8 papers
Factorization-Guided Training and Inference for Diffusion-Drafted Speculative Decoding
Jiakun Fan, Min Xiao, Qiang Wang +5
Speculative decoding accelerates large language model inference through parallel verification of tokens proposed by a drafter. Diffusion drafters further parallelize proposal gener…
Where Does Staleness Accumulate? Pool Aware Effective Staleness Control for Asynchronous RL in LLM Post-Training
Chenliang Li, Neiwen Ling, Zijun Wei +1
Fully asynchronous reinforcement learning (RL) improves resource utilization in large language model post-training by overlapping rollout generation with policy optimization, but i…
Diagnosing Training Inference Mismatch in LLM Reinforcement Learning via a Zero-Mismatch Reference
Tianle Zhong, Neiwen Ling, Yifan Pi +5
Modern LLM RL systems separate rollout generation from policy optimization. These two stages are expected to produce token probabilities that match exactly. However, implementation…
LPNSR: Learnable Noise Prediction for Diffusion-Based Image Super-Resolution
Shuwei Huang, Shizhuo Liu, Zijun Wei
Diffusion-based image super-resolution (SR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) observations. A key property of diffusion models is that, once…
VGent: Visual Grounding via Modular Design for Disentangling Reasoning and Prediction
Weitai Kang, Jason Kuen, Mengwei Ren +3
Current visual grounding models are either based on a Multimodal Large Language Model (MLLM) that performs auto-regressive decoding, which is slow and risks hallucinations, or on r…
Sparse-LaViDa: Sparse Multimodal Discrete Diffusion Language Models
Shufan Li, Jiuxiang Gu, Kangning Liu +4
Masked Discrete Diffusion Models (MDMs) have achieved strong performance across a wide range of multimodal tasks, including image understanding, generation, and editing. However, t…
Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation
Shufan Li, Jiuxiang Gu, Kangning Liu +4
We propose Lavida-O, a unified Masked Diffusion Model (MDM) for multimodal understanding and generation. Unlike existing multimodal MDMs such as MMaDa and Muddit which only support…
Refer to Any Segmentation Mask Group With Vision-Language Prompts
Shengcao Cao, Zijun Wei, Jason Kuen +6
Recent image segmentation models have advanced to segment images into high-quality masks for visual entities, and yet they cannot provide comprehensive semantic understanding for c…