Publication DirectSpeech2LLM: A Simple End-to-End Framework to Mitigate Prompt Overfitting in Speech-LLMs Hemant Yadav, Sunayana Sitaram, Roy Zimmermann, Rajiv Ratn Shah October 2026 arXiv | October 2026
Publication Cognitive Chain-of-Thought (CoCoT): Structured Multimodal Reasoning about Social Situations Eunkyu Park, Wesley Deng, Gunhee Kim, Motahhare Eslami, Maarten Sap The Third Annual Conference on Language Modeling | October 2026
Publication A Systematic Investigation of Bias in Large Language Models for Advertising Relevance Wei-Wei Wang, Ying Xu, JiaLu Gao, Youkow Homma, Jian Jiao October 2026 arXiv | October 2026
Publication Training Language Models To Be Coherent Decision-Makers K. Yamin, Xavier Fernandes, Paul Koch, Bryan Wilder, Eric Horvitz October 2026 arXiv | October 2026
Publication Activation Denoising: A Robustness View on Parallel vs Sequential LLM Quantization Yan Scholten, Rachel Lawrence, James Hensman, Stephan Gunnemann, Alicia Curth, Riccardo Grazzi October 2026 arXiv | October 2026
Publication EchoChat: Structured Cognitive Reasoning in Empathetic Spoken Dialogue Dingdong Wang, Shujie Liu, Yayue Deng, Yuxuan Hu, Yunrui Cai, Jincenzi Wu, Jianwei Yu, Jinyu Li, Helen M. Meng October 2026 arXiv | October 2026
Publication Prompt-Consistency Inference for Zero-Shot Flow-Matching Text-to-Speech Models Vasily Zadorozhnyy, Can Goksen, Kazuhito Koishida, Dung N. Tran October 2026 arXiv | October 2026
Publication FASTDIAR: Frame-level speaker encoder for Streaming Diarization Nikita Torgashov, Okan Kopuklu October 2026 arXiv | October 2026
Publication Pretext Reasoning: Scaling the Building Blocks of Interleaved Multimodal Reasoning Jiawei Gu, Linjie Li, Yiming Liu, Yunzhuo Hao, Zhichao Peng, Huichen Wang, Guanzheng Chen, Luxin Xu, Xinyu Zhang, Li Luo, Disen Lan, Zican Hu, Mingyang Song, David Valente, Alex Jinpeng Wang, Yafu Li, Ganqu Cui, Zhengyuan Yang, Michael Shieh, Yejin Choi, Ranjay Krishna, Yu Cheng NeurIPS 2026 | October 2026
Publication Teaching LLMs to Hear Who Spoke What: Metadata-Supervised Pretraining for Encoder-Free Speech-LLMs Mohan Shi, Ruchao Fan, Sunit Sivasankaran, Keqi Deng, Jinyu Li October 2026 arXiv | October 2026