Searcharxiv⌕ Search

arXiv subjects

Hongzhi Wang

Publications and source records attributed to Hongzhi Wang.

At least 19 recordsLinked to original sources

CARA: Exact Local Repair Queries for Cloud Consolidation

Cloud consolidation evaluates alternative workload placements to reduce overload under fixed host and migration budgets. A controller repeatedly queries the same demand history, but consumes only a small ranked result and one final repair. Shared aggregation and incremental assignment reuse individual computations but still reconstruct constraints and numerical certificates for many related queries. This preparation can erase the savings from skipping exact profiles. We present CARA, which compiles seed-universal movement constraints and family-wide load-error budgets, then acquires exact profiles according to certified ranking keys. The compiler leaves a migration-bounded assignment core and preserves ranked records, physical mappings and continuation state; a separate admission stage evaluates one frozen repair. On all 12,006 hourly series from four workload sources, CARA executes controlled queries 4.75 times faster than compact complete profiling and heterogeneous packed queries 3.05 times faster than family-local execution; across 300 budgeted consolidation decisions, it reduces excess over FFD by 35.8% and attains the lowest excess among the compared policies.

cs.DC↗

RiSE-Drive: Risk-Sensitive Long-Horizon Candidate Evaluation for End-to-End Autonomous Driving

End-to-end autonomous driving systems increasingly rely on generating multiple trajectory candidates and selecting one for execution. In this setting, a central challenge is no longer only candidate generation, but how to evaluate candidates according to their long-horizon consequences under uncertainty. Existing methods still mainly use deterministic point scores, heuristic subscores, or single-outcome evaluations, which makes it difficult to capture delayed failures, tail risk, and ranking instability under plausible future perturbations. We present RiSE-Drive, a framework for risk-sensitive long-horizon candidate evaluation in end-to-end autonomous driving. RiSE-Drive first performs candidate-conditioned latent future rollout, then estimates long-horizon outcome distributions instead of single scalar scores, and finally ranks candidates using a tail-risk-aware and perturbation-robust decision criterion. This reformulates candidate scoring from deterministic oracle-style evaluation into distributional outcome assessment with explicit risk control. As a result, the evaluator is encouraged to prefer candidates that are not only strong under nominal conditions, but also reliable under long-horizon rollout and safety-critical deviations. Experiments on the NAVSIM-v1 and NAVSIM-v2 benchmarks, as well as the closed-loop HUGSIM benchmark, show that RiSE-Drive achieves state-of-the-art performance and significantly improves the robustness of candidate selection.

cs.RO↗

Space-Optimal Algorithms for Spanning Forests in Dynamic Streams at Every Confidence Level: With and Without Deletion Constraints

We characterize the optimal space for one-pass spanning-forest computation in dynamic streams of $v$-vertex simple graphs with failure probability at most $δ$. Nelson and Yu proved an $Ω(v\log^2v\log(v/δ))$-bit lower bound, establishing the AGM algorithm's optimality for each fixed $0<ε<1$ and $2^{-v^{1-ε}}<δ\le1/4$. We resolve the remaining high-confidence regime: for every $0<δ\le1/4$, matching lower bounds and an algorithm give \[ Θ\!\left(\min\left\{v^2,\;v\log(v/δ)\log^2\!\left(2+\frac{v}{\log(v/δ)}\right)\right\}\right) \] bits, improving space by up to a factor of $Θ((\log v/\log\log v)^2)$ in this regime. We also study streams with at most $Z$ previously inserted edges deleted and not yet reinserted at report time, where the integer $Z\ge0$ is given in advance. Total deletions, restorations, and intermediate absence counts are unrestricted. For a single report and every $0<δ\le1/4$, matching lower bounds and a one-pass randomized algorithm yield optimal space $Θ(\mathcal L(v,Z,\log(1/δ)))$ bits, where $x_Z(t)=\min\{Z+1,v,\sqrt{vt}\}$ and \[ \mathcal L(v,Z,t)=v\log v\min\{\log^2v,\log^2(Z+2)\} +vt\log\!\left(1+\frac{x_Z(t)}t\right)\log\!\left(1+\frac v{x_Z(t)}\right). \] At zero error, a lower bound for all zero-error algorithms and a matching deterministic algorithm give optimal space \[ Θ\!\left(\min\{v^2,v(Z+1)\log(1+v/(Z+1))\}\right) \] bits. Together, these results characterize the memory required across all confidence levels and report-time edge-loss bounds.

