Claims Browser

KnockGS recovers material scales substantially more accurately than response retrieval, global regression, or fixed default materials across five held-out material targets

"Across five held-out material targets, our method recovers the scales substantially more accurately than response retrieval, global regression, or a fixed default material"

Interaction response carries enough information to calibrate material scales in physically grounded 3D Gaussian representations

"Interaction response therefore carries enough information to calibrate material scales in physically grounded 3D Gaussian representations."

This work represents a first step toward interactive PhysicalGS systems with calibrated Gaussian assets that have consistent rendered appearance and simulated response

"Our study is a first step toward interactive PhysicalGS systems that calibrate a Gaussian asset whose rendered appearance and simulated response are consistent."

Visual storytelling systems struggle to maintain character consistency when later prompts omit identity-related semantics from initial character descriptions

"Although this setting better reflects natural storytelling, later prompts may omit important identity-related semantics, making character consistency more difficult to maintain."

Sidecar improves prompt-image alignment and character consistency across SDXL and FLUX-based models without requiring additional training or architectural modifications

"Experiments on FreeStoryBench show that Sidecar consistently improves prompt-image alignment and character consistency across multiple SDXL- and FLUX-based baselines, with negligible computational overhead."

Single-stage 3D object detectors cannot project features into a common space that is adaptive for all tasks

"it is impossible to project features into a common space that is adaptive for all the tasks"

The proposed TADP method with task-aware deformation head shows good results when applied to other detection methods

"The experimental results demonstrate that the proposed deformation head shows good results on other detection methods"

The TADP method achieves 80.91% car mAP on KITTI dataset, surpassing many state-of-the-art methods

"The experimental results on the KITTI dataset demonstrate that the car mAP is 80.91%, surpassing many state-of-the-art methods on the KITTI benchmark"

Directly concatenating multispectral sequences for molecular structure inference exhibits anomalous performance degradation due to pronounced heterogeneity and multimodal imbalance

"the common paradigm of directly concatenating multispectral sequences can exhibit anomalous performance degradation, primarily due to pronounced heterogeneity and the resulting multimodal imbalance across modalities"

MM-Spectrum's modality-aware routing mechanism that exposes spectral identity to the router better matches information characteristics under multispectral imbalance

"MM-Spectrum introduces an explicit modality-aware routing mechanism that exposes spectral identity to the router in addition to token content representations"

Shared and interaction experts with heterogeneous capacities can extract modality-unique and cross-modal synergistic information while suppressing noise-induced interference

"it incorporates shared and interaction experts, together with heterogeneous expert capacities, to extract multispectral modality-unique and cross-modal synergistic information while suppressing noise-induced interference"

MM-Spectrum achieves consistent and substantial improvements across full-modality, bimodal, and missing-modality settings on molecular structural elucidation

"Across full-modality, bimodal, and missing-modality settings on molecular structural elucidation, MM-Spectrum achieves consistent and substantial improvements, supported by ablation studies and interpretability analyses"

Most state-of-the-art computer vision models perform well on standard benchmarks but often yield suboptimal results in specialized medical imaging tasks due to high levels of noise in the data

"Although computer vision has advanced significantly, most state-of-the-art models perform well on standard benchmarks but often yield suboptimal results in specialized medical imaging tasks due to the high level of noise present in the data."

Current video generation models fail to achieve probabilistic alignment - they cannot reproduce the correct distribution of possible behaviors under the same initial observation and action

"Across 50 scenarios and eleven current systems, no model consistently matches the reference probabilities while recovering the range of valid behaviors."

Video generation models are increasingly being framed as world models rather than just video generators

"Recent video generation models are increasingly framed as world models."

A proper world model should reproduce not just a single plausible trajectory but the full distribution of possible behaviors under the same initial conditions

"a world model should reproduce not only a plausible trajectory, but also the distribution of possible behaviors under the same initial observation and action"

Existing evaluations of video generation models do not test whether repeated generations recover the correct distribution of outcomes

"existing evaluations largely assess individual-video plausibility and do not test whether repeated generations recover the correct distribution"

Language prompts, initial noise sampling, and model training can potentially reshape a model's predictive distribution to improve probabilistic alignment

"we test whether language prompts, initial noise sampling, or model training can reshape the model's predictive distribution"