costs. Consequently, methods for efficient finetuning, inference and…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Felix Krause , Timy Phan , Ming Gui , Stefan Andreas Baumann , Vincent Tao Hu , Björn Ommer

Standard Latent Diffusion Models rely on a complex, three-part architecture consisting of a separate encoder, decoder, and diffusion network, which are trained in multiple stages. This modular design is computationally inefficient, leads to…

Computer Vision and Pattern Recognition · Computer Science 2025-11-19 Xiyuan Wang , Muhan Zhang

Current long chain-of-thought (long-CoT) models excel at mathematical reasoning but rely on slow and error-prone natural language traces. Tool-augmented agents address arithmetic via code execution, but often falter on complex logical…

Computation and Language · Computer Science 2025-09-03 Weihua Du , Pranjal Aggarwal , Sean Welleck , Yiming Yang

While long Chain-of-Thought (CoT) distillation effectively transfers reasoning capability to smaller language models, the reasoning process often remains redundant and computational budget uncontrollable, leading to inefficient resource…

Computation and Language · Computer Science 2025-12-29 Lujie Niu , Lei Shen , Yi Jiang , Caixia Yuan , Xiaojie Wang , Wenbo Su , Bo zheng

Reinforcement Learning (RL) has significantly improved large language model reasoning, but existing RL fine-tuning methods rely heavily on heuristic techniques such as entropy regularization and reweighting to maintain stability. In…

Computation and Language · Computer Science 2026-05-26 Shiqi Liu , Zeyu He , Guojian Zhan , Letian Tao , Zhilong Zheng , Jiang Wu , Yinuo Wang , Yang Guan , Kehua Sheng , Bo Zhang , Keqiang Li , Jingliang Duan , Shengbo Eben Li

The transfer of knowledge from one policy to another is an important tool in Deep Reinforcement Learning. This process, referred to as distillation, has been used to great success, for example, by enhancing the optimisation of agents,…

Enhancing small language models for real-life application deployment is a significant challenge facing the research community. Due to the difficulties and costs of using large language models, researchers are seeking ways to effectively…

Computation and Language · Computer Science 2024-09-20 Mohamad Ballout , Ulf Krumnack , Gunther Heidemann , Kai-Uwe Kühnberger

Reinforcement learning (RL) has played an important role in improving the reasoning ability of large language models (LLMs). Some studies apply RL directly to \textit{smaller} base models (known as zero-RL) and also achieve notable…

Artificial Intelligence · Computer Science 2025-05-28 Xiao Hu , Xingyu Lu , Liyuan Mao , YiFan Zhang , Tianke Zhang , Bin Wen , Fan Yang , Tingting Gao , Guorui Zhou

The advent of scalable deep models and large datasets has improved the performance of Neural Machine Translation. Knowledge Distillation (KD) enhances efficiency by transferring knowledge from a teacher model to a more compact student…

Computation and Language · Computer Science 2024-03-26 Heegon Jin , Seonil Son , Jemin Park , Youngseok Kim , Hyungjong Noh , Yeonsoo Lee

Large language models (LLMs) excel at reasoning tasks requiring long thought sequences for planning, reflection, and refinement. However, their substantial model size and high computational demands are impractical for widespread deployment.…

Computation and Language · Computer Science 2025-07-03 Dongyi Ding , Tiannan Wang , Chenghao Zhu , Meiling Tao , Yuchen Eleanor Jiang , Wangchunshu Zhou

Machine Speech Chain, simulating the human perception-production loop, proves effective in jointly improving ASR and TTS. We propose TokenChain, a fully discrete speech chain coupling semantic-token ASR with a two-stage TTS: an…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-05 Mingxuan Wang , Satoshi Nakamura

Decoding strategies play a central role in shaping the reasoning ability of large language models (LLMs). Traditional methods such as greedy decoding and beam search often suffer from error propagation, while sampling-based approaches…

Large language models (LMs) beyond a certain scale, demonstrate the emergent capability of generating free-text rationales for their predictions via chain-of-thought (CoT) prompting. While CoT can yield dramatically improved performance,…

Computation and Language · Computer Science 2023-09-01 Peifeng Wang , Zhengyang Wang , Zheng Li , Yifan Gao , Bing Yin , Xiang Ren

Owing to their powerful semantic reasoning capabilities, Large Language Models (LLMs) have been effectively utilized as recommenders, achieving impressive performance. However, the high inference latency of LLMs significantly restricts…

Information Retrieval · Computer Science 2024-08-21 Yu Cui , Feng Liu , Pengbo Wang , Bohao Wang , Heng Tang , Yi Wan , Jun Wang , Jiawei Chen