cs.MM · 2026-08-05 · No. 75
Multimedia, 2026-08-05.
2 new papers in cs.MM. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
2 entries-
01
Adaptive Modality Reliability Diagnosis and Restoration for Robust Multimodal Intent Recognition
Suraj Kumar, Mohnish Raj, Soumi Chattopadhayay, Chandranath Adak, Ayan Dutta
cs.MM · cs.AI · cs.CL
Multimodal intent recognition combines linguistic, acoustic, and visual evidence, but individual modalities may be noisy, missing, semantically conflicting, or disproportionately dominant. Existing methods typically infer modality importance implicitly and either reweight or suppress unreliable inputs, without determining whether a degraded modality can be repaired and subsequently trusted. We propose PRIME (Precision-weighted Reliability...
-
02
Balancing Efficiency and Efficacy: Training-Free Attention-Guided Switching Between Explicit and Latent Thoughts for MLLMs
Haoqian Kang, Liupeng Li, Kuofeng Gao, Jinpeng Wang, Zhenyu Lu, Bin Chen, Ke Chen, Yaowei Wang
cs.MM · cs.AI · cs.CL · cs.CV
Reasoning in Multimodal Large Language Models (MLLMs) requires both fine-grained visual perception and rigorous logical deduction. Explicit text-based Chain-of-Thought (CoT) is computationally expensive and prone to visual hallucinations, while existing latent reasoning methods typically require costly training. Furthermore, directly adapting training-free LLM reasoning mechanisms to the multimodal setting yields unstable performance. We...
This edition is part of The Daily Abstract — cs.MM archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.