cs.DS↗

Adaptive Data Selection for Text Classification: Hierarchical Value with a Local Utility Budget

Selecting compact training sets from heterogeneous text sources requires balancing target relevance, label reliability, and coverage. For small classifiers, discarding unfamiliar but useful texts can be as harmful as retaining annotation errors. Gradient-based selection estimates immediate target utility, whereas confidence and coverage scores capture complementary properties. Combining them with fixed weights leaves the utility sacrificed for this evidence uncontrolled across candidate pools. We propose Data Value Contribution (\DVC), which gates lexical, hidden-layer, and prediction-level evidence by neighborhood label support and calibrates its influence under a local utility budget; exact MLP gradient contractions and a monotone scoring path make the budget directly verifiable. At 20\% source retention, DVC achieves 75.4 mean macro F1 across eight classification and domain-transfer tasks, exceeding the strongest baseline under shared final training by 0.7 points and random selection by 4.3; an equal-budget tuning study confirms a 0.6-point gain over calibrated quality-only selection.

cs.LG↗

DeltaTrace: Efficient Signed Attribution for Reasoning Language Models

We study how words in the context support or oppose a language model's response and present DeltaTrace, a novel attribution framework that explains the effect of input tokens on a fixed model response. DeltaTrace measures how the response's log-probability changes when the context tokens being explained are masked. To distribute this difference among source tokens, it constructs operator-specific local rules for finite changes and composes them backward through the computational graph using effective secant slopes. Each token is assigned a signed attribution as the inner product of its embedding displacement and the corresponding backward-propagated slope. Local conservation makes these contributions sum to the measured score difference and preserves their meaning when aggregated over sentences or passages. DeltaTrace supports both attention and linear-attention models, with auxiliary memory growing linearly with sequence length at fixed model dimensions and chunk size. On the evaluated attention model, DeltaTrace achieves the lowest deletion-faithfulness scores (RISE and MAS) on most retrieval and reasoning tasks and the highest needle-in-a-haystack Recall, exceeding FlashTrace by 5.67-24.33 percentage points. On the evaluated hybrid attention and linear-attention model, DeltaTrace lowers RISE on 9 tasks and MAS on 12 relative to FlashTrace.

cs.LG↗

Conditional Indexing Lower Bounds and Normalization Boundaries for Elastic Subsequence Matching

We study static indexes for exact subsequence matching over all equal-length windows of a time series. Under deterministic SETH, for every fixed $β\ge1$ and $δ\in(0,1)$, we exclude $O(N^β)$ preprocessing together with $O(N^{1-δ})$ worst-case query time on domains containing the reduction's polylogarithmic query lengths. The bounded-error counterpart assumes randomized SETH. The results cover specified warping, bottleneck, edit, subsequence, local-alignment, and complexity-adjusted scores. Their reductions share a data-independent query interface but require different arguments for all-window soundness. We give complete representative proofs for the distinct mechanisms and state the changes needed by related scores. For soft-DTW, integer scaling yields an exact Boolean-predicate reduction in Word-RAM; a model with exact transcendental primitives requires a separate assumption. For independent window-wise Z-normalization, balanced coordinate gadgets and shifted-window moment bounds yield exact lower bounds for squared-cost DTW and discrete Fréchet distance. We give finite-word comparisons and a specified length-dependent rounding rule preserving these gaps. Raw and normalized discrete Fréchet constructions also exclude feasible-solution approximation within any fixed factor below two. Finally, we prove conditional signal-attenuation bounds for normalized anchor constructions and a fast index under the all-window common-mean promise.

cs.DS↗

Beyond Approved Actions: Runtime Validation of Persistent Outcomes in Agent Workflows

Large language model agents increasingly act on software systems, no longer merely generating text but also changing databases and online services. However, an approved database update may succeed yet leave an unapproved notification because execution can produce persistent effects beyond the requested change. Current safeguards can approve an action or record its aftermath, but without checking the persistent result before continuation, an unapproved outcome can be accepted as success and propagated to later steps. We present EffectMatch, a runtime that collects persistent changes within a controlled execution boundary and compares them with what the application approved for the current state and execution. The comparison governs commit and dependent execution. In comparative evaluation on 206 public business tasks, EffectMatch preserved all clean executions and prevented all tested incorrect commits. Six 20-run ablations exposed the failure caused by each removed mechanism, while 80 task-topology cases preserved truthful handoffs and blocked invalid continuation. Together, these results show that EffectMatch blocks the silent acceptance and downstream propagation of persistent outcomes inconsistent with application approval.

