arXiv subjects

Linghao Kong

Publications and source records attributed to Linghao Kong.

8 recordsLinked to original sources

arXiv2026

The Sparsity Whisperer

Pruning reduces the inference cost of large language models, but existing criteria primarily preserve large activations or reconstruct layer outputs. We argue that this overlooks a key computation performed by particularly sparsity-sensitive neurons in the MLP up and gate projections: separating similar inputs into dissimilar outputs. This suggests that effective pruning should preserve not only activations, but also the differences between outputs more broadly. We introduce a family of difference-informed pruning methods built upon this principle. Wisp is a first-order, update-free method that scores weights using input-difference norms, and Wisp+ refines this score neuronwise using the input pairs each neuron separates most strongly. Finally, Whisper is a second-order method that uses a lightly regularized difference Hessian as its reconstruction objective. Across Llama 2 and 3.1 models from 7B to 405B parameters, our second-order variant consistently improves over strong reconstruction-based baselines, while our update-free variants improve over activation-aware baselines, especially in constrained settings. The improvements over Wanda and SparseGPT extend to structured sparsity, downstream evaluations, and other model families. Augmenting stronger techniques such as RIA and ALPS with our difference-informed criteria yields further improvements, shifting the overall accuracy-runtime frontier outward at negligible additional cost. These results suggest that preserving output differences is a broadly useful and composable signal for post-training LLM sparsification.

cs.LG↗

arXiv2026

An Interpretable Latency Model for Speculative Decoding in LLM Serving

Speculative decoding (SD) accelerates large language model (LLM) inference by using a smaller draft model to propose multiple tokens that are verified by a larger target model in parallel. While prior work demonstrates substantial speedups in isolated or fixed-batch settings, the behavior of SD in production serving systems remains poorly understood: request load varies over time, and effective batch size emerges from the serving system rather than being directly controlled or observed. In this work, we develop a simple and interpretable latency model for SD in LLM serving. We infer effective batch size from request rate using Little's Law and decompose per-request demand into load-independent and load-dependent components for prefill, drafting, and verification. We validate our model using extensive measurements from vLLM across verifier and drafter model sizes, prefill and decode lengths, request rates, draft lengths, and acceptance probabilities. The model accurately describes observed latency, explains why speedups often diminish as server load increases, and characterizes how draft length, acceptance rate, and verifier-drafter size shape latency across serving conditions, with implications for configuring SD in deployed systems. We further show how the framework extends to mixture of experts models, where sparse expert activation changes the effective service costs across load regimes. Together, our results provide a structured framework for understanding SD in real LLM serving systems.

cs.LG↗

arXiv2025

Time Series Forecasting via Direct Per-Step Probability Distribution Modeling

Deep neural network-based time series prediction models have recently demonstrated superior capabilities in capturing complex temporal dependencies. However, it is challenging for these models to account for uncertainty associated with their predictions, because they directly output scalar values at each time step. To address such a challenge, we propose a novel model named interleaved dual-branch Probability Distribution Network (interPDN), which directly constructs discrete probability distributions per step instead of a scalar. The regression output at each time step is derived by computing the expectation of the predictive distribution on a predefined support set. To mitigate prediction anomalies, a dual-branch architecture is introduced with interleaved support sets, augmented by coarse temporal-scale branches for long-term trend forecasting. Outputs from another branch are treated as auxiliary signals to impose self-supervised consistency constraints on the current branch's prediction. Extensive experiments on multiple real-world datasets demonstrate the superior performance of interPDN.

cs.LG↗

arXiv2025

Expand Neurons, Not Parameters

This work demonstrates how increasing the number of neurons in a network without increasing its total number of non-zero parameters improves performance. We show that this gain corresponds with a decrease in interference between multiple features that would otherwise share the same neurons. On symbolic Boolean tasks, splitting each neuron into sparser sub-neurons with knowledge of the clauses systematically reduces polysemanticity metrics and yields higher task accuracy. Notably, even random splits of neuron weights approximate these gains, indicating that reduced collisions, not precise assignment, are a primary driver. Consistent with the superposition hypothesis, the benefits of this framework grow with increasing interference: when polysemantic load is high, accuracy improvements are the largest. Transferring these insights to more realistic models, including classifiers over CLIP embeddings, convolutional neural networks, and deeper multilayer networks, we find that widening networks while maintaining a constant non-zero parameter count consistently increases accuracy. These results identify an interpretability-grounded mechanism to leverage width against superposition, improving performance without increasing the number of non-zero parameters. Such a direction is well matched to modern accelerators, where memory movement of non-zero parameters, rather than raw compute, is often a dominant bottleneck.

