cider
PulseAugur coverage of cider — every cluster mentioning cider across labs, papers, and developer communities, ranked by signal.
- 2026-05-25 product_launch Mininglamp AI released the Cider SDK to add W8A8 activation quantization to the MLX framework. source
4 day(s) with sentiment data
-
New models tackle remote sensing change captioning with diffusion and directional representations · 2 sources tracked
Two new research papers introduce novel approaches to remote sensing image change captioning. EchoChange utilizes a diffusion language model with a dual-pass remasking strategy to iteratively refine captions, addressing…
-
New CapProbe benchmark evaluates detailed image captions from VLMs
Researchers have introduced CapProbe, a new benchmark designed to rigorously evaluate the detailed captions generated by vision-language models (VLMs). Unlike existing metrics that struggle with factual accuracy and pro…
-
New CIDER dataset aids LLMs in aligning with user privacy preferences
Researchers have introduced CIDER, a new dataset designed to help large language models better align with individual privacy preferences. The dataset contains over 14,000 human annotations across various communication s…
-
Adjudicated Captioning framework boosts zero-shot image captioning performance
Researchers have developed a novel multi-agent framework called Adjudicated Captioning to improve zero-shot image captioning. This inference-time system enhances an existing captioner by adding a stronger retrieval enco…
-
LLMs fail to translate Korean Braille, study finds
A new research paper reveals significant accessibility failures in state-of-the-art Large Language Models (LLMs) when it comes to translating Korean Braille. Despite expectations that these models could handle Braille t…
-
Mininglamp AI adds W8A8 quantization to MLX for faster Apple Silicon inference
Mininglamp AI has developed Cider, a new SDK that enhances the MLX framework by adding W8A8 activation quantization. This optimization significantly speeds up the prefill process for large vision-language models on Appl…
-
New AI model enhances video understanding by linking entities across roles and appearances
Researchers have developed a new method called Multimodal Entity Coreference (MEC) to improve video situation recognition. This approach links textual descriptions of entities with their visual representations across di…