12 papers
LLaDA2.1: Speeding Up Text Diffusion via Token Editing
Tiwei Bie, Maosong Cao, Xiang Cao +47
While LLaDA2.0 showcased the scaling potential of 100B-level block-diffusion models and their inherent parallelization, the delicate equilibrium between decoding speed and generati…
Towards Compressive and Scalable Recurrent Memory
Yunchong Song, Jushi Kai, Liming Lu +2
Transformers face a quadratic bottleneck in attention when scaling to long contexts. Recent approaches introduce recurrent memory to extend context beyond the current window, yet t…
KnowledgeSmith: Uncovering Knowledge Updating in LLMs with Model Editing and Unlearning
Yinyi Luo, Zhexian Zhou, Hao Chen +4
Knowledge editing and machine unlearning are two popular approaches for large language models (LLMs) to stay up-to-date. However, the knowledge updating mechanism of LLMs remains l…
Image Tokenizer Needs Post-Training
Kai Qiu, Xiang Li, Hao Chen +7
Recent image generative models typically capture the image distribution in a pre-constructed latent space, relying on a frozen image tokenizer. However, there exists a significant…
Robust Latent Matters: Boosting Image Generation with Sampling Error Synthesis
Kai Qiu, Xiang Li, Jason Kuen +7
Recent image generation schemes typically capture image distribution in a pre-constructed latent space relying on a frozen image tokenizer. Though the performance of tokenizer play…
Three-dimensional attention Transformer for state evaluation in real-time strategy games
Yanqing Ye, Weilong Yang, Kai Qiu +1
Situation assessment in Real-Time Strategy (RTS) games is crucial for understanding decision-making in complex adversarial environments. However, existing methods remain limited in…
XQ-GAN: An Open-source Image Tokenization Framework for Autoregressive Generation
Xiang Li, Kai Qiu, Hao Chen +5
Image tokenizers play a critical role in shaping the performance of subsequent generative models. Since the introduction of VQ-GAN, discrete image tokenization has undergone remark…
ImageFolder: Autoregressive Image Generation with Folded Tokens
Xiang Li, Kai Qiu, Hao Chen +4
Image tokenizers are crucial for visual generative models, e.g., diffusion models (DMs) and autoregressive (AR) models, as they construct the latent representation for modeling. In…
Efficient Autoregressive Audio Modeling via Next-Scale Prediction
Kai Qiu, Xiang Li, Hao Chen +5
Audio generation has achieved remarkable progress with the advance of sophisticated generative models, such as diffusion models (DMs) and autoregressive (AR) models. However, due t…
ControlVAR: Exploring Controllable Visual Autoregressive Modeling
Xiang Li, Kai Qiu, Hao Chen +4
Conditional visual generation has witnessed remarkable progress with the advent of diffusion models (DMs), especially in tasks like control-to-image generation. However, challenges…
-Bench: Benchmarking the Robustness of Referring Perception Models under Perturbations
Xiang Li, Kai Qiu, Jinglu Wang +6
Referring perception, which aims at grounding visual objects with multimodal referring guidance, is essential for bridging the gap between humans, who provide instructions, and the…
Exploring Transferability for Randomized Smoothing
Kai Qiu, Huishuai Zhang, Zhirong Wu +1
Training foundation models on extensive datasets and then finetuning them on specific tasks has emerged as the mainstream approach in artificial intelligence. However, the model ro…