English
Related papers

Related papers: Slow-Fast Inference: Training-Free Inference Accel…

200 papers

Speculative decoding is a widely used technique for accelerating inference in large language models (LLMs), but its performance degrades as input length grows, with significant drops even at moderate lengths. Yet, this early degradation has…

Computation and Language · Computer Science 2026-01-21 Jungyoub Cha , Hyunjong Kim , Sungzoon Cho

Long-context modeling is crucial for next-generation language models, yet the high computational cost of standard attention mechanisms poses significant computational challenges. Sparse attention offers a promising direction for improving…

Accurate uncertainty quantification is crucial for making reliable decisions in various supervised learning scenarios, particularly when dealing with complex, multimodal data such as images and text. Current approaches often face notable…

Machine Learning · Statistics 2026-03-30 Xinyu Tian , Xiaotong Shen

Large language models (LLMs) have exhibited impressive reasoning abilities on a wide range of complex tasks. However, enhancing these capabilities through post-training remains resource intensive, particularly in terms of data and…

Artificial Intelligence · Computer Science 2025-08-13 Shuo Cai , Su Lu , Qi Zhou , Kejing Yang , Zhijie Sang , Congkai Xie , Hongxia Yang

Posterior inference in directed graphical models is commonly done using a probabilistic encoder (a.k.a inference model) conditioned on the input. Often this inference model is trained jointly with the probabilistic decoder (a.k.a generator…

Machine Learning · Computer Science 2019-12-21 Amir Zadeh , Smon Hessner , Yao-Chong Lim , Louis-Phlippe Morency

We propose a sequence-to-sequence singing synthesizer, which avoids the need for training data with pre-aligned phonetic and acoustic features. Rather than the more common approach of a content-based attention mechanism combined with an…

Sound · Computer Science 2020-02-21 Merlijn Blaauw , Jordi Bonada

Recent progress in large language models (LLMs) has focused on test-time scaling to improve reasoning via increased inference computation, but often at the cost of efficiency. We revisit test-time behavior and uncover a simple yet…

Computation and Language · Computer Science 2026-01-13 Zhen Yang , Mingyang Zhang , Feng Chen , Ganggui Ding , Liang Hou , Xin Tao , Ying-Cong Chen

Reasoning language models have demonstrated remarkable capabilities on challenging tasks by generating elaborate chain-of-thought (CoT) solutions. However, such lengthy generation shifts the inference bottleneck from compute-bound to…

Split Federated Learning is a system-efficient federated learning paradigm that leverages the rich computing resources at a central server to train model partitions. Data heterogeneity across silos, however, presents a major challenge…

Machine Learning · Computer Science 2025-11-18 Mingkun Yang , Ran Zhu , Qing Wang , Jie Yang

Decoding stimuli or behaviour from recorded neural activity is a common approach to interrogate brain function in research, and an essential part of brain-computer and brain-machine interfaces. Reliable decoding even from small neural…

Neurons and Cognition · Quantitative Biology 2023-01-06 Justin Jude , Matthew G. Perich , Lee E. Miller , Matthias H. Hennig

Recent advances in large language models have demonstrated that Supervised Fine-Tuning (SFT) with Chain-of-Thought (CoT) reasoning data distilled from large reasoning models (e.g., DeepSeek R1) can effectively transfer reasoning…

Computation and Language · Computer Science 2025-05-22 Bin Yu , Hang Yuan , Haotian Li , Xueyin Xu , Yuliang Wei , Bailing Wang , Weizhen Qi , Kai Chen

Flow models are effective at progressively generating realistic images, but they generally struggle to capture long-range dependencies during the generation process as they compress all the information from previous time steps into a single…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Mude Hui , Rui-Jie Zhu , Songlin Yang , Yu Zhang , Zirui Wang , Yuyin Zhou , Jason Eshraghian , Cihang Xie

Text-to-image diffusion inference typically follows synchronized schedules, where the numerical integrator advances the latent state to the same timestep at which the denoiser is conditioned. We propose an asynchronous inference mechanism…

Computer Vision and Pattern Recognition · Computer Science 2025-12-23 Longhuan Xu , Feng Yin , Cunjian Chen

Decomposing knowledge into interchangeable pieces promises a generalization advantage when there are changes in distribution. A learning agent interacting with its environment is likely to be faced with situations requiring novel…

Machine Learning · Computer Science 2021-05-20 Kanika Madan , Nan Rosemary Ke , Anirudh Goyal , Bernhard Schölkopf , Yoshua Bengio

Existing large language models have to run K times to generate a sequence of K tokens. In this paper, we present RecycleGPT, a generative language model with fast decoding speed by recycling pre-generated model states without running the…

Computation and Language · Computer Science 2024-05-24 Yufan Jiang , Qiaozhi He , Xiaomin Zhuang , Zhihua Wu , Kunpeng Wang , Wenlai Zhao , Guangwen Yang

Diffusion-based image compression has demonstrated impressive perceptual performance. However, it suffers from two critical drawbacks: (1) excessive decoding latency due to multi-step sampling, and (2) poor fidelity resulting from…

Computer Vision and Pattern Recognition · Computer Science 2025-12-03 Zheng Chen , Mingde Zhou , Jinpei Guo , Jiale Yuan , Yifei Ji , Yulun Zhang

Flow-matching models deliver state-of-the-art fidelity in image and video generation, but the inherent sequential denoising process renders them slower. Existing acceleration methods like distillation, trajectory truncation, and consistency…

Computer Vision and Pattern Recognition · Computer Science 2026-02-12 Divya Jyoti Bajpai , Dhruv Bhardwaj , Soumya Roy , Tejas Duseja , Harsh Agarwal , Aashay Sandansing , Manjesh Kumar Hanawal

Stepwise inference protocols, such as scratchpads and chain-of-thought, help language models solve complex problems by decomposing them into a sequence of simpler subproblems. Despite the significant gain in performance achieved via these…

Machine Learning · Computer Science 2024-02-13 Mikail Khona , Maya Okawa , Jan Hula , Rahul Ramesh , Kento Nishi , Robert Dick , Ekdeep Singh Lubana , Hidenori Tanaka

Large language models (LLMs) equipped with chain-of-thought (CoT) achieve strong performance and offer a window into LLM behavior. However, recent evidence suggests that improvements in CoT capabilities often come with redundant reasoning…

Computation and Language · Computer Science 2026-02-03 Yanrui Du , Sendong Zhao , Yibo Gao , Danyang Zhao , Qika Lin , Ming Ma , Jiayun Li , Yi Jiang , Kai He , Qianyi Xu , Bing Qin , Mengling Feng

De-noising is a prominent step in the spectra post-processing procedure. Previous machine learning-based methods are fast but mostly based on supervised learning and require a training set that may be typically expensive in real…

Materials Science · Physics 2024-03-06 Dongchen Huang , Junde Liu , Tian Qian , Hongming Weng