PyTorchKR Papers

최신 논문

총 523,801편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2611.03430v1cs.CV

Evaluating Depth-Augmented Visual Features for Cross-Dataset Lunar Traversability Estimation

Autonomous mobility is essential for sustained lunar surface operations, as communication delays and line-of-sight occlusions limit continuous teleoperation. Although recent traversability estimation methods increasingly rely on deep learning, the domain gap between terrestrial analogue environments and real lunar terrain can limit their generalisation, and real lunar traversability labels are scarce, making fully supervised training difficult. To address these challenges, we build a weakly supervised framework trained on sparse pairwise annotations and study whether augmenting visual features with depth-derived geometric information: depth, surface normals, and combined geometric descriptors. We evaluate the models in both in-domain and cross-domain settings using two terrestrial analogue datasets and the real lunar Chang'E PCAM dataset. Contrary to expectations, we find that naive geometric augmentation yields no consistent improvement over a strong visual-only baseline in either setting, with effects small relative to seed-to-seed variance. Instead, the choice of training source emerges as the dominant factor in transfer quality: models trained on domain-relevant sources transfer substantially better to real lunar imagery than the geometric fusion strategy improves any single model. Our evaluation runs onboard a resource-constrained edge device and provides a controlled baseline for designing more expressive multimodal fusion architectures in future lunar perception systems.

arXiv:2611.03424v1cs.CL

IdeaTaste: Do LLMs Share the Research Taste of Human Researchers?

Research taste, the judgment of what to read, which problems to pursue, and which methods to try, increasingly shapes the work of AI scientists, yet it remains far less understood than their ability to execute research. We introduce IdeaTaste, a benchmark that scores an LLM by how closely the research proposals it writes from a literature snapshot frozen at 2025 match the work the same communities published in 2026. Our experiments span six contemporary language models and four research areas from established to emerging fields, covering more than 90{,}000 proposals in total. LLM agents fall well short of human communities in both the literature they cite and the ideas they state, reaching about 26\% of the human level on citation matching and only 18\% on idea matching. Their populations can cite as diversely as a community and take up its tasks and methods, yet rarely arrive at the concrete approaches and research plans it pursues. Neither richer field context nor larger populations substantially close this gap. In blinded expert review, AI proposals trail the 2026 papers least in presentation and most in expected success, echoing their gap in concrete approaches, and those whose ideas no human paper shares fare worst, suggesting weaker directions rather than overlooked opportunities. These results indicate that the main bottleneck in AI research taste lies less in finding the directions a community works on than in turning them into the concrete approaches it goes on to pursue. We release IdeaTaste as an open, continuously updated leaderboard (https://cxcscmu.github.io/IdeaTaste) that benchmarks contemporary AI proposals against future publication cycles.

arXiv:2611.03421v1cs.CV

Circumventing Magnitude Collapse via Modular Two-Stage Open-Set Recognition

Open-set recognition (OSR) requires neural networks to classify known classes while rejecting unknown samples, which is critical for real-world deployment. So far, OSR research studied and developed representation learning and postprocessing methods independently and their interactions remain unexplored. In this paper, we reconsider OSR as a modular two-stage pipeline and present the first systematic study of interactions between representation learning and postprocessing methods across dataset scales and usage of known unknown data. First, we discover a failure mode we term \emph{magnitude collapse}, where representation learning methods that utilize known unknown data can suffer performance degradation at large scale and irreversibly destroy discriminative information, despite excelling at small scale. Second, we study the modular interactions and reveal when they can be leveraged for modular performance gains via two-stage processing and where interaction effects amplify performance degradation due to magnitude collapse. Third, we show how these findings can be used to achieve state-of-the-art performance with a simple $K+1$ class classifier baseline and magnitude-aware postprocessing while circumventing magnitude collapse. Finally, our results demonstrate that small-scale evaluations with known unknown data are not predictive of large-scale performance, invalidating current best practices in OSR research. Code available at https://github.com/TwoDigitsOneNumber/Two-Stage-OSR.

