A developer trained a 4-billion-parameter language model using reinforcement learning to rewrite AI-generated text into more human-sounding prose, using AI detectors as reward functions. The project, …
Researchers developed AWARE-FX, an auditable AI/NLP system that converts corporate annual report text into traceable firm-year hedging-disclosure measures, and tested it on 24,909 Hong Kong firm-years…
Liquid AI released two open-weight bidirectional encoders, LFM2.5-Encoder-230M and LFM2.5-Encoder-350M, built on the LFM2 hybrid backbone with an 8,192-token context. The 350M model achieves a 17-task…
Liquid AI released LFM2.5-Encoder-230M and LFM2.5-Encoder-350M, general-purpose bidirectional encoders that match or beat larger models on GLUE, SuperGLUE, and multilingual tasks while running about 3…
Promptforce.ai launched Prefex, a local-first proxy that bundles over a dozen LLM cost-optimization techniques into a single Go binary for Claude Code and OpenAI-compatible APIs, claiming to reduce sp…
A new study from arXiv introduces Symbolic Augmentation, a training-time framework that generates label-preserving augmented data to fix a structural blind spot in neural fact-checkers: their accuracy…
A new study from researchers evaluating large language models as unified multimodal learners for clinical prediction finds that converting all patient data into a single natural language sequence and …
Alibaba-NLP released the gte-reranker-modernbert-base, a ModernBERT-based reranker model under the Apache-2.0 license, designed for RAG and search reranking workflows. The 1.1 GB model is available on…
Researchers at French institutions found that diversity-driven sampling can reduce pre-training dataset size by up to 94% and training time by 73% while maintaining performance in ModernBERT models. I…
Researchers released LOCUS, the largest open database of U.S. local laws, containing codes from 9,239 cities and counties. The corpus aims to fill a gap in machine-readable legal text for AI research,…
The article announces the release of six new Sentence Transformers CrossEncoder reranker models, ranging from 17 million to 1 billion parameters, which are built on Ettin ModernBERT encoders and achie…
IBM has released two new multilingual embedding models under the Apache 2.0 license, built on ModernBERT: a compact 97M-parameter model and a full-size 311M-parameter model. Both support over 200 lang…