9 papers
CastClaw: A Human-in-the-Loop Autonomous Agent for Interactive Time Series Forecasting
Xiaoyu Tao, Mingyue Cheng, Ze Guo +4
Practical time-series forecasting requires domain knowledge, constraints, plausibility checks, and human intervention. We present CastClaw, an interactive forecasting system center…
PoseAlign: Sculpting Pose-Consistent Meshes via Text-Guided Deformation
Shijin Wang, Zichong Chen, Yang Zhou +1
Mesh deformation, the process of altering the vertex positions of a 3D mesh while preserving its topological structure, is a cornerstone of computer graphics. Despite the recent em…
MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoning
Xiaoyu Tao, Mingyue Cheng, Ze Guo +4
Time series forecasting (TSF) plays a critical role in decision-making for many real-world applications. Recently, large language model (LLM)- based forecasters have made promising…
Latent Shadows: The Gaussian-Discrete Duality in Masked Diffusion
Guinan Chen, Xunpeng Huang, Ying Sun +3
Masked discrete diffusion is a dominant paradigm for high-quality language modeling where tokens are iteratively corrupted to a mask state, yet its inference efficiency is bottlene…
BLADE: A Behavior-Level Data Augmentation Framework with Dual Fusion Modeling for Multi-Behavior Sequential Recommendation
Yupeng Li, Mingyue Cheng, Yucong Luo +3
Multi-behavior sequential recommendation aims to capture users' dynamic interests by modeling diverse types of user interactions over time. Although several studies have explored t…
Disentangling the Drivers of LLM Social Conformity: An Uncertainty-Moderated Dual-Process Mechanism
Huixin Zhong, Yanan Liu, Qi Cao +4
As large language models (LLMs) integrate into collaborative teams, their social conformity -- the tendency to align with majority opinions -- has emerged as a key concern. In huma…
From Values to Tokens: An LLM-Driven Framework for Context-aware Time Series Forecasting via Symbolic Discretization
Xiaoyu Tao, Shilong Zhang, Mingyue Cheng +5
Time series forecasting plays a vital role in supporting decision-making across a wide range of critical applications, including energy, healthcare, and finance. Despite recent adv…
Confidence-Aware Self-Distillation for Multimodal Sentiment Analysis with Incomplete Modalities
Yanxi Luo, Shijin Wang, Zhongxing Xu +3
Multimodal sentiment analysis (MSA) aims to understand human sentiment through multimodal data. In real-world scenarios, practical factors often lead to uncertain modality missingn…
StyleBlend: Enhancing Style-Specific Content Creation in Text-to-Image Diffusion Models
Zichong Chen, Shijin Wang, Yang Zhou
Synthesizing visually impressive images that seamlessly align both text prompts and specific artistic styles remains a significant challenge in Text-to-Image (T2I) diffusion models…