arXiv:2611.03420v1cs.LG

Temporal Island Sparse Autoencoders for Interpreting Clinical Time-Series Models

Deep learning models for electronic health records achieve strong predictive performance but provide little insight into what clinical concepts they represent internally. Post-hoc attribution methods produce per-cell importance scores that lack temporal coherence, cross-variable structure, and reusability across patients. We introduce the Temporal Island Sparse Autoencoder (TI-SAE), which learns a backbone-specific, patient-shared clinical concept dictionary from a frozen predictive model's representations. Each dictionary entry (latent) is defined by learned temporal Gaussian islands (specifying when the concept is active) and a sparse variable-composition vector (specifying which variables are involved). A decoupled selector then identifies which dictionary entries drive each patient's prediction, separating representation learning from attribution. We evaluate TI-SAE across five backbone architectures spanning different representation strategies on MIMIC-III and MIMIC-IV (three prediction tasks each). TI-SAE produces structured clinical concepts that go beyond transient attribution heatmaps while achieving strong performance on standard faithfulness benchmarks.

arXiv:2611.03414v1cs.LG

Finite-Memory Control of POMDPs: Fundamental Limits and Efficient Design

Optimal control of partially observable Markov decision processes (POMDPs), in general, requires a complete history. The belief state, a distribution over hidden states, summarizes this history and provides the classical sufficient statistic to control POMDPs. However, the continuous nature of the belief space generally prevents a finite-memory controller from maintaining it exactly. This raises the question we address in this work: what must the available finite memory preserve to achieve near-optimal control performance? We study this question through an information-theoretic converse that gives a fundamental lower bound on the loss of any finite-memory controller. The analysis introduces the concept of a decision witness that characterizes belief states whose confusion would lead to unavoidable loss. Motivated by this bound, we propose RECAP, a constructive quantization method for designing representative memory states. We prove an upper bound on the optimality gap of any RECAP codebook and use the components of this bound together with the converse analysis to define the codebook objective. Experiments on 11 POMDP benchmarks demonstrate that RECAP improves over finite-memory representation baselines under the same memory budget.

arXiv:2611.03411v1cs.LG

Low-Rank Clebsch--Gordan Coupling for Equivariant Spherical Forecasting

Spherical-harmonic neural operators provide an efficient representation for global forecasting, but their discretized pointwise nonlinearities can break rotational equivariance through aliasing. Clebsch-Gordan (CG) tensor products provide exactly equivariant interactions between spherical-harmonic representations, but their computational cost grows rapidly with spectral bandwidth and has limited their use at forecasting scale. We introduce LCG-SFNO, which combines low-rank CG interactions within a controlled low-degree band with coefficient-space residual propagation and an exactly projected quadratic nonlinearity, preserving SO(3) equivariance throughout the learned operator. To make the CG interaction practical, we further develop SSHCG, a sparse GPU implementation with a factorized alternative for wider coupled bands. On spherical shallow-water dynamics and the ERA5-based WeatherBench benchmark, LCG-SFNO reduces rotational error to numerical precision (more than three orders of magnitude below SFNO on shallow water and five orders of magnitude below it on WeatherBench), while matching SFNO on shallow-water forecasting and substantially improving forecast skill relative to SFNO on WeatherBench. Matched ablations show that CG coupling accelerates convergence, while SSHCG keeps the coupling to about 10 percent of a training step at the operating bandwidth, making exact equivariant coupling practical at forecasting scale.

arXiv:2611.03404v1cs.CV

VidDub: Replacement-Aware Distillation for Two-Step Video Dubbing

Video dubbing aims to synthesize lip movements that match target speech while preserving the speaker identity, head pose, and background of a source video. Existing editors are predominantly trained via self-reconstruction under original paired audio, even though the source mouth becomes a conflicting target when driving speech is replaced. We introduce replacement-aware cross-audio supervision: paired-audio samples use full-frame reconstruction, whereas unpaired replacement-audio samples mask out source-mouth reconstruction losses and supervise the mouth solely through audio-visual synchronization while preserving unmasked facial regions and background. Because offline dubbing provides the complete source video and target speech beforehand, we present VidDub, a full-context diffusion editor distilled into two denoising steps (2 NFE). Our replacement-aware teacher first learns accurate lip synchronization without regressing toward conflicting source mouth movements. Matched trajectory regression then transfers the teacher's CFG-guided trajectories to a two-step student, and distribution matching distillation recovers visual quality after step compression. We will release the curated training dataset, VidDub-Bench, fixed paired- and cross-audio evaluation manifests, preprocessing outputs, and unified evaluation code. Across three training seeds, masking out conflicting source-mouth reconstruction improves cross-audio Sync-C by 0.833; the final two-step model combines strong lip synchronization with superior visual quality, identity preservation, and visual speech recognition across four benchmarks.

