Papers arxiv:2605.12411 Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling Published on May 12 Submitted by Eilam Shapira on May 14 Technion Israel institute of technology…
…robust Korean AI development. Generated by Qwen/Qwen2.5-Coder-32B-Instruct Frontier model evaluations are shifting from foundational capabilities (e.g., instruction following and reasoning) toward compositional, agentic ones, but Korean…
…Recasting Pretrained LLMs into Looped Latent Refinement Models Published on May 10 Submitted by TaekHyunPark on May 13 BIGDATA ANALYTICS ENGINEERING LAB, Pusan National University, Busan, Korea Authors: Taekhyun Park , , , Abstract LoopUS…
…Rian Touchent , Abstract Switching from Masked Language Modeling to Causal Language Modeling during encoder adaptation improves downstream performance on biomedical texts through dense supervision effects in lower transformer layers. AI-generated summary…
…We evaluate our model on four standard relation extraction benchmarks: CoNLL04 , DocRED , FewRel , and CrossRE , and demonstrate competitive performance against both specialized relation extraction models and large language models, while maintaining the…
…World Models (concrete reasoning) and Large Language Models (abstract reasoning). By integrating these two paradigms, we unlock a new level of multimodal AI capabilities. Get this paper in your agent: hf papers…
…Learning Transferable Capability Vectors in Parametric Space for Vision-Language-Action Models Published on May 11 Submitted by Wenxuan Song on May 12 OpenHelix-Team Authors: , , , , , , , , , Abstract A novel approach decouples auxiliary…
…on May 12 Authors: , , , , , , , , , Abstract Research demonstrates that structured pruning and knowledge distillation effectively compress mixture-of-experts models at scale, with progressive pruning and combined distillation strategies improving performance. AI-generated…
…AI-generated summary Autoregressive image modeling relies on visual tokenizers to compress images into compact latent representations . We design an end-to-end training pipeline that jointly optimizes reconstruction and generation , enabling…
…Measuring Human--AI Tacit Understanding (2026) Behavioral Transfer in AI Agents: Evidence and Privacy Implications (2026) The Attribution Blind Spot: Detecting When Language Models Rely on Memory Rather Than Retrieved Context (2026…