Claims Browser

A single Procrustes rotation fitted on parallel sentences can map hidden states between independently trained monolingual models

"a single Procrustes rotation fit on parallel sentences maps hidden states between models"

Rotated cross-lingual representations transfer functional content, as demonstrated by patching rotated English residuals into German models flipping predictions to the donor's answer

"the same rotation transfers functional content; patching a rotated English residual into a German model on a factual cloze flips the prediction to the donor's capital in most cases"

Cross-lingual alignment emerges from the structure of language itself rather than requiring joint training

"cross-lingual alignment can emerge from the structure of language and the information it carries rather than from joint training"

This finding enables practical applications including model stitching, merging, and modular multilingual systems built from monolingual components

"this points to practical future directions including model stitching, merging, and modular multilingual systems built from monolingual components"

AI models can form aesthetic categorization of human-produced media without explicit labels or cross-modal supervision

"What remains under-explored is how AI models form their own aesthetic categorization of human-produced media without explicit labels or cross-modal supervision."

A self-supervised framework can project four modalities into a shared 256-dimensional embedding space and discover aesthetic structure through iterative clustering

"We present a self-supervised framework that projects four modalities (text, audio, image and video) into a shared 256-dimensional embedding space and applies iterative clustering to discover aesthetic structure."

There is divergence between AI-generated cluster assignments and human affective register labels

"We discuss the divergence between AI-generated cluster assignments and human affective register labels on a weakly supervised multimodal dataset."

This approach has applications in understanding AI cross-modal similarity, organizing media collections for RAG, and automated data labeling

"This work has applications in understanding how AI structures cross-modal similarity, organizing heterogeneous media collections for Retrieval-Augmented Generation (RAG), and automated data labeling."

Directed graph learning with nonsymmetric propagation operators can be theoretically certified and controlled using a two-sided cone Rayleigh framework for generalized pencils

"Building on the two-sided cone Rayleigh framework for generalized pencils \[ B_θ-λG, \] we develop a learning-oriented methodology for spectral certification, sensitivity analysis, and control without requiring symmetry, nonnegativity, or cone preservation."

Computable cone bounds provide rigorous spectral enclosure with differentiable soft-min/max surrogates that maintain explicit approximation errors

"computable lower and upper cone bounds provide an a posteriori enclosure of a distinguished cone level, while smooth soft-min/max surrogates preserve rigorous one-sided bounds with explicit approximation errors and remain differentiable with respect to the trainable parameters."

Adaptive spectral control on the directed Cora citation network achieved approximately 21.5% reduction in spectral level under 0.5% edge-weight budget with no loss in test accuracy

"On the directed Cora citation network, adaptive recomputation of the right--left sensitivity reduces the distinguished spectral level by approximately $21.5\%$ under a cumulative edge-weight reduction budget of $0.5\%$, with no observed change in test accuracy for the trained model and data split considered."

Symmetrization of directed graphs can remove predictive information that is carried solely by edge direction

"controlled experiments show that symmetrization can remove predictive information carried solely by edge direction."

Llama-3.2-1B shows better TwinKV improvements on RULER benchmark than Qwen3-4B across all evaluated configurations

"On RULER with Llama-3.2-1B, however, that fourth policy improves in every evaluated cell because its Alone score leaves substantial room to improve."

Existing video-editing methods introduce facial-expression inconsistencies when applied to human-centric live streaming and typically depend on multiple offline inference steps, making them unsuitable for real-time interaction

"directly applying existing video-editing methods to human-centric live streaming remains challenging, as they may introduce facial-expression inconsistencies and typically depend on multiple offline inference steps, making them unsuitable for real-time interaction"

EditaLive delivers state-of-the-art editing performance with faithful preservation of facial expressions and low-latency real-time streaming inference

"Extensive experiments demonstrate that EditaLive delivers state-of-the-art editing performance with faithful preservation of facial expressions and low-latency real-time streaming inference"

A pretrained image animation model that naturally decouples appearance from motion can be repurposed as a base model for instruction-based human-centric video editing

"we start from a pretrained image animation model (Wan-Animate), which naturally decouples appearance from motion, and repurpose it as the base model for instruction-based human-centric video editing by reference frame editing and video reconstruction via the collected CharEdit-50K dataset"

An aligned self-rollout distillation strategy can compress a video editing model into a two-step sampler while reducing training-inference discrepancies and mitigating appearance drift

"design an aligned self-rollout distillation strategy that compresses the model into a two-step sampler, where fixed RoPE and align forcing reduce training--inference discrepancies, and first-frame preserved sparse attention filters redundant historical information to mitigate appearance drift"

Modern deep learning-based CSI predictors often provide only point predictions and lack calibrated uncertainty estimates

"Modern deep learning-based CSI predictors, however, often provide only point predictions and lack calibrated uncertainty estimates."