works on

From the 2 of 12 linked papers with an AI index.

collaborators

12 papers

cs.CL2026

Target-Aware Calibration Data Selection for Preserving Uncertainty in Quantized Language Models

Zhen Yang, Sizai Hou, Kaiwen Zheng +4

Quantization is widely used to deploy large language models, but its effect on uncertainty behavior, such as confidence, margins, and abstention, is rarely treated as a primary obj…

cs.IR2026

RecRec: Latent Interests Recursive Reasoning for Sequential Recommendation

Wenhao Deng, Junchen Fu, Hanwen Du +6

The paper introduces RecRec, a framework that separates reasoning from prediction in sequential recommendation by compressing user histories into multiple latent interests and recu…

cs.AI2026

Do We Really Need Multimodal Emotion Language Models Larger Than 1B Parameters?

Kaiwen Zheng, Junchen Fu, Wenhao Deng +3

The paper introduces Light-MER, a sub‑billion‑parameter multimodal emotion recognition model that uses knowledge distillation, an optimal transport loss, and a multi‑reward optimiz…

cs.IR2026

Stream-aware Side Adaptation for Large Pre-trained Multimodal Embedding Models in Sequential Recommendation

Junchen Fu, Kaiwen Zheng, Ioannis Arapakis +4

Recently, large pretrained multimodal embedding models such as Qwen3-VL Embedding have shown strong promise for sequential recommendation, as they provide reusable semantic item re…

cs.CL2026

Training-Free Test-Time Contrastive Learning for Large Language Models

Kaiwen Zheng, Kai Zhou, Jinwu Hu +3

Large language models (LLMs) demonstrate strong reasoning capabilities, but their performance often degrades under distribution shift. Existing test-time adaptation (TTA) methods r…

cs.MM2026

Benchmarking Multimodal Large Language Models for Missing Modality Completion in Product Catalogues

Junchen Fu, Wenhao Deng, Kaiwen Zheng +5

Missing-modality information on e-commerce platforms, such as absent product images or textual descriptions, often arises from annotation errors or incomplete metadata, impairing b…