Searcharxiv⌕ Search

arXiv subjects

Junlin Zeng

Publications and source records attributed to Junlin Zeng.

6 recordsLinked to original sources

Direction or Magnitude? Learning Scalars over Task-Calibrated Directions

Parameter-efficient fine-tuning (PEFT) aims to preserve adaptation quality while reducing training costs. We propose SCALAR, which achieves performance comparable to LoRA with substantially fewer trainable parameters, lower peak training memory, and higher throughput. SCALAR constructs a fixed input basis from task activations and assigns a random output dictionary to each input direction. Fine-tuning learns only layer-specific scalar coefficients, reducing gradient and optimizer-state storage. Grouped computation aggregates output atoms before applying the adapter to token activations, while dictionary sharing across compatible layers reduces fixed-basis storage. Experiments on commonsense reasoning, mathematical reasoning, code generation, and knowledge evaluation after instruction tuning demonstrate effective adaptation at small trainable budgets. On commonsense reasoning, SCALAR achieves accuracy comparable to LoRA with about 4% of its trainable parameters. System measurements on Qwen2.5-7B show 20% lower peak training memory and 6% higher throughput than LoRA. The combination of adaptation quality, a compact trainable state, and training efficiency makes SCALAR a promising approach to resource-constrained fine-tuning.

cs.LG↗

Wanda-Guided Sparse Perturbations for Efficient Zeroth-Order Optimization

Zeroth-order (ZO) optimization enables memory-efficient fine-tuning of large language models through forward-only evaluations, but high-dimensional random perturbations can limit optimization efficiency. Sparse perturbations reduce the search dimension, making the selection of informative coordinates critical. We propose Wanda-Importance Sparsity-MeZO (WIS-MeZO), which uses Wanda weight--activation saliency to construct task-conditioned sparse perturbation masks while keeping the pretrained model dense. We analyze support quality through gradient energy capture and relate it to gradient estimation and convergence. Across 16 benchmarks with LLaMA and Qwen models ranging from 3B to 32B parameters, WIS-MeZO achieves higher aggregate scores than MeZO and reaches comparable validation losses in fewer optimization steps. Comparisons with random and magnitude-based sparse perturbations further highlight the importance of informative support selection.

cs.LG↗

MoLS: SNR-Guided Module-Wise Learning-Rate Calibration for Large Language Models

Large language models (LLMs) contain functionally distinct modules with heterogeneous gradient statistics. Although Adam(W) adapts updates at the parameter level, selecting relative learning rates across modules often relies on costly manual tuning. We study this problem through gradient signal-to-noise ratio (SNR). Our analysis identifies structural sources of module-wise SNR differences and relates SNR to the attenuation of Adam's normalized mean-gradient component. Based on these findings, we propose \textbf{Module-wise Learning Rate Scaling via SNR (\name)}, a lightweight method that replaces manual multiplier search with one-shot calibration. MoLS estimates module-level SNRs after an initial adaptation period and uses inverse-square-root scaling to determine relative learning-rate multipliers. The multipliers are introduced smoothly during warmup and then held fixed while the global learning-rate schedule continues. Our theoretical results quantify the effect of calibration and its sensitivity to estimation error and relative SNR drift. Extensive experiments across LLM pre-training and fine-tuning show that MoLS reduces perplexity and improves downstream accuracy with minimal computational overhead. It achieves performance comparable to carefully tuned module-specific learning rates and integrates with memory-efficient optimizers and parameter-efficient fine-tuning.

cs.LG↗

GWT: Scalable Optimizer State Compression for Large Language Model Training

Training large language models (LLMs) requires substantial memory, a significant fraction of which is consumed by the moment states maintained by adaptive optimizers such as Adam. Existing memory-efficient approaches commonly compress parameters or gradients through low-rank projections, which may discard information outside the selected subspace or incur additional costs from subspace construction and singular value decomposition (SVD). We introduce \textbf{Gradient Wavelet Transform (GWT)}, an SVD-free framework that applies a multilevel Haar transform to matrix gradients. GWT maintains first- and second-moment states only for the compact approximation coefficients, while retaining all detail coefficients transiently in each update. We show that the orthogonal transform preserves the complete current gradient and establish gradient alignment and a stationary-point guarantee for smooth objectives under bounded preconditioning and a directly verifiable coarse-momentum coherence condition. Experiments on language-model pre-training and downstream fine-tuning show that GWT reduces estimated model-and-optimizer-state memory by up to 52\% while maintaining competitive or improved model quality. On LLaMA-3B pre-training, GWT achieves $1.9\times$ the throughput of 8-bit Adam and is compatible with multiple optimizer families, including Adam, Adam-mini, and Muon.

cs.LG↗

A $1000\times$ Faster LLM-enhanced Algorithm For Path Planning in Large-scale Grid Maps

Path planning in grid maps, arising from various applications, has garnered significant attention. Existing methods, such as A*, Dijkstra, and their variants, work well for small-scale maps but fail to address large-scale ones due to high search time and memory consumption. Recently, Large Language Models (LLMs) have shown remarkable performance in path planning but still suffer from spatial illusion and poor planning performance. Among all the works, LLM-A* \cite{meng2024llm} leverages LLM to generate a series of waypoints and then uses A* to plan the paths between the neighboring waypoints. In this way, the complete path is constructed. However, LLM-A* still suffers from high computational time for large-scale maps. To fill this gap, we conducted a deep investigation into LLM-A* and found its bottleneck, resulting in limited performance. Accordingly, we design an innovative LLM-enhanced algorithm, abbr. as iLLM-A*. iLLM-A* includes 3 carefully designed mechanisms, including the optimization of A*, an incremental learning method for LLM to generate high-quality waypoints, and the selection of the appropriate waypoints for A* for path planning. Finally, a comprehensive evaluation on various grid maps shows that, compared with LLM-A*, iLLM-A* \textbf{1) achieves more than $1000\times$ speedup on average, and up to $2349.5\times$ speedup in the extreme case, 2) saves up to $58.6\%$ of the memory cost, 3) achieves both obviously shorter path length and lower path length standard deviation.}

cs.RO↗

Utilizing Players' Playtime Records for Churn Prediction: Mining Playtime Regularity

In the free online game industry, churn prediction is an important research topic. Reducing the churn rate of a game significantly helps with the success of the game. Churn prediction helps a game operator identify possible churning players and keep them engaged in the game via appropriate operational strategies, marketing strategies, and/or incentives. Playtime related features are some of the widely used universal features for most churn prediction models. In this paper, we consider developing new universal features for churn predictions for long-term players based on players' playtime.

cs.HC↗