arXiv:2611.03399v1cs.CV

Image Guided Depth Upsampling using Anisotropic Total Generalized Variation

In this work we present a novel method for the challenging problem of depth image upsampling. Modern depth cameras such as Kinect or Time of Flight cameras deliver dense, high quality depth measurements but are limited in their lateral resolution. To overcome this limitation we formulate a convex optimization problem using higher order regularization for depth image upsampling. In this optimization an anisotropic diffusion tensor, calculated from a high resolution intensity image, is used to guide the upsampling. We derive a numerical algorithm based on a primaldual formulation that is efficiently parallelized and runs at multiple frames per second. We show that this novel upsampling clearly outperforms state of the art approaches in terms of speed and accuracy on the widely used Middlebury 2007 datasets. Furthermore, we introduce novel datasets with highly accurate groundtruth, which, for the first time, enable to benchmark depth upsampling methods using real sensor data.

arXiv:2611.03394v1cs.CV

TaoMate-HD: Progressive-Resolution Autoregressive Audio-Video Generation

Streaming digital humans produce detailed video while continuing speech as new text arrives. High-resolution denoising is costly, and text updates can cause repeated or interrupted speech. We present TaoMate-HD, an autoregressive model for high-resolution audio-video streaming. For each short segment, or chunk, two denoising steps establish coarse video structure at low resolution. A final step refines the video to high resolution, with audio generated throughout the same trajectory. Each stage passes its audiovisual predictions to the same stage of the next chunk as history. Across text updates, the model retains this history to infer what has already been spoken. Continuation training utilizes asymmetric text conditioning, with separate text windows for generation and distillation. Experiments show a 1.6x speedup over direct high-resolution generation with the same model and hardware. Optimized stage-parallel deployment provides a further 1.9x overall speedup over serial progressive generation. Our continuation training reduces character error rate by 11.18 percentage points relative to the baseline. The model also supports hour-long audiovisual generation. Our project page is https://taoliveaigc.github.io/TaoMate-HD.

arXiv:2611.03390v1cs.CV

Progressive Multi-Scale Super-Resolution via Cascaded Bicubic Anchors and Inter-Scale Mutual Refinement

Super-resolution networks are trained for one magnification factor, so several output resolutions require several models. We propose PMS-SR, a progressive single-input multiple-output network that produces x2, x4, and x8 results in one forward pass, with a Transformer backbone on the low-resolution grid. In Stage 1, each scale is predicted as a residual over the detached bicubic upsampling of the previous scale's prediction. With Dirac and zero initialization, training starts exactly from the bicubic cascade, and each head adds only the band the previous scale lacks. In Stage 2, inter-scale mutual refinement couples the scales in both directions through space-to-depth feedback, deformable alignment, and per-pixel fusion, so x8 features refine the x2 output. Trained on DF2K, the 7.95M-parameter model achieves a higher PSNR than every compared multi-scale method at x4 and x8 on all five standard benchmarks. At x8, it outperforms the x8-specific DRN-L on all of them, leads all compared methods on Urban100, and is within 0.13 dB of the best result elsewhere. Against three single-scale SwinIR-M models, PMS-SR uses 22% of the parameters, runs 2.9x faster on BSD100 inputs, and its outputs agree 6.7-12.4 dB more closely. Code and pretrained models will be released at https://github.com/julian135707/PMS-SR upon acceptance.

arXiv:2611.03388v1cs.AI

LAND: Learning an Adaptive Number of Draws for Bayesian Best-of-N Selection

Best-of-N decoding improves generation quality by sampling multiple candidates and selecting the best, but it allocates equal compute to sources regardless of how much they benefit from additional sampling: the expected benefit is small for sources with low-variance score distributions and potentially much larger for those with high-variance distributions. To address this shortcoming, we propose LAND (Learning an Adaptive Number of Draws), which dynamically allocates samples according to their posterior-predictive marginal value. LAND learns a discrete empirical mixture of source-conditioned score distributions from calibration data, updates its belief about a source as completion scores are observed, and stops sampling when the expected improvement of another draw falls below a shared compute price. Across machine-translation experiments with multiple models and language pairs, LAND achieves better MetricX scores than fixed best-of-N at matched average compute. Conversely, at matched translation quality, LAND requires approximately 20-40% fewer candidate generations. Adaptive allocation therefore provides a simple way to retain the benefits of best-of-N while substantially improving its compute efficiency.

