13 papers
Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning
Yan Jiang, Ruihong Qiu, Zi Huang
Recent diffusion large language models (dLLMs) have demonstrated both effectiveness and efficiency in reasoning via a block-based semi-autoregressive generation paradigm. Despite t…
Perceptual Flow Network for Visually Grounded Reasoning
Yangfu Li, Yuning Gong, Hongjian Zhan +8
Despite the success of Large-Vision Language Models (LVLMs), general optimization objectives (e.g., standard MLE) fail to constrain visual trajectories, leading to language bias an…
TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders
Teng Li, Ziyuan Huang, Cong Chen +5
We propose TC-AE, a ViT-based architecture for deep compression autoencoders. Existing methods commonly increase the channel number of latent representations to maintain reconstruc…
AgentVLN: Towards Agentic Vision-and-Language Navigation
Zihao Xin, Wentong Li, Yixuan Jiang +6
Vision-and-Language Navigation (VLN) requires an embodied agent to ground complex natural-language instructions into long-horizon navigation in unseen environments. While Vision-La…
StruVis: Enhancing Reasoning-based Text-to-Image Generation via Thinking with Structured Vision
Yuanhuiyi Lyu, Kaiyu Lei, Ziqiao Weng +7
Reasoning-based text-to-image (T2I) generation requires models to interpret complex prompts accurately. Existing reasoning frameworks can be broadly categorized into two types: (1)…
Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation
Canxiang Yan, Chunxiang Jin, Dawei Huang +22
Existing speech models suffer from competing requirements on token representations by understanding and generation tasks. This discrepancy in representation prevents speech languag…