…A Framework for Operationalizing Human Expert Preferences as Semantic Evals (2026) Automated Interpretability and Feature Discovery in Language Models with Agents (2026) The Moltbook Files: A Harmless Slopocalypse or Humanity's Last…
…It features a hierarchical abstract tree index with different abstraction strategies, enabling efficient and precise retrieval with logarithmic time. It employs a multi-granular agentic retriever including a powerful reading & answering agent…
…Yet, recent progress in LLM coding has focused on well-defined tasks such as feature implementation, bug fixing, and competitive programming . Open-ended coding remains a weak spot for LLMs, largely because…
…By inserting an SAE module into a pretrained VLM and training it with standard reconstruction objectives , we find that the learned sparse latent features naturally capture attack-relevant signals. These features enable…
…Get this paper in your agent: hf papers read 2605.12449 Don't have the latest CLI? curl -LsSf https://hf.co/cli/install.sh | bash No model linking this paper Cite…
…We introduce a low-cost, automated, and scalable data acquisition pipeline for creating customized occupancy datasets , and demonstrate its effectiveness through MinecraftOcc, a large-scale dataset featuring 100,165 images from 156…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Autonomous AI research agents aim to accelerate scientific discovery by automating the research pipeline, from hypothesis generation to peer review . However, existing benchmarks rarely…
…UniSD integrates complementary mechanisms that address supervision reliability, representation alignment, and training stability, including multi-teacher agreement , EMA teacher stabilization , token-level contrastive learning , feature matching , and divergence clipping . Across six benchmarks…
…Wiki-CoE , a large-scale dataset of structured web pages derived from 2WikiMultiHopQA, and SlideVQA , a challenging dataset of presentation slides featuring complex diagrams and free-form layouts. Experiments demonstrate that fine…
…Alongside the dataset, we propose the Cinematic Narrative Benchmark , featuring a visual-logic-driven paradigm and a novel Anti-Copy-Paste Variance (ACP-Var) metric to rigorously assess continuous storytelling and 3D…