DnD in Research: Diverse Meanings

• DnD is a polysemous acronym defined within multiple fields, including multimodal NLP, LLM adaptation, and materials science.
• Its applications range from creating Dungeons & Dragons conversation corpora to optimizing model efficiency and addressing adversarial security.
• The term highlights cross-disciplinary methodology sharing and the challenges of acronym collisions in modern research.

In current arXiv usage, DnD is not a single technical term but a polysemous acronym whose meaning is fixed by disciplinary context. It denotes, among other things, a Dungeons & Dragons-derived multimodal conversation corpus, a prompt-conditioned parameter generator for LLMs, a delayed backdoor prototype, a pairwise object-detection comparison method, a training-free neuron-interpretation pipeline, a dense monocular depth estimator, a post-training token-reprocessing method for LLMs, a mixed elliptic boundary condition shorthand, and a materials-science abbreviation for detonation nanodiamond (Suresh et al., 22 Oct 2025, Liang et al., 19 Jun 2025, Ding et al., 12 Mar 2026, Theodoridis et al., 5 Jun 2026, Bai et al., 2024, Jung et al., 2021, Chen et al., 13 Oct 2025, Zeng et al., 2023, Saberi-Movahed et al., 2021). The term therefore functions less as a stable concept than as a recurrent local shorthand.

1. Nomenclature and scope

The principal documented senses of DnD/DND in the cited literature are summarized below.

Usage	Meaning	Domain
DnD Gesture / DnD Gesture++	Dungeons & Dragons multi-party conversation corpus	Multimodal NLP
SHADE / CALYPSO DnD domain	Forgotten Realms lore and Dungeon Master support	NLP / HCI
Drag-and-Drop LLMs	Prompt-to-LoRA weight generation	LLM adaptation
Delayed Backdoor Attacks Based on Nonlinear Decay	Stateful delayed backdoor prototype	AI security
Differences in Detection	Pairwise detector comparison	Computer vision
Describe-and-Dissect	Neuron description pipeline	Interpretability
Dense Depth Estimation in Crowded Dynamic Indoor Scenes	Monocular depth method	3D vision
Dynamic Nested Depth	Selective token reprocessing in LLMs	LLM efficiency
Dirichlet–Neumann–Dirichlet	Mixed boundary condition shorthand	PDE / control
Detonation nanodiamond	Nanomaterial abbreviation	Materials science

This distribution is concrete rather than merely terminological. In the Dungeons & Dragons-centered literature, DnD names either the application domain or a corpus built from roleplaying interaction; in LLM work it names adaptation or compute-allocation methods; in security it marks either a delayed backdoor prototype or a conceptual defense architecture; and in PDEs and nanomaterials it is a conventional abbreviation embedded in preexisting technical vocabularies (Peiris et al., 2024, Zhu et al., 2023, A et al., 2019).

2. Dungeons & Dragons as corpus, ontology, and interaction setting

A prominent meaning of DnD is the Dungeons & Dragons roleplaying environment used as a naturalistic source of multimodal conversational data. The DnD Gesture corpus contains synchronized 3D body motion, audio, and transcripts from five English-speaking participants over four sessions, totaling about 6 hours. The extension DnD Gesture++ adds 2,663 semantic gesture annotations, about 444 labels/hour, following McNeill’s taxonomy: Iconic: 724, Metaphoric: 151, Deictic: 1,155, and Discourse: 633. Annotation was carried out in ELAN, with one track per participant, and the reported interrater agreement is Cohen’s $\kappa = 0.52$. The resulting turn-taking benchmark segments speech into Inter-Pausal Units (IPUs) ending at Transition Relevance Places (TRPs), uses a 200 ms silence threshold, yields about 12k turns total, and frames prediction as hold versus yield. In that setting, the best Text + Audio + Gesture (MoE) model reaches Accuracy: 71.5 and Macro-F1: 69.9, compared with 67.9 F1 for Text + Audio and 68.7 F1 for Text + Audio + Gesture (without semantics); the semantic gesture version is reported as significantly better with $p = 0.05$ (Suresh et al., 22 Oct 2025).

