arXiv AI August 25, 2026 By Zihao Zhou, Bin Yang, Jinghui Qin, Kebing Jin

DiaRelay: Relaying Dialogue Context with a Constant-Size Memory for Emotion Recognition in Conversation

DiaRelay introduces a lightweight adapter that lets large language models maintain a constant‑size dialogue‑level memory for emotion recognition in conversation. It builds on LoRA by adding a Selective Relay Memory Transition that aggregates useful historical evidence into a bounded memory, and a Dual‑axis Relay Memory Read that uses this memory to modulate low‑rank feature transformations. Experiments show DiaRelay achieves state‑of‑the‑art weighted F1 and accuracy on MELD with only 7.1 M additional trainable parameters, while also performing competitively on IEMOCAP.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 9

Titans-as-a-Layer: Test-Time Memory for Conversational Speech Emotion Recognition

arXiv:2606. 08573v1 Announce Type: new Abstract: Speech emotion recognition (SER) is commonly formulated as utterance-level classification, although conversational emotion depends on a speaker's usual vocal range and the emotional context established by previous utterances.

By Daniel Chen, Qicong Hu, Yang Xiao, Ting Dang, Hong Jia

llms

arXiv Computation and Language

Oct 8

FTA-Mem: Fact-Time-Affect Anchored Memory for Low-Density Long-Term Dialogue

arXiv:2608.16303v2 Announce Type: replace Abstract: Long-term emotional-support agents require memory mechanisms for personalized understanding across sessions. However, emotional-support dialogue is...

By Chang Liu, Junyi Zhao, Shuyi Zhang, Changsheng Ma, Yongfeng Tao, Minqiang Yang, Bin Hu

agents computer-vision nlp benchmarks

arXiv Computation and Language

Sep 3

TalkFa: A Unified Benchmark for Farsi Dialogue Generation and Understanding

TalkFa introduces a unified benchmark for Farsi dialogue generation and understanding, comprising three datasets: WIKI‑FADIAL (4.2K Wikipedia‑grounded dialogues), DAILYDIALOG‑FA (6.6K dialogues with dialogue‑act and emotion annotations), and PLAYDIAL‑FA (2.1K theatrical dialogues with sentiment labels). All dialogues are curated through multi‑stage review by native speakers, ensuring high quality. Experiments show that LoRA fine‑tuning improves generation performance with less data, while specific models excel on classification tasks, and human evaluation confirms the benchmark’s reliability.

By Neda Jamshidi, Kamyar Zeinalipour, Fahimeh Akbari, Monica Bianchini, Marco Maggini, Marco Gori

llms fine-tuning benchmarks

arXiv Machine Learning

Jun 11

Context-Driven Incremental Compression for Multi-Turn Dialogue Generation

arXiv:2606. 12411v1 Announce Type: cross Abstract: Modern conversational agents condition on an ever-growing dialogue history at each turn, incurring redundant attention and encoding costs that grow with conversation length.

By Yeongseo Jung, Jaehyeok Kim, Eunseo Jung, Jiachuan Wang, Yongqi Zhang, Ka Chun Cheung, Simon See, Lei Chen

agents nlp efficiency benchmarks

arXiv AI

Jun 11

MA-DLE: Speech-based Automatic Depression Level Estimation via Memory Augmentation

arXiv:2606. 11197v1 Announce Type: cross Abstract: Speech-based automatic estimation of depression levels is essential for enabling early detection and timely intervention, particularly in resource-constrained mental health settings.

By Xuzhi Wang, Xinran Wu, Ziping Zhao, Jianhua Tao, Bj\"orn W. Schuller

benchmarks

arXiv AI

Sep 10

RAFM-SER++: A Lightweight Multimodal Emotion Recognition Framework for Real-Time Behavioral Monitoring in Surveillance Systems

The paper introduces RAFM-SER++, a lightweight multimodal speech emotion recognition framework designed for real‑time surveillance systems. It replaces heavy bidirectional cross‑modal transformers with an asymmetric Residual Attention Fusion Mechanism that injects affective speech cues into text representations via a one‑directional residual attention pathway. Experiments on IEMOCAP and ESD show RAFM‑SER++ outperforms the HuBERT‑Base baseline and MemoCMT, reducing trainable parameters by over 60%, achieving 79.60 it/s inference speed, and reaching BACC scores of 81.10% on IEMOCAP and 95.39% on ESD.

By Ngo Truong Dinh, Tung-Lam Bui, Chi-Trung Duong, Vien Nguyen Thi, Viet-Anh Nguyen, Phuc-Lu Le

llms multimodal benchmarks safety