cs.SE↗

Explainable Multimodal Aspect-Based Sentiment Analysis with Dependency-guided Large Language Model

Multimodal aspect-based sentiment analysis (MABSA) aims to identify aspect-level sentiments by jointly modeling textual and visual information, which is essential for fine-grained opinion understanding in social media. Existing approaches mainly rely on discriminative classification with complex multimodal fusion, yet they lack explicit sentiment explainability. In this paper, we reformulate MABSA as a generative and explainable task, proposing a unified framework that simultaneously predicts aspect-level sentiment and generates natural language explanations. Based on multimodal large language models (MLLMs), our approach employs a prompt-based generative paradigm, jointly producing sentiment and explanation. To further enhance aspect-oriented reasoning capabilities, we propose a dependency-syntax-guided sentiment cue strategy. This strategy prunes and textualizes the aspect-centered dependency syntax tree, guiding the model to distinguish different sentiment aspects and enhancing its explainability. To enable explainability, we use MLLMs to construct explanation-augmented datasets for fine-tuning. Experiments show that our approach not only achieves overall gains in sentiment classification accuracy, but also produces coherent and aspect-grounded explanations.

cs.CL↗

Target-Independent Micro-Interventions for Predicting Training Response Across Language-Model Families

Benchmark scores describe what a checkpoint can do now, but they do not determine how it will respond to the next training episode. We measure this missing state by branching four short, standardized, target-independent micro-interventions from the same checkpoint and recording their effects in a common capability space. Together with current capability, these responses form L-State; its pulse block supports a flexible direct readout and a structure-preserving operator readout. Under smooth local dynamics, the operator construction admits an end-to-end cross-family bound with explicit source- and target-family coordinate heterogeneity. In three-family leave-one-family-out development, both pulse readouts reduce source-standardized MSE by 39.4% relative to capability alone, while separating the best response and direction estimates. On sealed GLM-4-9B, the direct and operator readouts reduce MSE by 71.8% and 78.3%, respectively, and the operator readout raises sign balanced accuracy from 0.366 to 0.754. On sealed Granite-3.1-8B, the direct readout reaches RMSE 0.544 and a development-fitted action-wise selector reaches 0.554, compared with 1.172 for capability alone. A five-family audit finds that the operator coordinate varies by action and family, and that modeling these deviations improves retrospective held-trajectory prediction. Target-independent interventions therefore expose training-response information that current capability misses, with direct and structured readouts covering complementary transfer regimes.

cs.LG↗

Record Grouping Controls Evidence Weight in Language Models

Retrieved records are presentation units; a supplied partition determines which records enter a language model as one evidential contribution. We characterize the invariant group-content state that removes within-group copies while retaining complementary canonical content, show that equal group counts can encode different evidence states, and derive a sharp content-aware partition-error bound. Given a supplied partition, our pre-generation representation deduplicates and aggregates content within groups and bounds each group's contribution. Across 104,402 trials and 6 public checkpoints, a central natural-text intervention finds that content-fixed false splits add 10.27-32.66 percentage points and false merges remove 9.13-31.79 points; a matched six-slot control retains the positive direction in all 16 cells. In a new 48-item controlled campaign panel, changing the supplied partition produces measurable, checkpoint-dependent decision shifts across all four models, and the balanced mirror design exposes substantial order interactions. Together, the theory and experiments establish the supplied partition as a controllable pre-generation representation variable and characterize its checkpoint-dependent behavioral effects.

cs.CL↗

Weighted Data Selection: Sharp Upper-Half and Five-Dimensional Laws

How much risk does a small reweighted training support retain? For finite weighted least squares with the minimum-norm learner, we prove the exact law $Γ_d(n)=3-n/d$ throughout $\lceil3d/2\rceil\leq n\leq2d-1$. The guarantee covers every observed feature rank and uses selections that preserve the full feature span. Balanced simplex anchors reduce dimension; positive-weight lifting and independent-line compression close the risk bound. Shifted coordinate pairs attain the matching lower bound. The complete dataset-level upper bound and sharpness construction are verified in Lean 4. At the smaller budget $(d,n)=(5,6)$, we also prove $Γ_5(6)=11/5$, matching the simplex-block prediction from $5=3+2$ over arbitrary interacting configurations. Circuit covers, comparison second moments, and circuit-plane probabilities give the sharp excess $6/5$, while polar-face geometry resolves shared rank-three circuits. The general simplex-block frontier connects these laws within the intermediate-budget selection problem.