The Dungeons & Dragons domain also appears as a knowledge-organization problem. SHADE (Semantic Hypernym Annotator for Domain-specific Entities) is a web-based annotation tool built for Forgotten Realms lore extracted from the Forgotten Realms Fandom Wiki, which the paper describes as having over 47,800 articles as of February 2023. SHADE is designed for domain-specific named entities and assigns semantic hypernyms using two restricted candidate lists derived from the article lead section: internal links and noun phrases. The system stores provenance through a 3-point scale: 1 = from links, 2 = from noun phrases, and 3 = manually typed in. It also distinguishes completed from skipped annotations at the database level, uses a lead-section fallback to the first paragraph under the first section when necessary, and tracks whether labels came from internal links, noun phrases, or manual entry. The paper’s examples, such as Aarakocra requiring avian humanoid rather than merely humanoid, and Tiamat not being reducible to the first linked phrase lawful evil, show that DnD ontology is treated as domain-specific rather than as a simple extension of general-language NER (Peiris et al., 2024).

A third Dungeons & Dragons-centered use is synchronous creative assistance. CALYPSO is described as a system of three LLM-powered interfaces for Dungeon Masters: Encounter Understanding, Focused Brainstorming, and an Open-Domain Chat Baseline. The formative phase involved 7 DMs with 1–39 years of experience. The in-the-wild deployment involved 71 players and DMs on a Discord-based play-by-post living world using Avrae. The paper reports that the improved Abstractive Understanding mode was helpful in 55 of 114 encounters and not helpful in 2, while Focused Brainstorming was used in 71 encounters over 162 rounds of conversation. By contrast, the open-domain interface was used in 51 threads with 2,295 rounds total and an average length of 45 rounds, which the authors interpret as less suitable for synchronous live support. Across these DnD-centered systems, the roleplaying setting is not incidental: it is the substrate for multimodal turn-taking, ontology construction, and real-time co-creative assistance (Zhu et al., 2023).

3. LLM adaptation and adaptive compute

In large-language-model research, DnD and DND name two distinct strategies for modifying model behavior without altering the conventional full fine-tuning paradigm in the usual way.

Drag-and-Drop LLMs (DnD) reframes PEFT as prompt-to-weights generation. Instead of optimizing LoRA parameters separately for each downstream task, DnD maps a small batch of unlabeled task prompts directly to a task-specific LoRA weight update. The system trains on prompt-checkpoint pairs, uses a lightweight text encoder—by default Sentence-BERT (all-MiniLM-L6-v2)—to produce condition embeddings, and then applies a cascaded hyper-convolutional decoder to generate the tokenized LoRA tensors. The reported training setup uses AdamW, learning rate $3\times 10^{-5}$, weight decay 0.1, max grad norm 1.0, 5000 training steps, and small noise augmentation ($10^{-4}$). The paper claims up to 12,000$\times$ lower overhead than full fine-tuning, up to 30% average performance gains over the strongest training LoRAs on unseen common-sense reasoning, math, coding, and multimodal benchmarks, and transfer from 0.5B to 7B backbones. It also reports per-model generation times on one A100 80GB GPU of 0.11 s for common sense, 0.53–0.55 s for math, 0.70–0.73 s for coding, and 0.61 s for multimodal tasks (Liang et al., 19 Jun 2025).

Dynamic Nested Depth (DND) addresses a different bottleneck: uniform token processing inside a transformer. It inserts a router into selected middle layers, scores token criticality, packs tokens above a threshold, reprocesses only those tokens through the same layer, and fuses the nested output with the vanilla output by a normalized gate. The design includes a router controlling loss—combining Score Dispersion Loss and Distribution Preservation Loss—and a threshold control scheme with buffer proportional control and EMA synchronization. In the reported configuration for a 48-layer Qwen3-MoE model, the first 4 and last 4 layers remain unchanged. The method is integrated during a post-training phase into Qwen3-1.7B and Qwen3-30B-A3B, yielding average benchmark gains of 1.88% and 0.87%, respectively. The additional parameter cost is described as roughly 0.03M, and the appendix estimates a total model FLOP overhead of about 6.27% for a 16,384-token sequence with 20% token selection (Chen et al., 13 Oct 2025).

Taken together, these two uses of DnD/DND are related only at the level of design philosophy. Both target post hoc specialization or compute allocation, but one generates LoRA matrices from prompts whereas the other reallocates depth across tokens. This suggests a shared rhetorical use of the acronym for controllable, low-friction model adaptation rather than a shared underlying formalism.

4. Security, delayed activation, and defensive architecture

In adversarial ML, DND appears in two sharply different senses: as a concrete delayed backdoor prototype and as a conceptual defense architecture.

