Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv:2605. 31119v2 Announce Type: replace-cross Abstract: In robotics, dangers and adversity modes are often embodiment-specific and relative to each agent.
arXiv:2607. 19806v1 Announce Type: cross Abstract: Activation steering provides a lightweight mechanism for controlling large language models at inference time, but steering vectors can have unintended externalities: utility vectors may weaken safety behavior, while refusal vectors may induce over-refusal on benign prompts.
arXiv:2607. 19364v1 Announce Type: new Abstract: Activation steering offers a lightweight alternative to fine-tuning for behavioral control of large language models, but SAE-based steering methods often rely on learned steering objectives or single-criterion feature selection.
arXiv:2607. 19361v1 Announce Type: cross Abstract: Most safety guardrails for large language models (LLMs) evaluate each prompt-response pair in isolation, which misses failures that arise only over a dialogue as benign turns compose into harm.
arXiv:2607. 19510v1 Announce Type: new Abstract: Modern LLM deployments use a number of implementation choices and inference optimizations (e.
arXiv:2607. 19386v1 Announce Type: new Abstract: Cross-paper comparison of sparse autoencoder (SAE) interpretability often relies on autointerpretability scores.
arXiv:2607. 19349v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as always-on online services, making efficient LLM serving a critical systems challenge.
arXiv:2607. 19438v1 Announce Type: cross Abstract: Apple's M5 generation introduces a redesigned GPU architecture in which every core carries a dedicated Neural Accelerator: on-die matrix units exposed through the Metal~4 tensor API.
arXiv:2512. 05462v2 Announce Type: replace-cross Abstract: Pharmaceutical drug discovery demands machine learning (ML) infrastructure that goes beyond general-purpose Machine Learning Operations (MLOps): inference-time composition of multiple models for multi-parameter optimization (MPO), version management for physics-based models without serialized ML artifacts, enterprise compound library precomputation, and governance structured around scientific organizational units rather than generic access controls.
arXiv:2607. 19629v1 Announce Type: cross Abstract: Large language models operating in emotionally sensitive contexts face a structural trilemma: when users in vulnerable states request information that may reinforce maladaptive attribution, current response architectures resolve the tension through protective restriction, uninflected facilitation, or unintegrated co-presence of both imperatives -- each preserving one objective at the cost of the other.
arXiv:2607. 20057v1 Announce Type: cross Abstract: Antibodies are essential proteins that play a central role in immune recognition by binding specific antigen molecules.
arXiv:2607. 19751v1 Announce Type: cross Abstract: We present a regression-based approach to Arabic dialect geolocation that models dialectal variation as a continuous geographic space rather than discrete categories.
arXiv:2604. 02694v2 Announce Type: replace-cross Abstract: The rapid progress of generative AI has enabled increasingly realistic text-centric image forgeries, posing major challenges to document safety.
arXiv:2607. 19449v1 Announce Type: cross Abstract: Evaluation frameworks for tool-augmented LLM agents focus overwhelmingly on capability metrics or explicit tool crashes, leaving silent infrastructure failures and HTTP 200 responses with empty, null, or malformed payloads largely unaudited.
arXiv:2606. 06460v3 Announce Type: replace-cross Abstract: Autonomous LLM agents increasingly hold real credentials and operate infrastructure with no human in the loop, yet operators have no standard way to tell an agent a resource is off-limits, or to ask a running agent to stand down: access controls either admit it or hard-fail it.
arXiv:2607. 19355v1 Announce Type: new Abstract: LLMs are increasingly used with external knowledge sources like the internet.
arXiv:2607. 19768v1 Announce Type: new Abstract: Very Large Scale Integration (VLSI) global routing is an NP-hard combinatorial optimization problem requiring signal net assignment across capacity-constrained 3D grids while minimizing congestion, wirelength, and via transitions.
arXiv:2607. 19366v1 Announce Type: new Abstract: Safety as Polytope (SaP) learns linear half-space constraints in LLM hidden space but requires per-category tuning of the constraint count K.
arXiv:2607. 19767v1 Announce Type: new Abstract: A rich and recognizable component library is the cornerstone of printed circuit board (PCB) design and generation.
arXiv:2607. 19635v1 Announce Type: cross Abstract: Neural solvers are built to deduce, branch, and revise intermediate states.