Claims Browser

Cross-lingual word-to-speech mappings can be learned directly from visual grounding without transcriptions or explicit model training

"Our work demonstrates that cross-lingual word-to-speech mappings can be learned directly from visual grounding without transcriptions or explicit model training."

Alignment-based approach using self-supervised features outperforms attention-based neural models for keyword spotting and localization

"Experiments evaluating keyword spotting and localization show that our alignment-based approach outperforms a previous attention-based neural model."

KinyaEmbed is the first dedicated sentence embedding model for Kinyarwanda

"We present KinyaEmbed, the first dedicated sentence embedding model for Kinyarwanda, a morphologically rich Bantu language spoken by over 12 million people in Rwanda."

Existing multilingual embedding models perform poorly on Kinyarwanda due to severe under-representation in their pre-training corpora

"Existing multilingual embedding models such as LaBSE, mE5-large, and OpenAI text-embedding-3-large perform poorly on Kinyarwanda due to severe under-representation in their pre-training corpora."

KinyaEmbed achieves Spearman correlation of 0.7298 on SemRel2024-rw, surpassing mE5-large by 20.9% and OpenAI text-embedding-3-large by 41.0%

"A seven-checkpoint ensemble (all5+23A*2, with the final stage double-weighted) achieves Spearman \r{ho}=0.7298 on SemRel2024-rw, surpassing mE5-large by 20.9% and OpenAI text-embedding-3-large by 41.0%."

Combining procedural generation with 4D visual dynamics in one environment still demands extensive manual effort and results are rarely editable or controllable enough to reuse at scale

"Combining these properties in one environment, however, still demands extensive manual effort, and the result is rarely editable or controllable enough to reuse at scale."

Vision-language models fail the majority of navigation tasks in 4DSynth-Nav benchmark and stall after early subtasks

"Two vision-language models evaluated across three difficulty tiers both fail the majority of tasks and stall after early subtasks."

Casual captures frequently contain transient objects that can produce blurred, duplicated, or floating artifacts in 3D Gaussian Splatting novel views

"However, such captures frequently contain transient objects that appear in only a subset of the views. Such content can be encoded into the per-view Gaussians associated with the inputs that observe it and remain in the combined representation despite being observed by no other input. As a result, it may produce blurred, duplicated, or floating artifacts in novel views."

AI has democratized conceptual art creation to everyone

AI capabilities have advanced from generating game descriptions and concept art to building actual functional games from image specifications in four years

Runway enabled Chime to produce a national TV spot at 85% cost savings versus traditional production methods

MiniMax-H3 video generation model can run locally on M5 Pro Mac with 115GB model download, taking around 45 minutes to generate

Astra is not a step change beyond Sol

Half of the Astra problems can be solved by Fable, and OpenAI did not have a control group

Astra is impressive but not ASI (Artificial Superintelligence)

DeepSeek-V4-Flash-0731 produces significantly better image generation results when reasoning mode is set to high versus default

There is a real and important difference between mathematical reasoning capabilities and capabilities in other domains

Existing medical image fusion methods lack deep understanding of diagnostic intents and pathological structures by applying uniform fusion rules globally