arXiv:2611.03384v1cs.AI

Can We Stop the Backtest Yet? Anytime-Valid Promotion Tests for Adaptive Financial Research Agents

Financial research agents can generate and monitor trading rules faster than a human can document the resulting selection process. Candidates appear at data-dependent times, weak rules are abandoned, and promising ones are watched until they cross a reporting threshold. We introduce PROMOTE, a protocol that assigns every candidate predictable testing wealth at birth and accumulates a cost-aware e-process only from subsequent returns. If lifetime allocations sum to at most one, a weighted Ville argument bounds the probability of ever promoting a rule whose declared bounded net score has always had nonpositive conditional mean. The result permits dependent candidates, adaptive births, and indefinite monitoring. We audit the implementation in two settings. A retrospective pseudo-out-of-sample replay contains 24 panel--rule hypotheses, 3,000 shared-sign null paths, injected alternatives, and public ETF and industry data. Repeated unadjusted tests produce a family crossing in 94.5% of null paths, versus 0.0% for PROMOTE; at a 15-bp aligned ETF-component perturbation, PROMOTE has 70.1% target power and median crossing session 2,327. A separate exact mean-zero experiment lets an agent select candidate identities and birth times from past scores; the funded gate has 1.77% false-family crossings across 3,000 programs. The market replay produces zero promotions after costs. The certificate controls historical false promotion under the declared null; it is not a certificate that an earlier edge remains profitable at deployment. AI-use disclosure. Generative AI tools, including OpenAI Codex, assisted manuscript preparation. For this preprint version, Codex assisted with LaTeX editing, author and venue metadata, compilation, and layout checks.

arXiv:2611.03382v1cs.CV

ASCoR: Asymmetric Semantic-Spatial Learning for Remote Sensing Domain Generalization

Source-only domain generalization (DG) for remote sensing semantic segmentation seeks reliable predictions in unseen domains without target-domain data during training. Although vision foundation models offer transferable knowledge, category recognition remains sensitive to source-specific visual cues, while task-specific adaptation may weaken pretrained transferability. We propose ASCoR, an asymmetric semantic-spatial framework built on SAM3. Its text-conditioned semantic branch uses class-name prompts to provide explicit category guidance. Probe-Once Dynamic Adaptive LoRA distributes a fixed adaptation budget across encoder blocks to limit source-specific specialization. A complementary task-specific dense branch learns multi-scale spatial representations using a separate frozen SAM3 image encoder. A lightweight reliability router integrates the two branches through bounded spatial correction based on local prediction reliability. All components are trained using source-domain supervision only. Experiments on the ISPRS, LoveDA, and OpenEarthMap benchmarks cover nine cross-domain transfers. ASCoR achieves a state-of-the-art mean IoU of 68.61% across six ISPRS transfers, outperforming the previous best method by 2.69 percentage points. It also achieves the best results on all three LoveDA/OpenEarthMap transfers, with 59.07%, 47.95%, and 49.38% mIoU on Rural-to-Urban, Urban-to-Rural, and Urban-to-OpenEarthMap, respectively. Ablation studies, feature visualizations, and spatial reliability analyses support the effectiveness and complementarity of the proposed components. Code: https://github.com/WangZitong42/ASCoR.

arXiv:2611.03381v1cs.LG

A Geometry-Informed Neural Operator surrogate of LISFLOOD-FP for rapid pluvial-fluvial flood forecasting: the case of Forl\`i, Italy

Physically based two-dimensional hydraulic models are too slow for real-time inundation forecasting and large ensembles. We present a time-dependent geometry-informed neural operator (GINO) surrogate of LISFLOOD-FP for the municipality of Forl\`i (Italy), severely affected by the May 2023 Emilia-Romagna floods. The surrogate is designed for an operational setting in which only river stage gauges and rain gauges are available. A reproducible pipeline turns public regional observations into a physically based training set: each river inflow is driven by the first stage gauge downstream of it through a calibrated water-surface boundary condition, and rain enters as SCS-CN effective rainfall. The surrogate is an autoregressive GINO trained on 216 simulations of 24 observed events with scaled forcing. It predicts volume-conserving polygon-mean depths on an exposure-based Voronoi mesh of 659 nodes, with a 20 min step over 72 h. The surrogate is tested on 38 independent observed events that it never saw during training. On these events it reaches a critical success index (CSI) of 0.934 at 0.05m and 0.844 at 0.3 m, a depth RMSE of 0.008m and an $R^2$ of 0.984 for maximum-depth maps. On one NVIDIA A10G GPU a 72-h forecast takes 1.7 s instead of 55 s with LISFLOOD-FP, and a 50-member ensemble, computed in a single batched rollout, takes 6.2 s instead of about 46 min, which makes probabilistic flood forecasting practical. These results show that neural-operator surrogates can deliver accurate pluvial-fluvial flood forecasts driven by river stage for operational early warning.

