English
Related papers

Related papers: O-MARC: Omni Memory-Augmented Compression Distilla…

200 papers

The use of omni-LLMs (large language models that accept any modality as input), particularly for multimodal cognitive state tasks involving speech, is understudied. We present OmniVox, the first systematic evaluation of four omni-LLMs on…

Computation and Language · Computer Science 2025-03-31 John Murzaku , Owen Rambow

Automated Audio Captioning (AAC) generates captions for audio clips but faces challenges due to limited datasets compared to image captioning. To overcome this, we propose the zero-shot AAC system that leverages pre-trained models,…

Computation and Language · Computer Science 2025-09-17 Vijay Govindarajan , Pratik Patel , Sahil Tripathi , Md Azizul Hoque , Gautam Siddharth Kashyap

Knowledge distillation offers a promising path to transfer reasoning capabilities from large teacher models to efficient student models; however, existing token-level on-policy distillation methods require token-level alignment between the…

Computation and Language · Computer Science 2026-01-30 Jing Xiong , Hui Shen , Shansan Gong , Yuxin Cheng , Jianghan Shen , Chaofan Tao , Haochen Tan , Haoli Bai , Lifeng Shang , Ngai Wong

Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external knowledge but incurs significant inference costs due to lengthy retrieved contexts. While context compression mitigates this issue, existing methods…

Computation and Language · Computer Science 2025-09-25 Shuyu Guo , Shuo Zhang , Zhaochun Ren

The rapid advancement of multi-modal language models (MLLMs) like GPT-4o has propelled the development of Omni language models, designed to process and proactively respond to continuous streams of multi-modal data. Despite their potential,…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Yuxuan Wang , Yueqian Wang , Bo Chen , Tong Wu , Dongyan Zhao , Zilong Zheng

Omni-modal large language models (om-LLMs) achieve unified audio-visual understanding by encoding video and audio into temporally aligned token sequences interleaved at the window level. However, processing these dense non-textual tokens…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Zijie Xin , Jie Yang , Ruixiang Zhao , Tianyi Wang , Fengyun Rao , Jing Lyu , Xirong Li

The integration of information across multiple modalities and across time is a promising way to enhance the emotion recognition performance of affective systems. Much previous work has focused on instantaneous emotion recognition. The 2018…

Image and Video Processing · Electrical Eng. & Systems 2018-05-07 Didan Deng , Yuqian Zhou , Jimin Pi , Bertram E. Shi

Semantic occupancy prediction enables dense 3D geometric and semantic understanding for autonomous driving. However, existing camera-based approaches implicitly assume complete surround-view observations, an assumption that rarely holds in…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Kaixin Lin , Kunyu Peng , Di Wen , Yufan Chen , Ruiping Liu , Kailun Yang

Research into the prediction and analysis of perceived audio quality is hampered by the scarcity of openly available datasets of audio signals accompanied by corresponding subjective quality scores. To address this problem, we present the…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-02 Matteo Torcoli , Chih-Wei Wu , Sascha Dick , Phillip A. Williams , Mhd Modar Halimeh , William Wolcott , Emanuel A. P. Habets

The practical deployment of medical vision-language models (Med-VLMs) necessitates seamless integration of textual data with diverse visual modalities, including 2D/3D images and videos, yet existing models typically employ separate…

Computation and Language · Computer Science 2025-04-22 Songtao Jiang , Yuan Wang , Sibo Song , Yan Zhang , Zijie Meng , Bohan Lei , Jian Wu , Jimeng Sun , Zuozhu Liu

Multi-agent debate can improve reasoning quality and reduce hallucinations, but it incurs rapidly growing context as debate rounds and agent count increase. Retaining full textual histories leads to token usage that can exceed context…

Artificial Intelligence · Computer Science 2026-02-03 Jing Wu , Yue Sun , Tianpei Xie , Suiyao Chen , Jingyuan Bao , Yaopengxiao Xu , Gaoyuan Du , Inseok Heo , Alexander Gutfraind , Xin Wang

Open-retrieval conversational machine reading comprehension (OCMRC) simulates real-life conversational interaction scenes. Machines are required to make a decision of "Yes/No/Inquire" or generate a follow-up question when the decision is…

Computation and Language · Computer Science 2022-12-20 Xiao Zhang , Heyan Huang , Zewen Chi , Xian-Ling Mao

Prompt compression is a promising approach to speeding up language model inference without altering the generative model. Prior works compress prompts into smaller sequences of learned tokens using an encoder that is trained as a LowRank…

Computation and Language · Computer Science 2025-01-14 Edouardo Honig , Andrew Lizarraga , Zijun Frank Zhang , Ying Nian Wu

Spoken dialogue is a primary source of information in videos; therefore, accurately identifying who spoke what and when is essential for deep video understanding. We introduce D-ORCA, a \textbf{d}ialogue-centric \textbf{o}mni-modal large…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Changli Tang , Tianyi Wang , Fengyun Rao , Jing Lyu , Chao Zhang

Open-vocabulary semantic segmentation (OVSS) aims to segment and recognize objects universally. Trained on extensive high-quality segmentation data, the segment anything model (SAM) has demonstrated remarkable universal segmentation…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Lin Chen , Yingjian Zhu , Qi Yang , Xin Niu , Kun Ding , Shiming Xiang

Long-form multimodal video understanding requires integrating vision, speech, and ambient audio with coherent long-range reasoning. Existing benchmarks emphasize either temporal length or multimodal richness, but rarely both and while some…

Learning common subspace is prevalent way in cross-modal retrieval to solve the problem of data from different modalities having inconsistent distributions and representations that cannot be directly compared. Previous cross-modal retrieval…

Multimedia · Computer Science 2021-10-27 Donghuo Zeng , Jianming Wu , Gen Hattori , Yi Yu , Rong Xu

Current multimodal large language models (MLLMs) have demonstrated remarkable capabilities in short-form video understanding, yet translating long-form cinematic videos into detailed, temporally grounded scripts remains a significant…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Junfu Pu , Yuxin Chen , Teng Wang , Ying Shan

Multi-hop audio-visual reasoning remains challenging for Omni-LLMs, as relevant evidence is often sparse, temporally dispersed, and distributed across both audio and visual streams. Existing benchmarks provide limited investigation of this…

Artificial Intelligence · Computer Science 2026-05-28 Ke Xu , Yuhao Wang , Ziyang Cheng , Hongcheng Liu , Yanfeng Wang , Yu Wang

Spatio-Temporal Video Grounding (STVG) aims to localize target objects in videos based on natural language descriptions. Despite recent advances in Multimodal Large Language Models, a significant gap remains between current models and…

Computer Vision and Pattern Recognition · Computer Science 2025-11-24 Hong Gao , Jingyu Wu , Xiangkai Xu , Kangni Xie , Yunchen Zhang , Bin Zhong , Xurui Gao , Min-Ling Zhang