English
Related papers

Related papers: LARV: Data-Free Layer-wise Adaptive Rescaling Vene…

200 papers

Large Vision-Language Models (LVLMs) have advanced rapidly by aligning visual patches with the text embedding space, but a fixed visual-token budget forces images to be resized to a uniform pretraining resolution, often erasing fine-grained…

Computer Vision and Pattern Recognition · Computer Science 2026-02-05 Zipeng Zhu , Zhanghao Hu , Qinglin Zhu , Yuxi Hong , Yijun Liu , Jingyong Su , Yulan He , Lin Gui

Model merging constructs versatile models by integrating task-specific models without requiring labeled data or expensive joint retraining. Although recent methods improve adaptability to heterogeneous tasks by generating customized merged…

Machine Learning · Computer Science 2026-02-09 Haiyun Qiu , Xingyu Wu , Liang Feng , Kay Chen Tan

Recent large reasoning models (LRMs) have made substantial progress in complex reasoning tasks, yet they often generate lengthy reasoning paths for every query, incurring unnecessary computation and latency. Existing speed-up approaches…

Computation and Language · Computer Science 2026-01-08 Zhaofeng Zhong , Wei Yuan , Tong Chen , Xiangyu Zhao , Quoc Viet Hung Nguyen , Hongzhi Yin

Model merging seeks to integrate task-specific expert models into a unified architecture while preserving multi-task generalization capabilities, yet parameter interference between constituent models frequently induces performance…

Machine Learning · Computer Science 2025-06-12 Runxi Cheng , Feng Xiong , Yongxian Wei , Wanyun Zhu , Chun Yuan

Model merging has emerged as a practical approach to combine capabilities of specialized large language models (LLMs) without additional training. In the Long-to-Short (L2S) scenario, merging a base model with a long-chain-of-thought…

Machine Learning · Computer Science 2026-03-24 Tian Xia

Visual Autoregressive (VAR) modeling inefficiently applies a fixed computational depth to each position when generating high-resolution images. While existing methods accelerate inference by pruning tokens using frequency maps, their binary…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Chunliang Li , Tianze Cao , Sanyuan Zhao

Parameter efficient fine tuning methods like LoRA have enabled task specific adaptation of large language models, but efficiently composing multiple specialized adapters for unseen tasks remains challenging. We present a novel framework for…

Computation and Language · Computer Science 2026-02-26 Riya Adsul , Balachandra Devarangadi Sunil , Isha Nalawade , Sudharshan Govindan

Despite the impressive advancements of Large Vision-Language Models (LVLMs), existing approaches suffer from a fundamental bottleneck: inefficient visual-language integration. Current methods either disrupt the model's inherent structure or…

Computer Vision and Pattern Recognition · Computer Science 2025-06-23 Tongtian Yue , Longteng Guo , Yepeng Tang , Zijia Zhao , Xinxin Zhu , Hua Huang , Jing Liu

Recent feed-forward reconstruction models like VGGT and $\pi^3$ achieve impressive reconstruction quality but cannot process streaming videos due to quadratic memory complexity, limiting their practical deployment. While existing streaming…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Tianye Ding , Yiming Xie , Yiqing Liang , Moitreya Chatterjee , Pedro Miraldo , Huaizu Jiang

Integrating Automatic Speech Recognition (ASR) into Speech Emotion Recognition (SER) enhances modeling by providing linguistic context. However, conventional feature fusion faces performance bottlenecks, and multi-task learning often…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-27 Chia-Yu Lee , Huang-Cheng Chou , Tzu-Quan Lin , Yuanchao Li , Ya-Tse Wu , Shrikanth Narayanan , Chi-Chun Lee

Large language models (LLMs) have not yet effectively leveraged the vast amounts of edge-device data, and federated learning (FL) offers a promising paradigm to collaboratively fine-tune LLMs without transferring private edge data to the…

Machine Learning · Computer Science 2026-02-02 Arian Raje , Baris Askin , Divyansh Jhunjhunwala , Gauri Joshi

Reinforcement Learning with Verifiable Rewards (RLVR) plays a key role in stimulating the explicit reasoning capability of Large Language Models (LLMs). We can achieve expert-level performance in some specific domains via RLVR, such as…

Artificial Intelligence · Computer Science 2026-03-12 Haoqing Wang , Xiang Long , Ziheng Li , Yilong Xu , Tingguang Li , Yehui Tang

Discrete Diffusion Language Models have emerged as a compelling paradigm for unified multimodal generation, yet their deployment is hindered by high inference latency arising from iterative decoding. Existing acceleration strategies often…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Chenglin Wang , Yucheng Zhou , Shawn Chen , Tao Wang , Kai Zhang

Model merging provides a compelling paradigm for integrating specialized expertise into a unified multi-task model, a goal that aligns naturally with the sequential knowledge acquisition in continual learning (CL). However, the requirement…

Machine Learning · Computer Science 2026-05-12 Xi Wang , Cheng Deng

Large reasoning models (LRMs) excel at a long chain of reasoning but often fail to faithfully follow instructions regarding output format, constraints, or specific requirements. We investigate whether this gap can be closed by integrating…

Machine Learning · Computer Science 2026-02-27 Zhehao Huang , Yuhang Liu , Baijiong Lin , Yixin Lou , Zhengbao He , Hanling Tian , Tao Li , Xiaolin Huang

Large-scale transformers are central to modern semantic communication, yet their high computational and communication costs hinder deployment on resource-constrained edge devices. This paper introduces a training-free framework for adaptive…

Machine Learning · Computer Science 2025-09-15 Omar Erak , Omar Alhussein , Hatem Abou-Zeid , Mehdi Bennis , Sami Muhaidat

Model merging enables powerful capabilities in neural networks without requiring additional training. In this paper, we introduce a novel perspective on model merging by leveraging the fundamental mechanisms of neural network…

Machine Learning · Computer Science 2025-09-19 Haiquan Qiu , You Wu , Dong Li , Jianmin Guo , Quanming Yao

Learning rate configuration is a fundamental aspect of modern deep learning. The prevailing practice of applying a uniform learning rate across all layers overlooks the structural heterogeneity of Transformers, potentially limiting their…

Machine Learning · Computer Science 2026-05-28 Di He , Songjun Tu , Keyu Wang , Lu Yin , Shiwei Liu

Self-supervised learning (SSL) speech representation models, trained on large speech corpora, have demonstrated effectiveness in extracting hierarchical speech embeddings through multiple transformer layers. However, the behavior of these…

Computation and Language · Computer Science 2024-06-18 Zihan Pan , Tianchi Liu , Hardik B. Sailor , Qiongqiong Wang

Model merging-based multitask learning (MTL) offers a promising approach for performing MTL by merging multiple expert models without requiring access to raw training data. However, in this paper, we examine the merged model's…

Machine Learning · Computer Science 2024-10-21 Enneng Yang , Li Shen , Zhenyi Wang , Guibing Guo , Xingwei Wang , Xiaocun Cao , Jie Zhang , Dacheng Tao