collaborators

8 papers

cs.LG2026

TimeOmni-VL: Unified Models for Time Series Understanding and Generation

Tong Guan, Sheng Pan, Johan Barthelemy +5

Recent time series modeling faces a sharp divide between numerical generation and semantic understanding, with research showing that generation models often rely on superficial pat…

cs.CV2026

SwitchCraft: Training-Free Multi-Event Video Generation with Attention Controls

Qianxun Xu, Chenxi Song, Yujun Cai +1

Recent advances in text-to-video diffusion models have enabled high-fidelity and temporally coherent videos synthesis. However, current models are predominantly optimized for singl…

cs.AI2026

VistaWise: Building Cost-Effective Agent with Cross-Modal Knowledge Graph for Minecraft

Honghao Fu, Junlong Ren, Qi Chai +3

Large language models (LLMs) have shown significant promise in embodied decision-making tasks within virtual open-world environments. Nonetheless, their performance is hindered by…

cs.CV2026

CRAFT-LoRA: Content-Style Personalization via Rank-Constrained Adaptation and Training-Free Fusion

Yu Li, Yujun Cai, Chi Zhang

Personalized image generation requires effectively balancing content fidelity with stylistic consistency when synthesizing images based on text and reference examples. Low-Rank Ada…

cs.AI2026

PromptCD: Test-Time Behavior Enhancement via Polarity-Prompt Contrastive Decoding

Baolong Bi, Yuyao Ge, Shenghua Liu +9

Reliable AI systems require large language models (LLMs) to exhibit behaviors aligned with human preferences and values. However, most existing alignment approaches operate at trai…

cs.CV2025

SegDebias: Test-Time Bias Mitigation for ViT-Based CLIP via Segmentation

Fangyu Wu, Yujun Cai

Vision language models such as CLIP have shown remarkable performance in zero shot classification, but remain susceptible to spurious correlations, where irrelevant visual features…