arXiv:2611.03379v1cs.LG

RangeFinder: Predicting Ligand Property Ranges from Protein Pockets

Identifying ligands for a protein target requires searching a vast chemical space for a comparatively small set of compatible molecules. Existing machine learning approaches primarily address this problem by generating candidate ligands or scoring individual protein-ligand pairs, but provide limited information about the broader chemical space compatible with a binding pocket. We introduce RangeFinder, an SE(3)-equivariant transformer pocket-level model, trained and evaluated on BioLiP2 data, that predicts ranges over nine physicochemical ligand properties directly from pocket structure, chemistry, and evolutionary context. Using an intersection-over-union objective and evaluation metric (range-IoU), RangeFinder achieves a range-IoU of $0.464 \pm 0.002$, outperforming all deployable baselines while requiring only $12.2$ ms per pocket. We also quantify our method's ability to reduce the ligand search space while retaining compatible binders; in this regard, RangeFinder achieves a Reduction-Recall F-Score of $0.543 \pm 0.011$ --- once again outperforming all deployable baselines. Ablation experiments indicate that RangeFinder's performance depends more strongly on the density and quality of ligand supervision than on any individual input modality or specialized training strategy. Together, these results position RangeFinder as an inexpensive and effective molecular filtering prior, with demonstrated potential in narrowing the ligand search space of target pockets before docking, generation, or synthesis. The code for this project can be found at: https://github.com/alannadels/RangeFinder.

arXiv:2611.03377v1cs.AI

Same Outputs, Different Scores: Auditing the Unchecked Graders of Multimodal LLM Benchmarks

Every multimodal-LLM multiple-choice benchmark ends with a scoring rule that converts a model's response, often free-form text rather than a clean option letter, into a right/wrong verdict, buried in its code. Unlike the dataset, this rule is chosen without justification and left unexamined, yet it sets the published number. We reproduce the official scorers of eight peer-reviewed benchmarks on five open vision-language models (VLMs) that fit a single 16 GB GPU, and introduce a blinded human-plus-LLM-judge adjudication (Cohen's kappa=0.956) that recovers what the model actually answered. The scoring rule alone moves accuracy by up to 22 points on identical outputs, yet exactly 0 wherever a model emits clean option letters, so it hides on strong-model leaderboards. It is the fallback and not the rambling that does the damage: the benchmark with the highest non-compliance we measure has an artifact of exactly zero, because its scorer abstains instead of guessing; a reasoning model with non-compliance 0.000 still swings 9.5 points with which regex match of its trace the parser keeps. No standard rule is reliable: snapping a non-answer to its closest option credits answers never given yet buries correct ones, abstention discards answers stated in words, and likelihood scoring follows answer-token priors, so a single grade conflates capability with luck rather than measuring either. We release all code, labels, and the protocol, and argue benchmarks should report a non-compliance rate and at least two rules, not one unexamined grade.

arXiv:2611.03376v1cs.AI

Mixed-Methods Exploration of Sociotechnical Factors to Improve Adoption of Crime-Reporting Apps in Urban Communities

Crime-reporting mobile applications can enhance community safety and engagement in urban areas, yet their adoption remains low, partly because developers prioritize technological features over residents' social realities. This study used an exploratory sequential mixed-methods design to identify and validate the sociotechnical factors that drive adoption. Two focus groups and an analysis of 660 app reviews revealed that users' initial sense of usefulness fades, whereas sustained engagement depends on perceived value (PV), comprising six dimensions: safety, anonymity, recency, autonomy, camaraderie, and accessibility. A survey of 505 urban residents, analyzed with PLS-SEM, validated PV as a formative higher-order construct formed by four of these dimensions (safety, anonymity, autonomy, and camaraderie). PV was the strongest predictor of behavioral intention, ahead of effort expectancy, facilitating conditions, and performance expectancy, and behavioral intention strongly predicted actual use. The model explained 75% of the variance in behavioral intention and 51% in actual use. The findings offer design principles for community-centered crime-reporting technologies.

