Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv:2607.12896v3 Announce Type: replace Abstract: Medical image segmentation foundation models are expected to generalize across diverse clinical scenarios, yet existing universal methods remain fr...
arXiv:2608.08374v3 Announce Type: replace Abstract: Transformer models are increasingly used for whole-slide image analysis in computational pathology. Yet, WSIs differ fundamentally from natural ima...
arXiv:2609.34167v2 Announce Type: replace Abstract: Foundation models pre-trained on large-scale fMRI datasets have shown strong downstream performance, but at substantial data and computation cost....
arXiv:2609.37040v1 Announce Type: cross Abstract: Natural language autoencoders translate a language model's internal activations into readable explanations. Explaining every token position is costly...
arXiv:2609.37134v1 Announce Type: cross Abstract: Frozen language models (LMs) are increasingly used as fixed feature extractors for downstream reranking, scoring, and preference modeling, raising a...
arXiv:2609.37119v1 Announce Type: cross Abstract: Recent approaches to reinforcement learning (RL) post-training for large language models increasingly remove the critic to reduce training instabilit...
arXiv:2609.37216v1 Announce Type: cross Abstract: Large language models can generate plausible code-review comments, but such comments may contain technically incorrect claims that mislead developers...
arXiv:2609.37371v1 Announce Type: cross Abstract: Model adaptation is typically governed by a fixed recipe, even though different update programs can produce substantially different behavioral outcom...
arXiv:2609.37351v1 Announce Type: cross Abstract: Test-time compute scaling has emerged as a cornerstone of advanced machine reasoning, yet performing iterative deliberation directly within continuou...
arXiv:2609.37443v1 Announce Type: cross Abstract: Long-term memory enables language models to use past interactions in future conversations. However, evidence needed to answer a question may be scatt...
arXiv:2609.37519v1 Announce Type: cross Abstract: Video-based policy learning is particularly promising, as it illustrates target behaviors without requiring action annotations or embodiment-matched...
arXiv:2609.37567v1 Announce Type: cross Abstract: Driven by the rapid advancement of large language models (LLMs), LLM-based multi-agent systems (MAS) have emerged as a powerful paradigm for collabor...
arXiv:2609.37617v1 Announce Type: cross Abstract: Speculative decoding accelerates autoregressive generation by using a smaller drafter to propose tokens for batched verification by a larger target....
arXiv:2609.37626v1 Announce Type: cross Abstract: No single way of parallelizing attention serves large language models well under all loads. Low concurrency favors tensor parallelism, many independe...
arXiv:2609.37669v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) is increasingly used to enhance Large Language Model (LLM)-based software vulnerability detection by grounding p...
arXiv:2609.37809v1 Announce Type: cross Abstract: Predicting canopy height from medium-resolution satellite imagery is a common and scalable approach for assessing the condition of the world's forest...
arXiv:2609.37849v1 Announce Type: cross Abstract: Scientific software is increasingly required to process larger datasets while maintaining acceptable execution times. Software optimization tradition...
arXiv:2609.37864v1 Announce Type: cross Abstract: Agent harness bugs exhibit unique characteristics and remain challenging for state-of-the-art software agents to repair. Progress in this area is fur...
arXiv:2609.37914v1 Announce Type: cross Abstract: Fine-tuning large language models on narrow, misaligned tasks can undo their post-training alignment and induce novel misaligned behaviors -- a pheno...
arXiv:2609.37974v1 Announce Type: cross Abstract: Masked diffusion models (MDMs) generate text by unmasking several tokens per step, but they are trained and sampled under different conditions. The m...