The paper introduces Training-Free Omni (TFO), a plug‑and‑play framework that transforms a frozen vision‑language model (VLM) into a speech‑centric omni model without modifying its architecture or requiring multimodal re‑alignment. TFO leverages Whisper to generate confidence‑filtered, timestamped transcripts and routes them through the VLM’s existing language interface, leaving the visual pathway untouched. Evaluations on 56 benchmarks across 21 languages show that TFO matches or surpasses native omni models on audio‑visual tasks, improves audio‑only performance, and preserves strong visual and reasoning capabilities.
By Ankan Deria, Hanoona Rasheed, Xilin He, Fahad Shahbaz Khan, Salman Khan
arXiv:2608. 04586v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have achieved significant success in speech-to-text translation (S2TT).
By Yexing Du, Kaiyuan Liu, Youcheng Pan, Bo Yang, Chengpeng Fu, Yu Wang, Ming Liu
arXiv:2608. 04586v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have achieved significant success in speech-to-text translation (S2TT).
By Yexing Du, Kaiyuan Liu, Youcheng Pan, Bo Yang, Chengpeng Fu, Yu Wang, Ming Liu
The paper introduces Modality Self-Play (MSP), a training framework that enables multimodal large language models to learn cross‑modal interactions without requiring paired non‑text data. MSP uses proxy‑mediated textual descriptions of unseen modalities as semantic bridges, allowing a model to generate and align these proxies with observed modalities. Experiments show that MSP achieves state‑of‑the‑art or competitive performance on several multimodal benchmarks and demonstrates effective zero‑shot modality composition through learned bridges and anchor‑supporting proxy descriptions.
By Robert Moseley, Md Kaykobad Reza, Ameya Patil, Edward Ayrapetian, Salman Asif
TokenSwap introduces a method to benchmark and reduce the modality gap in multimodal large language models (MLLMs) by interleaving semantically aligned images with text tokens. By transforming text-only benchmarks like MMLU into image‑interleaved versions (TokenSwap‑Bench), the authors reveal a pervasive performance drop—averaging 19.6%—across 42 MLLMs, with reasoning models showing smaller gaps. Training with TokenSwap mitigates this gap while maintaining strong text‑only and vision‑language performance.
By Andong Hua, Colton Bishop, Igor Mordatch, Arian Hosseini, Jindong Gu, Aleksandra Faust, Rebecca Roelofs, Yao Qin
EXAM$^2$ is a new benchmark for audio understanding that covers six languages and multiple modalities—speech, sound, music, mixed-audio, and visual images—providing 5,667 multiple-choice questions, 22,614 image instances, and 135,684 multilingual translations. It evaluates large audio language models (LALMs) and multimodal large language models (LLMs), revealing significant gaps in multilingual and cross‑modal performance. The authors also introduce Gemma3n-EXAM$^2$, a lightweight fusion model that improves multilingual results by up to 12.4% and multimodal results by 21.7% over a strong baseline.
By Jiawen Wang, Xiaoxue Gao, Zi Haur Pang, Nancy F. Chen
arXiv:2608.23758v3 Announce Type: replace-cross
Abstract: Recent large audio language models (LALMs) have achieved impressive progress in audio understanding. However, existing evaluations remain lar...
By Jiawen Wang, Xiaoxue Gao, Zi Haur Pang, Nancy F. Chen
The paper proposes Metric-based Loss Weighting to enhance visual grounding in multimodal machine translation. By increasing loss for tokens that benefit from image context—identified via the Point-wise Cross-mutual Information (PCXMI) metric and its Congruency-based variant—the method improves translation accuracy on the CoMMuTE dataset by over 7 percentage points. Experiments fine-tune three pretrained multimodal LLMs across three language directions, showing superior performance compared to standard fine-tuning while preserving overall translation quality.
By Pawe{\l} M\k{a}ka, Piotr Andruszkiewicz, Yusuf Can Semerci, Jan Scholtes, Gerasimos Spanakis
The paper investigates how to scale a Transformer-based vision‑language model trained from scratch on multimodal inputs under a fixed compute budget. It finds that minimal loss follows a predictable compute law while optimal model size and token count obey power‑law scaling, with language and multimodal objectives showing distinct allocation trends. The study also proposes a budget‑compensation rule that allows additional multimodal tokens to offset text‑efficiency penalties, and demonstrates that native multimodal pre‑training improves spatial reasoning and few‑shot learning.
By Haoyuan Wu, Aoqi Wu, Hai Wang, Jiajia Wu, Jinxiang Ou, Bei Yu
arXiv:2607. 10299v1 Announce Type: new Abstract: Recent advances in large-scale multimodal models have drivenremarkable progress in vision-language tasks; however, comprehensiveomni-modal understanding remains under-explored, largely due to thescarcity of datasets with rich, explicitly aligned auditory cues.
By Kaiying Yan, Luoyi Sun, Xiao Zhou, Weidi Xie
arXiv:2608. 09227v1 Announce Type: new Abstract: Omnimodal language models (OLMs) enable unified audio-visual understanding, but processing long joint token sequences makes inference computationally prohibitive.
By Puneet Mathur, Manan Suri, Dinesh Manocha
arXiv:2609.06188v1 Announce Type: new
Abstract: Multimodal sentiment analysis and emotion recognition in conversations demand effective modeling of heterogeneous interactions across textual, acoustic...
By Pengfei Shao, Jisheng Dang, Jiawen Fang, Ning Liu, Wencan Zhang, Bimei Wang, Jingwen Zhao, Jianhuang Lai, Qi Tian, Tat-Seng Chua