cs.LG↗

arXiv2025

Negative Pre-activations Differentiate Syntax

Modern large language models increasingly use smooth activation functions such as GELU or SiLU, allowing negative pre-activations to carry both signal and gradient. Nevertheless, many neuron-level interpretability analyses have historically focused on large positive activations, often implicitly treating the negative region as less informative, a carryover from the ReLU-era. We challenge this assumption and ask whether and how negative pre-activations are leveraged by models. We address this question by studying a sparse subpopulation of Wasserstein neurons whose output distributions deviate strongly from a Gaussian baseline and that functionally differentiate similar inputs. We show that this negative region plays an active role rather than reflecting a mere gradient optimization side effect. A minimal, sign-specific intervention that zeroes only the negative pre-activations of a small set of Wasserstein neurons substantially increases perplexity and sharply degrades grammatical performance on BLiMP and TSE, whereas both random and perplexity-matched ablations of many more non-Wasserstein neurons in their negative pre-activations leave grammatical performance largely intact. Conversely, on a suite of non-grammatical benchmarks, the perplexity-matched control ablation is more damaging than the Wasserstein neuron ablation, yielding a double dissociation between syntax and other capabilities. Part-of-speech analysis localizes the excess surprisal to syntactic scaffolding tokens, layer-specific interventions show that small local degradations accumulate across depth, and training-dynamics analysis reveals that the same sign-specific ablation becomes more harmful as Wasserstein neurons emerge and stabilize. Together, these results identify negative pre-activations in a sparse subpopulation of Wasserstein neurons as an actively used substrate for syntax in smooth-activation language models.

cs.LG↗

arXiv2025

Electro-mechanical wrinkling of soft dielectric films bonded to hyperelastic substrates

Active control of wrinkling in soft film-substrate composites using electric fields is a critical challenge in tunable material systems. Here, we investigate the electro-mechanical instability of a soft dielectric film bonded to a hyperelastic substrate, revealing the fundamental mechanisms that enable on-demand surface patterning. For the linearized stability analysis, we use the Stroh formalism and the surface impedance method to obtain exact and sixth-order approximate bifurcation equations that signal the onset of wrinkles. We derive the explicit bifurcation equations giving the critical stretch and critical voltage for wrinkling, as well as the corresponding critical wavenumber. We look at scenarios where the voltage is kept constant and the stretch changes, and vice versa. We provide the thresholds of the shear modulus ratio $r_{\rm c}^0$ or pre-stretch $\lambda_{\rm c}^0$ below which the film-substrate system wrinkles mechanically, prior to the application of a voltage. These predictions offer theoretical guidance for practical structural design, as the shear modulus ratio $r$ and/or the pre-stretch $\lambda$ can be chosen to be slightly greater than $r_{\rm c}^0$ and/or $\lambda_{\rm c}^0$, so that the film-substrate system wrinkles with a small applied voltage. Finally, we simulate the full nonlinear behavior using the Finite Element method (FEniCS) to validate our formulas and conduct a post-buckling analysis. This work advances the fundamental understanding of electro-mechanical wrinkling instabilities in soft material systems. By enabling active control of surface morphologies via applied electric fields, our findings open new avenues for adaptive technologies in soft robotics, flexible electronics, smart surfaces, and bioinspired systems.

cond-mat.soft↗

arXiv2024

Wasserstein Distances, Neuronal Entanglement, and Sparsity

Disentangling polysemantic neurons is at the core of many current approaches to interpretability of large language models. Here we attempt to study how disentanglement can be used to understand performance, particularly under weight sparsity, a leading post-training optimization technique. We suggest a novel measure for estimating neuronal entanglement: the Wasserstein distance of a neuron's output distribution to a Gaussian. Moreover, we show the existence of a small number of highly entangled "Wasserstein Neurons" in each linear layer of an LLM, characterized by their highly non-Gaussian output distributions, their role in mapping similar inputs to dissimilar outputs, and their significant impact on model accuracy. To study these phenomena, we propose a new experimental framework for disentangling polysemantic neurons. Our framework separates each layer's inputs to create a mixture of experts where each neuron's output is computed by a mixture of neurons of lower Wasserstein distance, each better at maintaining accuracy when sparsified without retraining. We provide strong evidence that this is because the mixture of sparse experts is effectively disentangling the input-output relationship of individual neurons, in particular the difficult Wasserstein neurons.

cs.LG↗

arXiv2022

Defending Adversarial Examples by Negative Correlation Ensemble

The security issues in DNNs, such as adversarial examples, have attracted much attention. Adversarial examples refer to the examples which are capable to induce the DNNs return completely predictions by introducing carefully designed perturbations. Obviously, adversarial examples bring great security risks to the development of deep learning. Recently, Some defense approaches against adversarial examples have been proposed, however, in our opinion, the performance of these approaches are still limited. In this paper, we propose a new ensemble defense approach named the Negative Correlation Ensemble (NCEn), which achieves compelling results by introducing gradient directions and gradient magnitudes of each member in the ensemble negatively correlated and at the same time, reducing the transferability of adversarial examples among them. Extensive experiments have been conducted, and the results demonstrate that NCEn can improve the adversarial robustness of ensembles effectively.

cs.CR↗