Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv:2510. 11686v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) promises to expand the capabilities of language models, but it is unclear if current RL techniques promote the discovery of novel behaviors, or simply sharpen those already present in the base model.
arXiv:2607. 07050v2 Announce Type: replace-cross Abstract: Agentic language models must learn when to call tools, when to consume tool responses, and when to answer directly.
arXiv:2606. 05981v2 Announce Type: replace-cross Abstract: Aggressive distillation of the diffusion U-Net inverts the per-frame bottleneck of real-time text-to-image pipelines: once the denoiser is a 4-step or 1-step distilled student, the text encoder becomes the critical path.
arXiv:2502. 07780v4 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved significant success across various NLP tasks.
arXiv:2510. 13903v2 Announce Type: replace-cross Abstract: Chain-of-thought prompting has popularized step-by-step reasoning in large language models, yet model performance still degrades as problem complexity and context length grow.
arXiv:2602. 12811v2 Announce Type: replace-cross Abstract: When humans and large language models (LLMs) process the same text, activations in the LLMs correlate with brain activity measured, e.
arXiv:2607. 13425v1 Announce Type: cross Abstract: Learning effectively from limited data is critical in domains like security where labeled examples are scarce.
arXiv:2607. 13899v1 Announce Type: new Abstract: We propose the AIMO Interpretability Challenge, a competition on distinguishing robust from spurious reasoning in frontier mathematical language models based on the models' internal mechanisms.
arXiv:2607. 13501v1 Announce Type: new Abstract: Reinforcement learning for multi-turn search reasoning typically relies on terminal outcome rewards, which cannot distinguish useful, redundant, and harmful intermediate interactions.
arXiv:2607. 13072v1 Announce Type: cross Abstract: Zero-shot object-goal navigation aims to enable an intelligent agent to explore and navigate to objects of unknown categories in an unfamiliar environment without specific target training.
arXiv:2607. 13763v1 Announce Type: cross Abstract: Single-task fine-tuning of graph neural networks (GNNs) for power grid problems exhibits a systematic failure mode: models that achieve the lowest in-distribution error degrade the most under topology shift.
arXiv:2607. 13115v1 Announce Type: new Abstract: Small language models (SLMs) have shown promise for zero-shot molecular property prediction from SMILES strings, yet they often suffer from structural blindness because sequence representations under-specify key graph-topological cues.
arXiv:2607. 13305v1 Announce Type: cross Abstract: Benchmark accuracy in video large language models (LLMs) is often treated as evidence of visual understanding.
arXiv:2607. 13038v1 Announce Type: cross Abstract: We present the design and implementation of a safety constrained large language model (LLM) system for public health information access, focusing on maternal and child health (MCH) resource navigation.
arXiv:2604. 06614v2 Announce Type: replace-cross Abstract: Prompt learning has gained significant attention as a parameter-efficient approach for adapting large pre-trained vision-language models to downstream tasks.
arXiv:2605. 14477v2 Announce Type: replace Abstract: We introduce EvoLib, a test-time learning framework that enables large language models to accumulate, reuse, and evolve knowledge across problem instances without parameter updates or external supervision.
arXiv:2607. 13164v1 Announce Type: cross Abstract: Sign language is a primary communication channel for millions of Deaf and hard-of-hearing people, yet text-to-signer video generation remains costly because video diffusion models are expensive to train and evaluate.
arXiv:2607. 13051v1 Announce Type: cross Abstract: TriAttention is a recent method for shrinking the KV cache of long-reasoning LLMs: it scores each cached key by how much attention it is likely to receive and evicts the lowest-scoring ones.
arXiv:2607. 13918v1 Announce Type: cross Abstract: Serial verification gates are a core reliability primitive in LLM harnesses: a candidate answer is returned only if $k$ verifier calls all accept it.
arXiv:2607. 13465v1 Announce Type: cross Abstract: LLM-based agents have rapidly improved at operating individual digital environments such as mobile applications, desktop systems, and smart homes.