Delayed Backdoor Attacks Based on Nonlinear Decay (DND) is the proof-of-concept system for the broader Delayed Backdoor Attack (DBA) paradigm. Its central claim is that conventional backdoors assume immediate activation, whereas DND makes trigger exposure and malicious behavior temporally decoupled. The system maintains a persistent cumulative state $O$, applies a nonlinear decay schedule

$T(O)=\frac{a}{(O+1)^b},$

and activates only when the current trigger condition is satisfied and the accumulated state aligns with the decay-controlled schedule. The implementation uses a state-tracking module and a nonlinear activation controller; during latency mode it attenuates trigger tokens through the attention mask, while during outbreak mode it injects a logit bias toward a target label $Y^T$. The reported experiments use BERT-base on SST-2, HSOL, Offenseval, and Twitter, a poisoning rate usually 10%, target label $Y^T=1$, and a trigger set of four rare tokens—“cf,” “bb,” “ak,” and “mn”—with trigger combination size $s=2$ and activation threshold 500. Clean accuracy remains high—95.5% on HSOL, 91.9% on SST-2, 84.6% on Offenseval, and 94.2% on Twitter—while ASR$p = 0.05$0 is 99.2%, 98.7%, 99.8%, and 100%, respectively. The paper further reports only slight ASR$p = 0.05$1 drops under ONION, STRIP, RAP, and CUBE, by about 2.3%, 1.9%, 1.4%, and 1.3% on HSOL, and argues that the temporal dimension makes common, everyday words plausible triggers in principle (Ding et al., 12 Mar 2026).

By contrast, Dynamic Neural Defense (DND) is a conceptual AI firewall architecture intended to make AI systems safer against adversarial attacks through three mechanisms: randomness at inference time, LSTM-based detection of suspicious query sequences, and reconstruction of visually similar inputs using a VAE. The paper describes randomized selection of a neural network or computation graph at runtime, an LSTM that analyzes input streams from a source such as an IP address, and a reconstruction pipeline based on AE/VAE components. It also refers to NAS, SSGAN-LSTM, decoy CNNs, and YOLO, but the evaluation is explicitly limited: the paper does not report standard benchmark results, attack success rates, ablations, or detailed datasets, and presents the system chiefly as a roadmap rather than a rigorously validated method (A et al., 2019).

The contrast between these two security uses is substantial. One is a stateful attack with explicit activation dynamics and benchmarked results; the other is a layered defense proposal with minimal empirical substantiation. The shared acronym is therefore potentially misleading unless the surrounding literature is specified.

5. Vision, detection, and interpretability

Computer-vision work uses DnD for at least three independent method families.

Differences in Detection (DnD) is a pairwise, ground-truth-centered comparison framework for object detectors. Starting from the same IoU-based matching algorithm used by mAP, it partitions the ground-truth set into

$p = 0.05$2

where $p = 0.05$3 are labels matched by both models, $p = 0.05$4 and $p = 0.05$5 are labels matched by only one model, and $p = 0.05$6 are labels matched by neither. It then defines unmatched sets per model,

$p = 0.05$7

and exclusive error sets $p = 0.05$8 and $p = 0.05$9. The method is positioned as a complement to mAP and TIDE, especially when combined with TIDE error types in a confusion-matrix analysis, and as a way to guide explainability methods such as ODAM toward metric-relevant examples (Theodoridis et al., 5 Jun 2026).

DnD: Dense Depth Estimation in Crowded Dynamic Indoor Scenes addresses monocular dense depth prediction in environments containing a static background and multiple moving people. The network is a U-Net-based encoder-decoder trained from RGB images and sparse metric depth maps produced by SfM + MVS rather than from dense depth sensors. Its total loss is a weighted combination of five terms:

$3\times 10^{-5}$0

where $3\times 10^{-5}$1 is sparse absolute-scale depth loss, $3\times 10^{-5}$2 is photometric consistency, $3\times 10^{-5}$3 is edge-aware smoothness, $3\times 10^{-5}$4 is a flow-guided shape constraint, and $3\times 10^{-5}$5 is a normal-guided scale constraint. On the NAVERLABS dataset, the paper reports a 3.6% improvement in RMSE for human regions and a 10.2% reduction in RMSE for the entire scene relative to recent baselines; relative to a photometric-only variant, the full model reduces RMSE by 26.4% in the full scene and 32.2% in human regions (Jung et al., 2021).

