11 citations · 12 across the 9 of their papers we have counts for
9 papers
HarnessEval-W: Agentifying the Evaluation of Visual Worlds
Weiliang Chen, Haowen Sun, Jun Gao +40
A benchmark should deliver more than a scalar score: what makes an evaluation trustworthy is the reasoning that justifies the score. This is especially critical for world models, w…
Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning
Hanyang Wang, Yimo Cai, Weiliang Chen +14
Physical understanding and reasoning depend on forming compact and generalizable representations of the world. While modern vision-language models can recognize and explain diverse…
Foresight Diffusion: Improving Sampling Consistency in Predictive Diffusion Models
Yu Zhang, Xingzhuo Guo, Haoran Xu +2
Diffusion and flow-based models have enabled significant progress in generation tasks across various modalities and have recently found applications in predictive learning. However…
Dynamical Diffusion: Learning Temporal Dynamics with Diffusion Models
Xingzhuo Guo, Yu Zhang, Baixu Chen +3
Diffusion models have emerged as powerful generative frameworks by progressively adding noise to data through a forward process and then reversing this process to generate realisti…
Diffusion Tuning: Transferring Diffusion Models via Chain of Forgetting
Jincheng Zhong, Xingzhuo Guo, Jiaxiang Dong +1
Diffusion models have significantly advanced the field of generative modeling. However, training a diffusion model is computationally expensive, creating a pressing need to adapt o…
CogDPM: Diffusion Probabilistic Models via Cognitive Predictive Coding
Kaiyuan Chen, Xingzhuo Guo, Yu Zhang +2
Predictive Coding (PC) is a theoretical framework in cognitive science suggesting that the human brain processes cognition through spatiotemporal prediction of the visual world. Ex…
On the Embedding Collapse when Scaling up Recommendation Models
Xingzhuo Guo, Junwei Pan, Ximei Wang +3
Recent advances in foundation models have led to a promising trend of developing large recommendation models to leverage vast amounts of available data. Still, mainstream models re…
Decoupled Training: Return of Frustratingly Easy Multi-Domain Learning
Ximei Wang, Junwei Pan, Xingzhuo Guo +2
Multi-domain learning (MDL) aims to train a model with minimal average risk across multiple overlapping but non-identical domains. To tackle the challenges of dataset bias and doma…
CLIPood: Generalizing CLIP to Out-of-Distributions
Yang Shu, Xingzhuo Guo, Jialong Wu +3
Out-of-distribution (OOD) generalization, where the model needs to handle distribution shifts from training, is a major challenge of machine learning. Contrastive language-image pr…