arXiv subjects

Yufeng Xu

Publications and source records attributed to Yufeng Xu.

6 recordsLinked to original sources

arXiv2026

Small LLMs: Pruning vs. Training from Scratch

Pruning promises a shortcut to strong small language models. In this work, we examine this promise by pruning Llama-3.1-8B at pruning ratios of 0.5--0.8 with six methods spanning depth, width, and sparse granularities, under two controlled token-matched settings. (1) With the same training token budget, pruned initialization consistently outperforms random initialization. This shows that the parent model provides a strong starting point, although the advantage narrows as the training token budget grows and as the pruning ratio rises, nearly vanishing at the highest pruning ratio we study. (2) When training from scratch is instead given the full token budget consumed by the whole pipeline, pruning at finer granularities still retains an advantage, while coarser structured pruning can be matched or surpassed. This suggests that the parent model transfers knowledge that additional training tokens alone cannot fully recover, but only at fine granularity. Taken together, our results yield a clear recommendation: with a large pretrained model in hand and a limited training token budget, pruning is better than training from scratch; when the training budget is not limited, training from scratch can be competitive for coarser pruning, so a large pretrained parent is not always necessary.

cs.LG↗

arXiv2026

Multi-Token Residual Prediction

Diffusion Language Models (DLMs) generate text by iteratively denoising masked token sequences, offering a tradeoff between parallelism and quality compared to autoregressive models. In current practice, the number of tokens decoded per step is controlled by a confidence threshold, and quality degrades monotonically as more tokens are denoised per step. We introduce Multi-token Residual Prediction (MRP), a lightweight module that enables dependency-aware multi-token denoising within a single backbone forward pass. MRP exploits a key property of the denoising process: the logit distributions at adjacent denoising steps are remarkably similar. Rather than running the backbone a second time to obtain the next-step logits, MRP predicts the residual between steps from the backbone's hidden states, effectively denoising more tokens per backbone forward at a fraction of the cost. We apply MRP across the two operating regimes of DLM decoding. In the high-quality-low-throughput static denoising regime, MRP serves as a drafter for speculative decoding: its proposals are verified against the backbone, yielding lossless acceleration of up to 1.4x in SGLang. In the low-quality-high-throughput dynamic denoising regime, MRP instead drives a remasking scheme that revokes over-eager reveals, recovering most of the accuracy lost to aggressive low-threshold decoding and improving accuracy by up to 22.6 points on code generation task HumanEval and 17.7 points on reasoning task GSM8K.

cs.LG↗

arXiv2026

Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning

Post-training of reasoning LLMs is a holistic process that typically consists of an offline SFT stage followed by an online reinforcement learning (RL) stage. However, SFT is often optimized in isolation to maximize SFT performance alone. We show that, after identical RL training, models initialized from stronger SFT checkpoints can significantly underperform those initialized from weaker ones. We attribute this to a mismatch typical in current SFT-RL pipelines: the distribution that generates the offline SFT data can differ substantially from the policy optimized during online RL, which learns from its own rollouts. We propose PEAR (Policy Evaluation-inspired Algorithm for Offline Learning Loss Re-weighting), an SFT-stage method that corrects this mismatch and better prepares the model for RL. PEAR uses importance sampling to reweight the SFT loss, with three variants operating at the token, block, and sequence levels. It can be used to augment standard SFT objectives and incurs little additional training overhead once probabilities for the offline data are collected. We conduct controlled experiments on verifiable reasoning games and mathematical reasoning tasks on Qwen 2.5 and 3 and DeepSeek-distilled models. PEAR consistently improves post-RL performance over canonical SFT, with pass at 8 gains up to a 14.6 percent on AIME2025. Our results suggest that PEAR is an effective step toward more holistic LLM post-training by designing and evaluating SFT with downstream RL in mind rather than in isolation.

cs.LG↗

arXiv2024

Tokensome: Towards a Genetic Vision-Language GPT for Explainable and Cognitive Karyotyping

Automatic karyotype analysis is often defined as a visual perception task focused solely on chromosomal object-level modeling. This definition has led most existing methods to overlook componential and holistic information, significantly constraining model performance. Moreover, the lack of interpretability in current technologies hinders clinical adoption. In this paper, we introduce Tokensome, a novel vision-language model based on chromosome tokenization for explainable and cognitive karyotyping. Tokensome elevates the method from the conventional visual perception layer to the cognitive decision-making layer. This elevation enables the integration of domain knowledge and cognitive reasoning via knowledge graphs and LLMs, markedly enhancing model's explainability and facilitating abnormality detection.

cs.CV↗

arXiv2024

BotanicGarden: A High-Quality Dataset for Robot Navigation in Unstructured Natural Environments

The rapid developments of mobile robotics and autonomous navigation over the years are largely empowered by public datasets for testing and upgrading, such as sensor odometry and SLAM tasks. Impressive demos and benchmark scores have arisen, which may suggest the maturity of existing navigation techniques. However, these results are primarily based on moderate structured scenario testing. When transitioning to challenging unstructured environments, especially in GNSS-denied, texture-monotonous, and dense-vegetated natural fields, their performance can hardly sustain at a high level and requires further validation and improvement. To bridge this gap, we build a novel robot navigation dataset in a luxuriant botanic garden of more than 48000m2. Comprehensive sensors are used, including Gray and RGB stereo cameras, spinning and MEMS 3D LiDARs, and low-cost and industrial-grade IMUs, all of which are well calibrated and hardware-synchronized. An all-terrain wheeled robot is employed for data collection, traversing through thick woods, riversides, narrow trails, bridges, and grasslands, which are scarce in previous resources. This yields 33 short and long sequences, forming 17.1km trajectories in total. Excitedly, both highly-accurate ego-motions and 3D map ground truth are provided, along with fine-annotated vision semantics. We firmly believe that our dataset can advance robot navigation and sensor fusion research to a higher level.

cs.RO↗

arXiv2023

Empirical Review of Smart Contract and DeFi Security: Vulnerability Detection and Automated Repair

Decentralized Finance (DeFi) is emerging as a peer-to-peer financial ecosystem, enabling participants to trade products on a permissionless blockchain. Built on blockchain and smart contracts, the DeFi ecosystem has experienced explosive growth in recent years. Unfortunately, smart contracts hold a massive amount of value, making them an attractive target for attacks. So far, attacks against smart contracts and DeFi protocols have resulted in billions of dollars in financial losses, severely threatening the security of the entire DeFi ecosystem. Researchers have proposed various security tools for smart contracts and DeFi protocols as countermeasures. However, a comprehensive investigation of these efforts is still lacking, leaving a crucial gap in our understanding of how to enhance the security posture of the smart contract and DeFi landscape. To fill the gap, this paper reviews the progress made in the field of smart contract and DeFi security from the perspective of both vulnerability detection and automated repair. First, we analyze the DeFi smart contract security issues and challenges. Specifically, we lucubrate various DeFi attack incidents and summarize the attacks into six categories. Then, we present an empirical study of 42 state-of-the-art techniques that can detect smart contract and DeFi vulnerabilities. In particular, we evaluate the effectiveness of traditional smart contract bug detection tools in analyzing complex DeFi protocols. Additionally, we investigate 8 existing automated repair tools for smart contracts and DeFi protocols, providing insight into their advantages and disadvantages. To make this work useful for as wide of an audience as possible, we also identify several open issues and challenges in the DeFi ecosystem that should be addressed in the future.

cs.CR↗