AI Research

Cutting-edge AI research papers, breakthroughs, and academic developments.

1153 articles · page 48

Latest

Google's Gemma Gets a LoRA Tune-Up: Fine-Tune a 2B Model Free on Colab

Matryoshka embeddings shrink AI search costs without killing accuracy

Google's Gemma 7B matches Mistral on benchmarks as open model race tightens

Upstage's Korean LLM leaderboard hits 1,000 models in five months

PEFT Adds LoRA Merging on the Fly, No Checkpoint Download Needed

Fine-tune with Mixtral: $2.70 beats GPT-4's $3,061 price tag

AMD and Hugging Face Team Up to Kill GPU Code Headaches

Hugging Face TGI 1.4 brings OpenAI API drop-in replacement for open LLMs

SegMoE packs 4 Stable Diffusion models into one pipeline — and prompt accuracy jumps

NPHardEval's 900-Question Gauntlet Exposes GPT-4 Turbo's Reasoning Limits

Hugging Face Releases Recipe for Self-Aligning Open LLMs Without Human Labels

Hugging Face TGI hits AWS Inferentia2, cutting GPU dependence for LLM deployments

PatchTST hits Hugging Face: IBM's 64-word time series trick goes zero-shot

New LLM leaderboard tests models on finance, legal work, and customer support

Intel Xeon CPUs hit 7x faster StarCoder inference via INT8 quantization

New leaderboard ranks which LLMs hallucinate least — and the results sting

DecodingTrust Goes Public: A Free Safety Leaderboard for Testing Any LLM

Hugging Face deepens Google Cloud pact to push open models on Vertex, TPUs

Mixtral beats GPT-3.5 as an agent — Hugging Face releases smolagents

IBM's PatchTSMixer beats transformers by 60% and lands on Hugging Face

Wav2Vec2-BERT crushes Whisper on Mongolian ASR, 10x faster

DPO vs IPO vs KTO: Hugging Face's hyperparameter sweep crowns a winner

ONNX Runtime boosts SDXL Turbo image generation by 229% over PyTorch

Turn Any ComfyUI Workflow Into a Free Web App With This Trick