arXiv subjects

Hong-Kai Zheng

Publications and source records attributed to Hong-Kai Zheng.

4 recordsLinked to original sources

arXiv2026

DeLS-Spec: Decoupled Long-Short Contexts for Parallel Speculative Drafting

Speculative decoding accelerates LLM inference by drafting multiple tokens and verifying them in parallel. Block-parallel drafters such as DFlash further improve drafting efficiency by predicting an entire block in one pass, but their position-wise predictions lack explicit intra-block causal conditioning. Recent methods such as Domino and DSpark attempt to introduce such causality into block-parallel drafting, but they require training the draft model from scratch, which limits their flexibility and increases training cost. We propose DeLS-Spec, a decoupled long-short context speculative decoding method. DeLS-Spec treats the fixed DFlash model as a long-context expert and introduces a lightweight local head as a short-context expert. The local head can be trained independently with a standard next-token prediction objective, without joint training with the target model or the DFlash backbone, leading to extremely low training cost. At inference time, DeLS-Spec combines long-context and short-context logits, and the local head is not tied to a specific DFlash checkpoint, making the method more modular and flexible. Experiments on Qwen3 models show that DeLS-Spec consistently improves speedup and average acceptance length over DFlash across math, code, and dialogue benchmarks.

cs.CL↗

arXiv2026

Temporal Guidance for Large Language Models

Contrastive Decoding (CD) enhances the generation quality of large language models (LLMs) but incurs significant additional computational overhead due to the need for an auxiliary model. Existing internal self-contrastive decoding methods, such as Decoding by Contrasting Layers (DoLa), focus on discrepancies across different layers, which are notably unstable on small-scale models. In this work, based on the observation that LLMs exhibit local preferences, we propose a novel contrastive guidance strategy along the temporal dimension, namely Temporal Guidance (TeGu). Our method ingeniously leverages Multi-Token Prediction (MTP) to construct weaker amateur predictions for model self-contrast. To standardize the implementation of this mechanism, we further introduce a lightweight Conditional MTP Projector (cMTPP), which avoids maintaining multiple independent networks as required by other MTP modules. Across various model series and benchmarks, TeGu achieves significant performance improvements while maintaining low additional memory consumption and computational overhead.

cs.CL↗

arXiv2025

LSRS: Latent Scale Rejection Sampling for Visual Autoregressive Modeling

Visual Autoregressive (VAR) modeling approach for image generation proposes autoregressive processing across hierarchical scales, decoding multiple tokens per scale in parallel. This method achieves high-quality generation while accelerating synthesis. However, parallel token sampling within a scale may lead to structural errors, resulting in suboptimal generated images. To mitigate this, we propose Latent Scale Rejection Sampling (LSRS), a method that progressively refines token maps in the latent scale during inference to enhance VAR models. Our method uses a lightweight scoring model to evaluate multiple candidate token maps sampled at each scale, selecting the high-quality map to guide subsequent scale generation. By prioritizing early scales critical for structural coherence, LSRS effectively mitigates autoregressive error accumulation while maintaining computational efficiency. Experiments demonstrate that LSRS significantly improves VAR's generation quality with minimal additional computational overhead. For the VAR-d30 model, LSRS increases the inference time by merely 1% while reducing its FID score from 1.95 to 1.78. When the inference time is increased by 15%, the FID score can be further reduced to 1.66. LSRS offers an efficient test-time scaling solution for enhancing VAR-based generation.

cs.CV↗

arXiv2025

Group-Wise Optimization for Self-Extensible Codebooks in Vector Quantized Models

Vector Quantized Variational Autoencoders (VQ-VAEs) leverage self-supervised learning through reconstruction tasks to represent continuous vectors using the closest vectors in a codebook. However, issues such as codebook collapse persist in the VQ model. To address these issues, existing approaches employ implicit static codebooks or jointly optimize the entire codebook, but these methods constrain the codebook's learning capability, leading to reduced reconstruction quality. In this paper, we propose Group-VQ, which performs group-wise optimization on the codebook. Each group is optimized independently, with joint optimization performed within groups. This approach improves the trade-off between codebook utilization and reconstruction performance. Additionally, we introduce a training-free codebook resampling method, allowing post-training adjustment of the codebook size. In image reconstruction experiments under various settings, Group-VQ demonstrates improved performance on reconstruction metrics. And the post-training codebook sampling method achieves the desired flexibility in adjusting the codebook size.

cs.CV↗