English
Related papers

Related papers: KaVa: Latent Reasoning via Compressed KV-Cache Dis…

200 papers

Large Language Models (LLMs) rely heavily on Key-Value (KV) caching to minimize inference latency. However, standard KV caches are context-dependent: reusing a cached document in a new context requires recomputing KV states to account for…

Machine Learning · Computer Science 2026-04-20 Chuangtao Chen , Grace Li Zhang , Xunzhao Yin , Cheng Zhuo , Bing Li , Ulf Schlichtmann

We propose a resource-efficient framework for compressing large language models through knowledge distillation, combined with guided chain-of-thought reinforcement learning. Using Qwen 3B as the teacher and Qwen 0.5B as the student, we…

Computation and Language · Computer Science 2026-03-17 Alejandro Paredes La Torre , Barbara Flores , Diego Rodriguez

Knowledge-based visual question answering (KB-VQA) is a challenging task, which requires the model to leverage external knowledge for comprehending and answering questions grounded in visual content. Recent studies retrieve the knowledge…

Computer Vision and Pattern Recognition · Computer Science 2024-03-18 Dongze Hao , Jian Jia , Longteng Guo , Qunbo Wang , Te Yang , Yan Li , Yanhua Cheng , Bo Wang , Quan Chen , Han Li , Jing Liu

Long-form video question answering (VQA) overwhelms current vision-language models (VLMs) because attention and key-value (KV) caches grow with runtime, forcing either expensive inference or near-sighted sliding windows. We introduce…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Shrenik Patel , Daivik Patel

Transferring the reasoning capability from stronger large language models (LLMs) to smaller ones has been quite appealing, as smaller LLMs are more flexible to deploy with less expense. Among the existing solutions, knowledge distillation…

Computation and Language · Computer Science 2024-11-26 Yijun Tian , Yikun Han , Xiusi Chen , Wei Wang , Nitesh V. Chawla

Large language models (LLMs) excel at processing long sequences, boosting demand for key-value (KV) caching. While recent efforts to evict KV cache have alleviated the inference burden, they often fail to allocate resources rationally…

Computation and Language · Computer Science 2025-12-25 Ziran Qin , Yuchen Cao , Mingbao Lin , Wen Hu , Shixuan Fan , Ke Cheng , Weiyao Lin , Jianguo Li

Vision-Language-Action (VLA) models offer a unified framework for robotic perception and control, but their ability to scale to real-world, long-horizon tasks is limited by the high computational cost of attention and the large memory…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Wanshun Xu , Long Zhuang , Lianlei Shan

Multimodal large language models (MLLMs) have demonstrated great performance on visual question answering (VQA). When it comes to knowledge-based Visual Question Answering (KB-VQA), MLLMs may lack the specialized domain knowledge needed to…

Computer Vision and Pattern Recognition · Computer Science 2025-02-04 Weixi Weng , Jieming Zhu , Xiaojun Meng , Hao Zhang , Rui Zhang , Chun Yuan

Large Language Models (LLMs) have demonstrated outstanding performance across a range of NLP tasks, however, their computational demands hinder their deployment in real-world, resource-constrained environments. This work investigates the…

Computation and Language · Computer Science 2025-07-11 Joyeeta Datta , Niclas Doll , Qusai Ramadan , Zeyd Boukhers

The deployment and application of Large Language Models (LLMs) is hindered by their memory inefficiency, computational demands, and the high costs of API inferences. Traditional distillation methods, which transfer the capabilities of LLMs…

Computation and Language · Computer Science 2024-11-21 Yifei Zhang , Bo Pan , Chen Ling , Yuntong Hu , Liang Zhao

Multimodal Large Language Models (MLLMs) have achieved remarkable performance by integrating powerful language backbones with large-scale visual encoders. Among these, latent Chain-of-Thought (CoT) methods enable implicit reasoning in…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Yang Zhang , Danyang Li , Yuxuan Li , Xin Zhang , Tianyu Xie , Mingming Cheng , Xiang Li

Steering large language models (LLMs) is usually done by either instruction prompting or activation steering. Prompting often gives strong control, but caches guidance tokens at every layer and can clutter long interactions; activation…

Machine Learning · Computer Science 2026-05-12 Andy Zeyi Liu , Michael Zhang , Ilana Greenberg , Adam Alnasser , Lucas Baker , John Sous

Key-Value (KV) Caching has become an essential technique for accelerating the inference speed and throughput of generative Large Language Models~(LLMs). However, the memory footprint of the KV cache poses a critical bottleneck in LLM…

Machine Learning · Computer Science 2024-02-29 June Yong Yang , Byeongwook Kim , Jeongin Bae , Beomseok Kwon , Gunho Park , Eunho Yang , Se Jung Kwon , Dongsoo Lee

Transformer-based large language models (LLMs) demonstrate impressive potential in various practical applications. However, long context inference poses a significant challenge due to the enormous memory requirements of the key-value (KV)…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-03 Bo Jiang , Taolue Yang , Youyuan Liu , Chengming Zhang , Xubin He , Sian Jin

We study how to extend chain-of-thought (CoT) beyond language to better handle multimodal reasoning. While CoT helps LLMs and VLMs articulate intermediate steps, its text-only form often fails on vision-intensive problems where key…

Artificial Intelligence · Computer Science 2026-02-03 Yifei Shao , Kun Zhou , Ziming Xu , Mohammad Atif Quamar , Shibo Hao , Zhen Wang , Zhiting Hu , Biwei Huang

Pre-trained language-vision models have shown remarkable performance on the visual question answering (VQA) task. However, most pre-trained models are trained by only considering monolingual learning, especially the resource-rich language…

Computation and Language · Computer Science 2021-09-13 Humair Raj Khan , Deepak Gupta , Asif Ekbal

Large Language Models (LLMs) demonstrate exceptional reasoning capabilities, often achieving state-of-the-art performance in various tasks. However, their substantial computational and memory demands, due to billions of parameters, hinder…

Computation and Language · Computer Science 2024-11-25 Xunyu Zhu , Jian Li , Can Ma , Weiping Wang

Large Language Models (LLMs) have shown outstanding performance across wide range of downstream tasks. This competency is attributed to their substantial parameter size and pre-training on extensive corpus. Moreover, LLMs have exhibited…

Computation and Language · Computer Science 2023-08-10 Yuhan Ma , Haiqi Jiang , Chenyou Fan

Listwise reranking utilizing Large Language Models (LLMs) has achieved state-of-the-art retrieval effectiveness. Recently, reasoning-enhanced models have further pushed these boundaries by employing Chain-of-Thought (CoT) to perform deep…

Information Retrieval · Computer Science 2026-05-15 Danyang Liu , Kan Li

Long-context inference in Large Language Models (LLMs) is bottlenecked by the linear growth of Key-Value (KV) cache memory. Existing KV cache compression paradigms are fundamentally limited by heuristics: heuristic budgeting relies on…

Machine Learning · Computer Science 2026-05-11 Enshuai Zhou , Yifan Hao , Chao Wang , Rui Zhang , Di Huang , Jiaming Guo , Xing Hu , Zidong Du , Qi Guo , Yunji Chen