arXiv:2611.03374v1cs.LG

Characterizing When Language Models Take Harmful Actions to Protect Their Assigned Goals

Recent language model (LM) safety failures have largely been studied as disparate phenomena. In agentic misalignment, a model blackmails an executive to avoid being replaced. In alignment faking, it complies with harmful requests during training to keep its values from being modified. We argue that these behaviours share a common decision structure: a model assigned a goal must either take a harmful action to preserve it or refuse and lose it. We formalize this as a goal-harm conflict and present the same conflict under various elicitation protocols that range from compact forced-choice prompts to simulated agentic environments. These protocols span two perspectives on LM decision-making, which we term (i) the logit view, reading preferences from answer-token probabilities, and (ii) the sampling view, classifying open-ended responses with an LM judge. Under the logit view, we show that goal importance and harm severity additively shape how a model resolves these value conflicts. Under the sampling view, we derive two factorizations of the harmful-action probability that safety evaluations commonly report. The first measures how well a preference read from answer tokens carries over into behaviour, such as making a harmful tool call. The second attributes a low harmful-action rate either to refusal or to responses that reach no resolution. We then show how fictional context changes a model's preference under the logit view, and how tool use and partial observability -- two features of agentic evaluations -- change its harmful-action rate under the sampling view. Our work offers a descriptive framework for studying how LMs resolve such value conflicts and for estimating low-probability harmful actions at a finer granularity than the aggregate harm rates commonly reported in safety evaluations.

arXiv:2611.03371v1cs.CV

EO-Jev: Decision Model for Earth Observation

Earth observation (EO) workflows require selecting among known outcomes, estimating confidence, and processing large volumes of imagery. Generative vision-language models can address these tasks, but autoregressive decoding is computationally costly and their confidence estimates are unreliable. Decision models offer an alternative, returning probabilities over candidate answers in a single forward pass. However, their accuracy, calibration, and transfer across EO tasks remain insufficiently understood. We investigate these properties through a diagnostic study of d3-flash (8.4B parameters) across 30 settings from 23 public EO benchmarks. We find that compositional reasoning transfers well and calibration improves over its Qwen3.5-9B backbone on 24 settings, while counting, change quantification, damage grading, and absent-object recognition remain challenging. To address these limitations, we adapt d3-flash through low-rank fine-tuning on public EO training splits, producing EO-Jev. EO-Jev improves significantly over d3-flash on 26 of 30 settings and matches or exceeds specialist references on 20 of 28. It also achieves an average gain of 8.0 points across 12 held-out settings and lower expected calibration error than specialists on 21 of 28 settings. These improvements come at a modest cost of 1.8 points in general decision performance. Our results demonstrate the potential of adapting general decision models into competitive EO generalists while highlighting persistent challenges in quantitative perception, option-order consistency, and calibration under distribution shift.

arXiv:2611.03370v1cs.CV

Fuse To Align: Multimodal Representation Learning for Retrieval via Hypergraph Regularization

Multimodal retrieval must integrate complementary evidence from views that may be missing, noisy, or unequally informative. When a sample provides limited reliable evidence, learning from its views alone can hinder the acquisition of useful retrieval representations. Semantically related training samples may provide complementary observations, yet existing volume-based objectives jointly align modalities within each sample without explicitly enabling information exchange across samples. We therefore propose a training-time hypergraph fusion framework that connects observed modalities both within samples and across semantically related samples, allowing representation learning to draw on evidence beyond an individual sample while leaving the retrieval pipeline unchanged at inference. The framework includes HyVol as a special case and introduces two configurations: wHyVol learns view contribution weights and symmetric semantic affinities, whereas wRHG additionally models typed interactions and participant roles through relational propagation. Missing modalities are omitted rather than imputed, and the hypergraph is discarded after training, incurring no additional inference cost. Experiments on eleven zero-shot video-text and audio-text retrieval benchmarks demonstrate broad improvements with both GRAM and HyperGRAM. Across 17 video benchmark-modality settings evaluated in both retrieval directions, wRHG outperforms GRAM in all 34 comparisons and HyperGRAM in 33 of 34. Mean text-to-video R@1 increases from 63.4 to 68.2 with GRAM and from 64.8 to 68.4 with HyperGRAM, while the largest video-to-text gain reaches 13.3 percentage points on ActivityNet. Under missing-modality evaluation, both weighted configurations retain positive text-to-video gains over GRAM across seven benchmarks at every evaluated missingness rate, even when 90% of clips lack one modality.