Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv:2604. 09552v2 Announce Type: replace-cross Abstract: Engineering rulebooks and technical standards contain multimodal information like dense text, tables, and illustrations that are challenging for retrieval augmented generation (RAG) systems.
arXiv:2606. 07404v1 Announce Type: new Abstract: This paper reports on training a hundred-billion-parameter sparse mixture of experts on a single eight-GPU node, end to end.
arXiv:2606. 06990v1 Announce Type: new Abstract: The generation of high-fidelity synthetic Electronic Health Records (EHR) is crucial for advancing medical research while preserving patient privacy.
arXiv:2606. 07181v1 Announce Type: cross Abstract: Single-step retrosynthesis needs both accurate first-ranked suggestions and candidate lists that are rich enough for downstream selection.
arXiv:2509. 05316v2 Announce Type: replace-cross Abstract: A conventional LLM Unlearning setting consists of two subsets -"forget" and "retain", with the objectives of removing the undesired knowledge from the forget set while preserving the remaining knowledge from the retain.
arXiv:2606. 06679v1 Announce Type: cross Abstract: Court judgments are central to legal practice and jurisprudence, yet discourse analysis of Hong Kong judgments has received limited attention, owing largely to the absence of expert-annotated corpora.
arXiv:2606. 07414v1 Announce Type: new Abstract: Sparsity allows scaling model parameters without proportionally increasing computational cost.
arXiv:2606. 03002v2 Announce Type: replace-cross Abstract: Quantization is a standard path to deploying large language models, and quantized models are typically judged acceptable when perplexity or downstream accuracy remains close to the full-precision original.
arXiv:2505. 14289v2 Announce Type: replace Abstract: Graphical User Interface (GUI) agents powered by Multimodal Large Language Models (MLLMs) are increasingly deployed yet vulnerable to Environmental Injection Attacks (EIAs).
arXiv:2606. 06547v1 Announce Type: cross Abstract: Diffusion Large Language Models (dLLMs) refine tokens iteratively but commit them irreversibly, leading to a "stability lag" where early decisions remain fragile even after being written.
arXiv:2606. 07031v1 Announce Type: new Abstract: Self-supervised learning (SSL) for time-series representation learning is dominated by two paradigms: contrastive methods, which face challenges in constructing positive or negative pairs, and masking-based methods, which disrupt the temporal continuity of time-series signals.
arXiv:2606. 06854v1 Announce Type: new Abstract: This paper uses geometry to explain how a machine learning model can be stolen using an already existing well-known method.
arXiv:2603. 06915v2 Announce Type: replace-cross Abstract: The extraction of structured information from raw text is a fundamental component of many NLP applications, including document retrieval, ranking, and relevance estimation.
arXiv:2606. 06743v1 Announce Type: cross Abstract: The popularity of neural audio codecs as speech tokenizers has surged with the advent of Multimodal Large Language Models.
arXiv:2606. 06614v1 Announce Type: cross Abstract: Despite growing interest, most evaluations of large language models' (LLMs') personalization abilities have relied on synthetic data.
arXiv:2606. 06735v1 Announce Type: new Abstract: Linear activation steering has gained popularity as a simple and empirically effective way to control language model behavior.
arXiv:2603. 16689v2 Announce Type: replace Abstract: Next-token predictors often appear to develop internal representations of the latent world and its rules.
arXiv:2606. 07082v1 Announce Type: cross Abstract: On-policy distillation (OPD) is increasingly used to improve large language model reasoning, but its training dynamics remain poorly understood.
arXiv:2606. 07001v1 Announce Type: cross Abstract: High-quality training data is essential to large language models (LLMs) and typically requires extensive and costly manual curation.
arXiv:2604. 08168v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models have advanced robot manipulation through large-scale pretraining, but real-world deployment remains challenging due to partial observability and delayed feedback.