Claims Browser

It has no emotion

"It has no emotion"

It's just for experiments

"It's just for experiments"

It's only good for memes

"It's only good for memes"

It has no soul

"It has no soul"

It's slop

"It's slop"

It's just a research demo

"It's just a research demo"

Runway's generation capabilities are sufficiently advanced that they can challenge users to a HORSE-style competition

"All you have to do is beat us at HORSE. Respond with your best generation."

Once computational overhead is removed, video becomes a viable and in several respects preferable substrate for general-purpose visual pretraining

"These results indicate that, once its computational overhead is removed, video becomes a viable and in several respects preferable substrate for general-purpose visual pretraining."

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."

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"

Visual text error correction requires profound understanding of the interplay between visual text and its surrounding visual context

"which requires a profound understanding of the interplay between visual text and its surrounding visual context"

Explicit acoustic evidence aggregation through an Audio Twin framework provides a more controllable interface for diagnosing and improving speech-grounded reasoning

"explicit acoustic evidence aggregation provides a more controllable interface for diagnosing and improving speech-grounded reasoning"

Transcript-based shortcuts represent an important failure mode in spoken dialogue understanding that current models struggle with

"These results identify transcript-based shortcuts as an important failure mode in spoken dialogue understanding"

The efficiency-calibration patterns observed are robust across different pretrained initializations but do not demonstrate external clinical generalizability

"Similar efficiency-calibration patterns were observed using the public VoCo checkpoint, supporting robustness across pretrained initializations rather than external clinical generalizability"

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"

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."

The remaining bottlenecks in cross-cultural meme transcreation lie in humor reconstruction and image-text alignment rather than simple cultural knowledge gaps

"Our error analysis suggests that the remaining bottlenecks lie in humor reconstruction and image-text alignment rather than simple cultural knowledge gaps, pointing to future work on humor transfer"

Contrastive instability (the conditional rate at which a model fails to resolve all statements within a triplet) can isolate fragmented reasoning from complete failure in multimodal models

"We define contrastive instability as the conditional rate at which a model fails to resolve all statements within a triplet, isolating fragmented reasoning from complete failure"