25 citations · 62 across the 17 of their papers we have counts for
19 papers
What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling
Renping Zhou, Zanlin Ni, Zihao Fan +8
World action models (WAMs) predict the future alongside actions during training. Due to the heavy computation cost of video denoising, whether the future must still be generated du…
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
DeepSeek-AI, :, Anyi Xu +585
The widespread adoption of long-horizon agents has made model workloads increasingly input-heavy. Although prior work has substantially reduced the cost of long-context computation…
InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation
Yang Yue, Fangyun Wei, Tianyu He +10
Text and faces are among the most perceptually salient and practically important patterns in visual generation, yet they remain challenging for autoregressive generators built on d…
Steering Visual Generation in Unified Multimodal Models with Understanding Supervision
Zeyu Liu, Zanlin Ni, Yang Yue +5
Unified multimodal models are envisioned to bridge the gap between understanding and generation. Yet, to achieve competitive performance, state-of-the-art models adopt largely deco…
AdaGen: Learning Adaptive Policy for Image Synthesis
Zanlin Ni, Yulin Wang, Yeguo Hua +5
Recent advances in image synthesis have been propelled by powerful generative models, such as Masked Generative Transformers (MaskGIT), autoregressive models, diffusion models, and…
The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models
Zanlin Ni, Shenzhi Wang, Yang Yue +8
Diffusion Large Language Models (dLLMs) break the rigid left-to-right constraint of traditional LLMs, enabling token generation in arbitrary orders. Intuitively, this flexibility i…
Co-GRPO: Co-Optimized Group Relative Policy Optimization for Masked Diffusion Model
Renping Zhou, Zanlin Ni, Tianyi Chen +6
Recently, Masked Diffusion Models (MDMs) have shown promising potential across vision, language, and cross-modal generation. However, a notable discrepancy exists between their tra…
Emulating Human-like Adaptive Vision for Efficient and Flexible Machine Visual Perception
Yulin Wang, Yang Yue, Huanqian Wang +11
Human vision is highly adaptive, efficiently sampling intricate environments by sequentially fixating on task-relevant regions. In contrast, prevailing machine vision models passiv…
CODA: Repurposing Continuous VAEs for Discrete Tokenization
Zeyu Liu, Zanlin Ni, Yeguo Hua +4
Discrete visual tokenizers transform images into a sequence of tokens, enabling token-based visual generation akin to language models. However, this process is inherently challengi…
ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis
Zanlin Ni, Yulin Wang, Renping Zhou +5
Recently, token-based generation have demonstrated their effectiveness in image synthesis. As a representative example, non-autoregressive Transformers (NATs) can generate decent-q…
AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation
Zanlin Ni, Yulin Wang, Renping Zhou +6
Recent studies have demonstrated the effectiveness of token-based methods for visual content generation. As a representative work, non-autoregressive Transformers (NATs) are able t…
Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis
Zanlin Ni, Yulin Wang, Renping Zhou +6
The field of image synthesis is currently flourishing due to the advancements in diffusion models. While diffusion models have been successful, their computational intensity has pr…
Everything to the Synthetic: Diffusion-driven Test-time Adaptation via Synthetic-Domain Alignment
Jiayi Guo, Junhao Zhao, Chaoqun Du +6
Test-time adaptation (TTA) aims to improve the performance of source-domain pre-trained models on previously unseen, shifted target domains. Traditional TTA methods primarily adapt…
LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images
Ruyi Xu, Yuan Yao, Zonghao Guo +7
Visual encoding constitutes the basis of large multimodal models (LMMs) in understanding the visual world. Conventional LMMs process images in fixed sizes and limited resolutions,…
Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models
Jiayi Guo, Xingqian Xu, Yifan Pu +6
Recently, diffusion models have made remarkable progress in text-to-image (T2I) generation, synthesizing images with high fidelity and diverse contents. Despite this advancement, l…
Deep Incubation: Training Large Models by Divide-and-Conquering
Zanlin Ni, Yulin Wang, Jiangwei Yu +3
Recent years have witnessed a remarkable success of large deep learning models. However, training these models is challenging due to high computational costs, painfully slow conver…
Cross-Modal Adapter for Vision-Language Retrieval
Haojun Jiang, Jianke Zhang, Rui Huang +4
Vision-language retrieval is an important multi-modal learning topic, where the goal is to retrieve the most relevant visual candidate for a given text query. Recently, pre-trained…
Revisiting Locally Supervised Learning: an Alternative to End-to-end Training
Yulin Wang, Zanlin Ni, Shiji Song +2
Due to the need to store the intermediate activations for back-propagation, end-to-end (E2E) training of deep networks usually suffers from high GPUs memory footprint. This paper a…
Uncertainty-aware Score Distribution Learning for Action Quality Assessment
Yansong Tang, Zanlin Ni, Jiahuan Zhou +4
Assessing action quality from videos has attracted growing attention in recent years. Most existing approaches usually tackle this problem based on regression algorithms, which ign…