stat.ML↗

SMM Transformer: Leveraging Spiking Neural Networks for Multimodal Tasks

Spiking Neural Networks (SNNs) enable event-driven computation with sparse activations, but building multimodal Transformers on SNNs is hindered by unstable training in deep spiking stacks and the mismatch between dense softmax attention and spike-based communication. We propose SMM Transformer, an SNN-based multimodal Transformer framework that combines (i)PLMP, a Parallel LIF with Multistage Learnable Parameters neuron and a tailored P-STBP algorithm for stable deep SNN training, (ii) SMSA, an attention-inspired spike-driven token-mixing module that replaces dense pairwise softmax attention with channel-wise spike co-activation and self-compensation, and (iii)SMoE, a spiking mixture-of-experts module for modality-aware fusion. Across visual and multimodal benchmarks, SMM Transformer achieves competitive accuracy compared to ANN baselines. Under a standard MAC/AC arithmetic model, SMSA reduces the estimated operator-level compute energy of the attention module by up to 97%, while whole-model profiling shows more moderate but consistent efficiency gains.

cs.NE↗

Spike-HTR: Spiking Neural Transformer for Handwritten Text Recognition

Handwritten Text Recognition (HTR) is computationally imbalanced in two ways: most image pixels are background, and many width-axis sequence positions are blank-dominated. This creates a mismatch for Spiking Neural Networks (SNNs): handwriting is observed as a static image, whereas spiking computation unfolds over timesteps. We propose Spike-HTR, a hybrid spiking recognizer that controls both the number of spiking steps and the number of width positions processed by the deep sequence mixer. To make a static image suitable for short-horizon spiking inference, InkCoder converts it into a coarse-to-fine input stream, where early steps cover broad stroke regions and later steps emphasize sharper stroke details. To reduce sequence computation, a CTC-guided length reducer keeps likely character or uncertain positions and compresses long blank-dominated stretches before deep mixing. With $T{=}2$, Spike-HTR trains only on target data, decodes without language models or lexicons, and reaches validation/test CERs of 3.5/5.4, 2.3/2.5, and 4.2/3.9 on IAM, LAM, and READ2016. Codes are available at https://github.com/QomolangmaH/SpikeHTR.

cs.NE↗

ALIVE: Warnings Before Exclusion in Budgeted Multi-Source Learning

A routing decision can be revised at the next transaction, but a latched source exclusion persists across later decisions. We ask what evidence should authorize these unequal-persistence actions when finite-population auditing and learning share a budget. ALIVE (Action-Layered Intervention via Evidence) is an auditable control layer: one randomized without-replacement prefix supplies cached evidence, heuristic warnings drive non-latching floor-bounded routing, and only two fresh simultaneous certificate separations may latch an exclusion request subject to capacity-feasible activation. Conditional on fixed support and labels under an ideal uniform audit permutation, any predictable controller preserving this interface inherits an anytime familywise bound of δon acting against a source that fails the pre-fixed absolute or relative strict-majority-disagreement predicate. With a published known-size, all-strict-majority PPR engine, median evidence count fell from 304 to 96 identities in e40 and from 171 to 62 in e60, while both engines used 48 in e80. In the matched CIFAR controller, the persistent-action layer added +0.1935 accuracy-AUBC percentage points over routing-only in all ten paired seed clusters. The +0.1954-point full-system contrast against CBR was also positive but did not meet the predeclared multiplicity-adjusted criterion (conditional Holm-adjusted sign-flip reference value =.097656). On a fixed natural panel, exploratory PPR used a median closure prefix of 95 rather than 105 for exploratory Serfling/FPC, but still exposed 88.0% of the panel and had no downstream task. Together these results map a restraint--power--cost--utility boundary: the action contract controls a defined persistent decision, while net value depends on evidence margin, audit cost, and budget regime.

