arXiv:2606. 05121v1 Announce Type: cross Abstract: Audio is an inherently interactive modality, yet today's Large Audio Language Models (LALMs) are offline, and streaming audio models each handle only a single task such as streaming ASR or voice chatting.
By Zhifei Xie, Zihang Liu, Ze An, Xiaobin Hu, Yue Liao, Ziyang Ma, Dongchao Yang, Mingbao Lin, Deheng Ye, Shuicheng Yan, Chunyan Miao
arXiv:2608.05803v2 Announce Type: replace
Abstract: Recent advances in generative video modeling have enabled diverse generation, reference-based synthesis, extension, and editing, but existing appro...
By Vorch Team, Xiaoyu Chen, Yang Ding, Cong Han, Menglin Han, Yuxin Hong, Jiebo Hou, Zequn Jie, Xiang Li, Jing Liu, Qi Liu, Yulei Lu, Siyuan Luo, Lin Ma, Xin Ma, Yinlong Qian, Peng Shi, Fang Wan, Siqi Wang, Yaohui Wang, Yaole Wang, Yidi Wu, Siqian Yang, Mingyu Yin, Haoran Yu, Gang Yue, Lisai Zhang, Yuting Zhang
Recent advances in generative video modeling have enabled diverse generation, reference-based synthesis, extension, and editing, but existing approaches often rely on fragmented task-specific models. A general model must distinguish heterogeneous target, source, and reference signals to determine what to generate, preserve, or use as guidance, while reducing interference among tasks.
arXiv:2610.02181v1 Announce Type: new
Abstract: We present OmniSeek, an agentic framework that transforms an Omni Large Language Model (Omni-LLM) into an active, multi-turn reasoning agent with nativ...
By Haibo Wang, Jiteng Mu, Jialu Li, Jingru Yi, Yuanjun Xiong, Jianming Zhang, Lifu Huang, Mingze Xu
arXiv:2609.23407v2 Announce Type: replace-cross
Abstract: Humans can effortlessly localize the direction of a sound source and integrate it with visual cues for reasoning, yet this remains challengin...
By Ruixun Liu, Yuxuan Wang, Jiacheng Xie, Yuhuan You, Donghua Cai, Junming Lin, Xiong-Hui Chen, Zhifang Guo, Yunfei Chu, Qize Yang, Xize Cheng, Jin Xu, Yiwu Zhong
arXiv:2606. 12688v1 Announce Type: cross Abstract: We are entering a new era of composite model architectures that integrate diverse components such as vision encoders, language backbones, diffusion and flow heads, audio codecs, action generators, and world-model predictors.
By Atindra Jha, Naomi Sagan, Keisuke Kamahori, Irmak Sivgin, Rohan Sanda, Steven Gao, Mark Horowitz, Luke Zettlemoyer, Olivia Hsu, Jure Leskovec, Baris Kasikci, Stephanie Wang
arXiv:2608. 09435v1 Announce Type: new Abstract: Understanding dynamic sound sources requires jointly determining what produces a sound, where the source is located, and how it moves over time.
By Zhi Zeng, Cheng Zhang, Zesheng Yang, Rendong Pi, Jiaying Wu, Di Zhang, Zihan Ma, Guodong Li, Zhou Yang, Yu Xiang, Yifei Zheng, Minnan Luo
arXiv:2609.23407v1 Announce Type: cross
Abstract: Humans can effortlessly localize the direction of a sound source and integrate it with visual cues for reasoning, yet this remains challenging for em...
By Ruixun Liu, Yuxuan Wang, Jiacheng Xie, Yuhuan You, Donghua Cai, Junming Lin, Xiong-Hui Chen, Zhifang Guo, Yunfei Chu, Qize Yang, Xize Cheng, Jin Xu, Yiwu Zhong
The paper introduces PlanAudio, an end‑to‑end framework that generates unified audio—combining speech and sound—directly from free‑form text prompts without intermediate preprocessing. PlanAudio uses latent planning to predict a continuous audio layout before synthesizing acoustic tokens, enabling coherent temporal and semantic interactions in the output. The authors build a large training corpus and a Free‑Form Unified Audio Generation Benchmark (FUAG), demonstrating that PlanAudio outperforms both pipeline and unified baselines on speech‑and‑sound tasks while remaining competitive with specialist models on speech and sound alone.
By Yuyue Wang, Xihua Wang, Xin Cheng, Yijing Chen, Ruihua Song
Long audio-video reasoning is difficult for omnimodal LLMs because the decisive evidence is often sparse, cross-modal, and too expensive to preserve with uniformly high-fidelity inputs. We introduce OmniReasoner, a tool-use post-training framework for Thinking with Long Audio-Video: omni-modal LLMs learn, via supervised fine-tuning and reinforcement learning, to decide whether and where to call a zoom-in tool before answering.
The paper introduces the Neural Action Codec (NAC), a convolutional encoder‑decoder architecture that treats short robot action trajectories as multi‑channel 1D signals and compresses them using a multi‑scale residual vector quantization (RVQGAN) model. NAC replaces traditional discrete action tokenizers with a compact, ordered token space via offset codebooks, allowing standard autoregressive policies to operate over short, structured sequences while a Vocos‑style decoder reconstructs the actions. Experiments on LIBERO‑10, RoboMimic, and real‑world manipulation tasks show that NAC achieves higher reconstruction fidelity and better average success rates than existing binning, FAST, and VQ‑based tokenizers at comparable or improved compression rates.
By Ahad Jawaid, Yu Xiang
Understanding dynamic sound sources requires jointly determining what produces a sound, where the source is located, and how it moves over time. Yet existing audio-language models often represent clips as global acoustic events, while vision-language models lack the spatial audio cues needed to localize and track individual sources.