Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv:2511. 00810v4 Announce Type: replace-cross Abstract: Graphical user interface (GUI) grounding is a key capability for computer-use agents, mapping natural-language instructions to actionable regions on the screen.
arXiv:2606. 31557v1 Announce Type: cross Abstract: In the evolving threat landscape, adversaries exploit software vulnerabilities to launch sophisticated attacks, challenging traditional defenses.
arXiv:2601. 04126v3 Announce Type: replace-cross Abstract: GUI agents that interact with graphical interfaces on behalf of users represent a promising direction for practical AI assistants.
arXiv:2606. 31591v1 Announce Type: cross Abstract: Emergent misalignment (EM) is a recently discovered phenomenon in LLMs where fine-tuning on a narrow misaligned task, such as writing insecure code, leads to broadly misaligned behaviour on unrelated prompts.
arXiv:2606. 30813v1 Announce Type: cross Abstract: Deep neural networks with repeated architectural blocks, such as transformers, often exhibit structured relationships across layers that emerge during training.
arXiv:2606. 30899v1 Announce Type: cross Abstract: Backdoor attacks pose a serious threat to large language models (LLMs) by causing otherwise benign systems to produce attacker-specified malicious behavior when a hidden trigger is present.
arXiv:2606. 31397v1 Announce Type: cross Abstract: State-based fine-tuning has emerged as a compelling alternative to weight-based adaptation for transformers, updating lightweight controls into states rather than model weights, offering substantial memory savings while retaining parameter efficiency.
arXiv:2601. 16398v3 Announce Type: replace-cross Abstract: Algorithmic audits are essential tools for examining systems for properties required by regulators or desired by operators.
arXiv:2606. 30696v1 Announce Type: cross Abstract: Enabling robots to follow natural language commands to complete zero-shot long-horizon tasks remains challenging.
arXiv:2606. 31338v1 Announce Type: cross Abstract: Recent music audio-language models achieve high accuracy on instrument question-answering benchmarks, but it remains unclear whether this reflects robust audio grounding or benchmark-specific shortcuts.
arXiv:2606. 31182v1 Announce Type: new Abstract: Recent work shows that LLM agents can improve sharp-constant inequalities by searching for extremal constructions, which yield upper bounds.
arXiv:2509. 24575v2 Announce Type: replace-cross Abstract: This paper presents a framework to prompt multi-robot teams with high-level tasks using natural language expressions.
arXiv:2606. 31963v1 Announce Type: new Abstract: Modern LLM workflows move coordinate-indexed objects across checkpoints: steering vectors, sparse autoencoders, top-$k$ neuron sets, attribution lists, and merge alignments.
arXiv:2606. 31808v1 Announce Type: new Abstract: Language model systems built around proprietary APIs often operate on a token-based cost model.
arXiv:2606. 30651v1 Announce Type: cross Abstract: Delirium is common in hospitalized patients and is often missed in routine care.
arXiv:2606. 31859v1 Announce Type: new Abstract: Residual connections add every sublayer's proposed update with a fixed coefficient of one; the network never evaluates whether an update is reliable before committing it.
arXiv:2606. 31745v1 Announce Type: cross Abstract: Remote sensing change detection (CD) traditionally focuses on pixel-level binary segmentation, which identifies where changes occur but neither what nor why.
arXiv:2606. 31543v1 Announce Type: new Abstract: Large language models can produce fluent, internally coherent reasoning traces for abstract reasoning tasks while still being confidently wrong - making selection among candidates, not just generation, the central challenge.
arXiv:2606. 31464v1 Announce Type: cross Abstract: Recent advances in Large Language Models (LLMs) have motivated their adoption across a wide range of domains, including Artificial Intelligence (AI) for mental health.
arXiv:2606. 31474v1 Announce Type: new Abstract: Tabular foundation models enable accurate in-context learning (ICL) from small labeled datasets, but the private records placed in context can leak through model predictions.