Describe-and-Dissect (DnD) is a training-free, label-free neuron-interpretation pipeline for deep vision networks. It first augments the probing set with attention crops, then uses BLIP to caption the top-$3\times 10^{-5}$6 activating images for a neuron, GPT-3.5 Turbo to summarize those captions into candidate concepts, and Stable Diffusion to generate synthetic images for each candidate. Candidate labels are then ranked by activation-based and similarity-based scores, with TopK Squared + Image Products used as the main scoring rule. On final-layer automatic evaluation for ResNet-50, DnD reports CLIP cosine similarity 0.7598 vs. 0.7080 for MILAN, mpnet cosine similarity 0.4588 vs. 0.2788, and BERTScore 0.8286 vs. 0.8206. In the AMT study, it is reported as more than 2$3\times 10^{-5}$7 as likely to be selected as the best explanation as the best baseline. The paper also notes a computational cost of about 38.8 seconds per neuron on a Tesla V100 GPU (Bai et al., 2024).

Across these vision papers, DnD names either a structured set-theoretic comparison procedure, a geometric depth-learning framework, or a multimodal explanation pipeline. The commonality is methodological rather than semantic: each use turns an opaque evaluation or representation problem into a more structured intermediate object.

6. Mathematical and materials-science meanings

Outside ML, DND retains older domain-specific meanings with no connection to Dungeons & Dragons or modern model architectures.

In nonlinear PDE theory, DND abbreviates the Dirichlet–Neumann–Dirichlet mixed boundary value problem for a $3\times 10^{-5}$8-Laplacian system. The paper studies the equation

$3\times 10^{-5}$9

on a bounded Lipschitz domain with boundary decomposition $10^{-4}$0, subject to

$10^{-4}$1

Under the hypotheses $10^{-4}$2, $10^{-4}$3, $10^{-4}$4, $10^{-4}$5, $10^{-4}$6 with $10^{-4}$7, and $10^{-4}$8 with $10^{-4}$9, the paper proves that the DND problem has a unique weak solution $\times$0, establishes comparison and monotonicity results relative to the associated DNN problem, shows $\times$1 strongly in $\times$2 as $\times$3, and proves existence and asymptotic convergence results for optimal controls governed by the DND and DNN state equations (Zeng et al., 2023).

In materials science and colloid chemistry, DND commonly means detonation nanodiamond. One molecular-dynamics study investigates ion adsorption on DND surfaces in water and argues that the main organizing principle is Collins’ law of matching water affinity: matched water affinities favor contact ion pairs (CIP), whereas mismatched affinities favor solvent-shared ion pairs (SIP). The simulations use a single cuboctahedral DND in 0.1 M aqueous salt solution with OPLS-AA, SPC/E water, LAMMPS, PPPM electrostatics, and 2 ns NPT equilibration + 2 ns NVT production. The paper reports that Na$\times$4 has the strongest tendency to form CIP with $\times$5 among the monovalent ions studied, whereas Mg$\times$6 mostly forms SIP except in the extreme case of 84 $\times$7 groups on DND–COOH, where a few Mg$\times$8–$\times$9 CIPs are hypothesized to arise from entropy gains. It also reports that Mg$O$0 and, to a lesser extent, Ca$O$1 markedly increase water residence times in the first hydration layer of charged DND–COOH (Saberi-Movahed et al., 2021).

A second nanodiamond paper studies DND seeds during early MWCVD diamond growth. After seeding Si(100) with an initial density of $O$2, the authors observe that 48 h at 700 °C in high vacuum does not change the seed density, whereas 10 min H$O$3 plasma at 700 °C, 600 W, 24.5 Torr removes almost all seeds. The kinetics are modeled through a curvature-dependent chemical potential,

$O$4

which lowers the etching barrier for smaller particles and yields a critical radius $O$5 separating growth from etching. Fitted values are 3.58 nm at 300 W, 0.5% CH$O$6, 2.95 nm at 600 W, 0.5% CH$O$7, 2.67 nm at 800 W, 0.5% CH$O$8, and 2.92 nm at 600 W, 1% CH$O$9. The reported growth coefficients are 0.09, 0.4, 0.95, and 0.4 nm/min for those respective conditions (Salerno et al., 2023).

These non-ML senses are historically stable within their own fields. A plausible implication is that acronym collisions around DnD are now common enough that cross-disciplinary citation and indexing require immediate local definition, especially when ML papers reuse the string for new architectures or datasets.