cs.LG↗

Musings on Constructions of Optimal Latin Hypercube Designs with Flexible Sizes

Latin hypercube designs (LHDs) play an important role in computer experiments, offering flexible and efficient space-filling properties under a variety of optimality criteria, including maximin distance, maximum projection, and orthogonality. Constructing optimal LHDs with flexible sizes is challenging due to the limited availability of theoretical results, namely, algebraic constructions with provable optimality guarantees, and the rapidly expanding search space encountered by search algorithms. For design sizes outside the scope of known algebraic constructions, search-based algorithms are widely used, but they often involve substantial computational effort and lack assurances of global optimality. This paper provides a comprehensive review and comparison of current popular algebraic constructions for optimal LHDs and widely adopted search algorithms for generating high-quality LHDs. By reviewing their theoretical properties and empirical performance across a range of criteria, we offer a unified perspective on their relative strengths and limitations. The comparisons presented herein aim to assist practitioners in selecting appropriate design strategies for different objectives and constraints. The insights from this work also highlight open challenges and may serve as a benchmark for future development in optimal LHD construction.

stat.ME↗

Cordon-MAS: Defending RAG against Knowledge Poisoning via Information-Flow Control

Retrieval-augmented generation (RAG) increasingly underpins high-stakes applications, yet remains vulnerable to Confundo-style poisoning where adversarially optimized documents manipulate generated outputs. Existing defenses assume that detecting poisoned evidence prevents harm. We show this assumption is incorrect: models exhibit a monitoring-control gap -- they can detect contradictions in retrieved evidence yet still act on poisoned claims. We introduce the Cordon Principle -- no agent capable of final synthesis may access untrusted natural-language evidence -- and realize it through CORDON-MAS, a compartmentalized framework that enforces this principle architecturally by separating evidence extraction, cross-source audit, and answer synthesis into agents with asymmetric memory privileges. Across five BEIR datasets, CORDON-MAS reduces attack success rate by 92.4\% relative to undefended RAG. This reframes RAG poisoning from a detection problem to an information-flow control problem.

cs.CR↗

Composition Collapse: Stable Factual Knowledge Does Not Imply Compositional Reasoning

Post-training is routinely evaluated through aggregate benchmark scores that treat multi-hop reasoning as a single capability -- as if a model that answers more questions correctly must be better at assembling facts. We show that this assumption can be misleading: recipes with statistically indistinguishable atomic knowledge produce composition behaviour separated by over 40 percentage points, a phenomenon we call composition collapse: the systematic failure to assemble stably-known facts into chains, invisible to aggregate metrics. We introduce a double-gate protocol that changes the estimand from an aggregate compositionality gap to residual composition failure conditioned on stable atomic access, decomposing post-training gains into three independent channels: atomic stability, residual composition, and critical depth. On a benchmark of temporal factual chains spanning depths 2--11 across four post-training recipes, this decomposition reveals that post-training objectives shift composition capability in directions that aggregate metrics mask, and suggests that claims about multi-hop reasoning improvement should be accompanied by atomic-gate-controlled composition metrics. Diagnostic probes further show that a substantial share of measured composition failure reflects generation-time computation constraints rather than permanent inability to compose.

cs.AI↗

FREE-Switch: Frequency-based Dynamic LoRA Switch for Style Transfer

With the growing availability of open-sourced adapters trained on the same diffusion backbone for diverse scenes and objects, combining these pretrained weights enables low-cost customized generation. However, most existing model merging methods are designed for classification or text generation, and when applied to image generation, they suffer from content drift due to error accumulation across multiple diffusion steps. For image-oriented methods, training-based approaches are computationally expensive and unsuitable for edge deployment, while training-free ones use uniform fusion strategies that ignore inter-adapter differences, leading to detail degradation. We find that since different adapters are specialized for generating different types of content, the contribution of each diffusion step carries different significance for each adapter. Accordingly, we propose a frequency-domain importance-driven dynamic LoRA switch method. Furthermore, we observe that maintaining semantic consistency across adapters effectively mitigates detail loss; thus, we design an automatic Generation Alignment mechanism to align generation intents at the semantic level. Experiments demonstrate that our FREE-Switch (Frequency-based Efficient and Dynamic LoRA Switch) framework efficiently combines adapters for different objects and styles, substantially reducing the training cost of high-quality customized generation.

cs.CV↗