activity
20232026
most citedDo LLMs "Feel"? Emotion Circuits Discovery and Control

2 citations · 3 across the 24 of their papers we have counts for

collaborators

37 papers

cs.CL2026

LITERARYBIGFIVE: Author-Personalized Text Generation in a Unified Interpretable Space

Jinghui Zhang, Lang Gao, Ao Li +5

Personalized text generation for authors and literary writing is essential for applications such as adaptive writing assistants, creative support tools, and computational literary…

cs.CL2026

Measure, Don't Optimize: Forecasting Recovery in LLM Unlearning

Zirui Song, Huaxing Liu, Xiang Wang +8

Prior white-box studies show that large language models can retain latent traces of target knowledge after unlearning, even when the knowledge is no longer expressed in their outpu…

cs.AI2026

OmniFood-Bench: Evaluating VLMs for Nutrient Reasoning and Personalized Health Advice

Qian Jiang, Zhecheng Shi, Jingpu Yang +2

The rapid integration of Large Vision-Language Models (VLMs) into critical infrastructure promises to revolutionize personalized healthcare and dietary management. However, in the…

cs.LG2026

Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias

Zixiang Xu, Sixian Li, Huaxing Liu +4

Existing studies of LLM-as-judge scoring bias work predominantly at the input-output level: they perturb inputs, measure score deltas, and propose prompt-level mitigations. We argu…

cs.LG2026

Parametric Memory Decoding for Zero-Shot Routing in LoRA-Based External Parametric Memory

Fengxian Ji, Zhuohan Xie, Jingpu Yang +3

With the rise of parametric memory, LoRA-based External Parametric Memory (EPM) has emerged as a modular solution, but existing routing methods often introduce additional training,…

cs.AI2026

Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments

Xianhui Meng, Zirui Song, Yuchen Zhang +10

Large Language Models (LLMs) have demonstrated remarkable capabilities in 3D indoor synthesis for Manhattan environments. However, existing methods often fail to capture plausible…