Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv:2603. 21396v5 Announce Type: replace Abstract: Recent work has shown that LLMs can sometimes detect when steering vectors are injected into their residual stream and identify the injected concept -- a phenomenon termed "introspective awareness.
arXiv:2602. 10743v2 Announce Type: replace Abstract: State-space language models such as Mamba and gated linear attention (GLA) offer linear-complexity, parallelisable alternatives to transformers, but their linear state updates limit expressivity and robust state tracking.
arXiv:2509. 23982v2 Announce Type: replace-cross Abstract: Preference alignment is a critical step in making Large Language Models (LLMs) useful and aligned with (human) preferences.
arXiv:2511. 09789v2 Announce Type: replace Abstract: Recent advances in deep forecasting models have achieved remarkable performance, yet most approaches still struggle to provide both accurate predictions and interpretable insights into temporal dynamics.
arXiv:2606. 11375v1 Announce Type: cross Abstract: Standard linear probing declares a property "encoded" when a classifier on hidden states achieves high accuracy.
arXiv:2606. 12378v1 Announce Type: cross Abstract: Physiological awareness is important for service, social, and assistive robots that interact with humans in everyday environments.
arXiv:2606. 11209v1 Announce Type: cross Abstract: Visual question answering increasingly requires multi-step reasoning.
arXiv:2606. 11290v1 Announce Type: cross Abstract: Large Language Model (LLM)-based multi-agent systems are increasingly powerful, but current agentic workflow optimization paradigms make an unsatisfying trade-off.
arXiv:2606. 12191v1 Announce Type: cross Abstract: Environments serve as interactive systems for large language model (LLM) based agents across diverse scenarios and play a crucial role in driving the continual evolution of model capabilities.
arXiv:2606. 12106v1 Announce Type: cross Abstract: This paper presents our solution to the 2026 SoccerNet VQA Challenge.
arXiv:2606. 11660v1 Announce Type: new Abstract: Data attribution is a promising field in interpretability that aims to explain model behavior through the influence of its training data, with applications including debugging undesirable model behavior and training dataset curation.
arXiv:2606. 11625v1 Announce Type: new Abstract: Time-series foundation models (TSFMs) are increasingly explored as predictive experts within emerging agentic time-series systems.
arXiv:2606. 11382v1 Announce Type: new Abstract: Deep learning models facilitate the discovery of molecules with tailored properties among billions of candidate compounds.
arXiv:2606. 11425v1 Announce Type: cross Abstract: Jailbreak attacks expose persistent safety weaknesses in large language models (LLMs), but existing stateless single-turn methods face a trade-off: hand-crafted prompts are expressive but static, while iterative prompt optimization can adapt but often relies on low-level mutations that require many target queries.
arXiv:2606. 12300v1 Announce Type: cross Abstract: Temporal grounding--returning the interval $[t_s, t_e]$ for a natural-language query over a video--is the language interface to long-form video, yet has been studied on short videos; the dynamics of hour-scale natural-language grounding remain underexplored.
arXiv:2602. 22962v2 Announce Type: replace Abstract: Data-driven models are revolutionizing weather forecasting.
arXiv:2606. 11201v1 Announce Type: cross Abstract: The wide deployment of LLMs has made model alignment necessary to make newly trained models safely and effectively respond to user instructions.
arXiv:2606. 12040v1 Announce Type: new Abstract: The design of reinforced concrete highway barriers is a safety-critical process that requires strict compliance with regulatory provisions such as the AASHTO-LRFD bridge design guidelines.
arXiv:2606. 12364v1 Announce Type: new Abstract: Transformers dominate modern sequence modeling, but their quadratic attention incurs substantial computational cost.
arXiv:2606. 11680v1 Announce Type: new Abstract: Large language model (LLM) agents struggle with long-horizon tasks due to their inherent statelessness, requiring all task-relevant information to be encoded in growing input contexts.