Claims Browser

Reliable evaluation of vision-language models requires calibrated confidence, particularly under realistic clinical conditions

"Reliable evaluation of vision-language models (VLMs) and medical vision-language models (Medical-VLMs) requires calibrated confidence, particularly under realistic clinical conditions"

Multi-Class Margin (MCM) regularization achieves lowest Expected Calibration Error on 10 out of 12 in-domain settings and remains competitive under domain shifts

"Multi-Class Margin (MCM) regularization, which achieves lowest ECE on 10 out of 12 settings in in-domain and remains competitive under domain shifts"

MVC-Bench provides a structured evaluation framework and actionable guidance for improving calibration in safety-critical medical workflows

"MVC-Bench provides a structured evaluation framework and actionable guidance for improving calibration in safety-critical medical workflows"

Gemini 3.5 Transcribe provides more intelligent speech-to-text transcription capabilities

"you can get more intelligent speech-to-text transcription with Gemini 3.5 Transcribe"

Large multilingual foundation models like Whisper can be successfully adapted to extremely low-resource indigenous languages with very limited training data

"multilingual foundation models can be successfully adapted to extremely low-resource indigenous languages"

ASR technologies have achieved remarkable performance in recent years through large multilingual foundation models

"Automatic Speech Recognition (ASR) technologies have achieved remarkable performance in recent years through the use of large multilingual foundation models"

Fine-tuned Whisper Small model achieved 37.5% WER and 7.45% CER on Baniwa language with only 0.54 hours of training speech

"The best model achieved a WER of 37.5% and a CER of 7.45%, demonstrating that multilingual foundation models can be successfully adapted to extremely low-resource indigenous languages"

Most ASR advances remain concentrated on high-resource languages while indigenous languages lack speech resources and language technologies

"most advances remain concentrated on high-resource languages, while indigenous languages continue to suffer from a lack of speech resources and language technologies"

Deepgram's Flux TTS can respond in as low as 80ms for live conversation with context and interruption handling

"Deepgram just dropped Flux TTS, text-to-speech built for live conversation. It responds in as low as 80ms, carries context across turns, and handles interruptions natively."

GPT-Live enables continuous voice interaction with AI using a turnless speech model

"GPT-Live enables continuous voice interaction with AI, using a turnless speech model"

GPT-Live uses low-latency architecture for faster, more natural conversations

"low-latency architecture for faster, more natural conversations"

Google DeepMind has developed a breakthrough sign-language-to-text model called SL2T

"Introducing sign-language-to-text (SL2T), our breakthrough model powering new sign language features for Deaf and hard of hearing users."

The SL2T model enables new sign language features for Deaf and hard of hearing users

"our breakthrough model powering new sign language features for Deaf and hard of hearing users"

Better training objectives can improve controllability in image generation

"We explore why better training objectives can improve controllability, how separating scene planning from rendering may lead to more reliable image generation"

Qwen 3.7 27B running as a 17GB GGUF on an M5 Max MacBook Pro produces the best quality pelican riding a bicycle image compared to other models that run locally on laptops

"The new Qwen 3.7 27B, running as a 17GB GGUF in LM Studio on my M5 Max MacBook Pro, just drew me the best pelican riding a bicycle I've seen from any model that runs on my laptop"

Previous experiments with models adjusting output after seeing rendered images were disappointing, but warrant re-testing with more recent models

"I experimented last year with letting the models adjust after seeing a rendered image and it was a bit disappointing, but it's about time I gave that another go with more recent models"

Codex + GPT-5.6 Sol Ultra better understood the 'heist' and 'team' aspects of a game creation prompt compared to another model

"I had Codex + GPT-5.6 Sol Ultra try the same prompt and the result was a better game - it understood the "heist" and "team" aspects better, you have to rescue your two raccoon crewmates and then stack on top of each other to steal the Golden Sardine from a museum"

TabuLM is the first language model pre-trained on Kinyarwanda tabular data

"We present TabuLM, the first language model pre-trained on Kinyarwanda tabular data."