5 papers
Stop the Flip-Flop: Context-Preserving Verification for Fast Revocable Diffusion Decoding
Yanzheng Xiang, Lan Wei, Yizhen Yao +8
Parallel diffusion decoding can accelerate diffusion language model inference by unmasking multiple tokens per step, but aggressive parallelism often harms quality. Revocable decod…
Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States
Qinglin Zhu, Yizhen Yao, Runcong Zhao +7
Autoregressive (AR) models remain the standard for natural language generation but still suffer from high latency due to strictly sequential decoding. Recent diffusion-inspired app…
Diffusion Instruction Tuning
Chen Jin, Ryutaro Tanno, Amrutha Saseendran +2
We introduce Lavender, a simple supervised fine-tuning (SFT) method that boosts the performance of advanced vision-language models (VLMs) by leveraging state-of-the-art image gener…
Segment Anyword: Mask Prompt Inversion for Open-Set Grounded Segmentation
Zhihua Liu, Amrutha Saseendran, Lei Tong +8
Open-set image segmentation poses a significant challenge because existing methods often demand extensive training or fine-tuning and generally struggle to segment unified objects…
DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations
Aryo Pradipta Gema, Chen Jin, Ahmed Abdulaal +5
Large Language Models (LLMs) often hallucinate, producing unfaithful or factually incorrect outputs by misrepresenting the provided context or incorrectly recalling internal knowle…