Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv:2510. 01377v2 Announce Type: replace-cross Abstract: In this paper, we propose DeMuon, a method for decentralized matrix optimization over a given communication topology.
arXiv:2602. 17063v2 Announce Type: replace-cross Abstract: Sub-bit model compression targets storage below one bit per weight; as magnitudes are aggressively compressed, the sign bit becomes a fixed-cost bottleneck.
arXiv:2606. 03112v1 Announce Type: cross Abstract: With the increasing scale and number of wind farms, wind turbines' daily operation and maintenance costs are increasing.
arXiv:2502. 09755v4 Announce Type: replace-cross Abstract: Safety-aligned LLMs respond to prompts with either compliance or refusal, each corresponding to distinct directions in the model's activation space.
arXiv:2606. 03280v1 Announce Type: new Abstract: Recent work shows that language models can transmit behavioural traits through hidden signals in generated data during training.
arXiv:2512. 05530v2 Announce Type: replace Abstract: Recently, multimodal large language models (MLLMs) have been widely applied to reasoning tasks.
arXiv:2606. 03963v1 Announce Type: cross Abstract: Deep reinforcement learning has shown strong potential for enabling autonomous robots to learn complex navigational tasks.
arXiv:2506. 00431v2 Announce Type: replace Abstract: Due to the proficiency of self-attention mechanisms (SAMs) in capturing dependencies in sequence modeling, several existing dynamic graph neural networks (DGNNs) utilize Transformer architectures with various encoding designs to capture sequential evolutions of dynamic graphs.
arXiv:2601. 23169v2 Announce Type: replace Abstract: Current neural architectures lack a principled way to handle interchangeable tokens, i.
arXiv:2606. 03969v1 Announce Type: cross Abstract: Reliable uncertainty communication is critical to the trustworthiness of LLMs, yet faithful calibration (FC)--the alignment between models' intrinsic and (linguistically) expressed confidence--is a persistent failure mode.
arXiv:2606. 03361v1 Announce Type: new Abstract: Rubric-based rewards are increasingly used for open-ended language model post-training, but criterion-level scores are often aggregated as independent utilities.
arXiv:2606. 03219v1 Announce Type: cross Abstract: African languages have very little labelled data, and it is unclear if augmenting the quantity of annotation data reliably enhances downstream performance.
arXiv:2510. 23469v2 Announce Type: replace Abstract: Self-supervised pre-training on unlabeled graph data has become a common paradigm for Graph Neural Networks (GNNs).
arXiv:2606. 03137v1 Announce Type: new Abstract: LLM-based multi-agent simulation offers a promising way to study social interaction, deliberation, and collective opinion dynamics.
arXiv:2606. 02584v1 Announce Type: cross Abstract: Idiomatic expressions remain a persistent challenge for natural language processing because their meanings are often non-compositional, context-dependent, and difficult to align across languages.
arXiv:2606. 03792v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) successfully enables personalization in text-to-image generation by adapting pre-trained diffusion models to specific visual concepts and styles.
arXiv:2605. 03353v3 Announce Type: replace-cross Abstract: LLM agents increasingly rely on reusable skills (e.
arXiv:2606. 02765v1 Announce Type: cross Abstract: Model dimension ($d_{model}$) is a fundamental hyperparameter in transformer language models, yet its role in setting the geometric limits of feature representation remains under-explored.
arXiv:2606. 03803v1 Announce Type: cross Abstract: We present LiveBand, a real-time system that generates high-fidelity music accompaniments to live audio input, respecting strict causal constraints.
arXiv:2606. 03165v1 Announce Type: cross Abstract: The language used by digital chat assistants such as ChatGPT can diverge from human expectations (misalignment).