Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv:2606. 09558v1 Announce Type: cross Abstract: Motivation: Transformer-based models are increasingly applied to large-scale single-cell transcriptomics, showing strong performance through self-supervised learning on millions of cells.
arXiv:2606. 08892v1 Announce Type: new Abstract: AI models deployed in critical domains, such as AI safety research, may subtly sabotage our efforts due to misalignment.
arXiv:2606. 09079v1 Announce Type: cross Abstract: Conventional LLMs keep the full KV cache loaded during decoding, causing a severe GPU memory bottleneck for ultra-long context serving.
arXiv:2606. 07622v1 Announce Type: new Abstract: Accurate passenger queue forecasting in airport terminals is essential for efficient departure operations, as it enables proactive congestion management.
arXiv:2604. 17324v2 Announce Type: replace-cross Abstract: Global self-attention drives modern graph transformers, yet the softmax at its core imposes a structural constraint rarely examined directly: every attention row is non-negative and sums to one, so each per-head output is a mass-conserving convex combination of value vectors.
arXiv:2605. 03862v4 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards has become a common way to improve explicit reasoning in large language models, but final-answer correctness alone does not reveal whether the reasoning trace is faithful, reliable, or useful to the model that consumes it.
arXiv:2606. 09500v1 Announce Type: new Abstract: Objective.
arXiv:2606. 08779v1 Announce Type: new Abstract: Reinforcement Learning (RL) has emerged as a pivotal post-training paradigm, yet it frequently suffers from unpredictable sub-optimum performance or even training collapses.
arXiv:2605. 03229v2 Announce Type: replace-cross Abstract: Adapting a pretrained language model to a new task often hurts the general capabilities it already had, a problem known as catastrophic forgetting.
arXiv:2606. 08132v1 Announce Type: cross Abstract: Vision Transformers operate on fixed patch grids, which can introduce phase-dependent instability for dense prediction: changing the patch partition can change the token evidence available to a pixel, especially near boundaries.
arXiv:2606. 07548v1 Announce Type: cross Abstract: The MedHopQA challenge presents a critical test for Large Language Models (LLMs): complex, multi-hop reasoning in the high-stakes biomedical domain.
arXiv:2605. 03226v2 Announce Type: replace-cross Abstract: Safety fine-tuning of language models typically requires a curated adversarial dataset.
arXiv:2606. 08262v1 Announce Type: new Abstract: Recent advances in Large Language Models (LLMs) have opened new possibilities for time series forecasting by enabling alignment between temporal patterns and pretrained word embeddings.
arXiv:2606. 08768v1 Announce Type: new Abstract: Transformers consistently fail to learn certain simple functions that are provably expressible with specific parameter settings.
arXiv:2606. 09456v1 Announce Type: new Abstract: On-Policy Distillation (OPD) has become a core technique in the post-training of Large Language Models (LLMs) for transferring knowledge from domain experts to student models.
arXiv:2605. 22781v2 Announce Type: replace-cross Abstract: LLM-powered AI agents require high-frequency state exploration (e.
arXiv:2606. 07805v1 Announce Type: new Abstract: The rapid evolution of Large Language Models (LLMs) from passive assistants to autonomous, execution-capable agents has introduced critical operational risks.
arXiv:2606. 07541v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have shown strong performance on objective tasks such as video understanding and reasoning.
arXiv:2606. 07559v1 Announce Type: cross Abstract: Fine-tuning a language model on contexts whose correct completion has a near-synonym competitor often fails silently.
arXiv:2603. 13259v2 Announce Type: replace-cross Abstract: When a decoder-only transformer is forced to process matched correct and incorrect single-token continuations of a factual query, the two pathways through hidden-state space diverge in a specific way: displacement vectors from the query-only representation maintain approximately equal magnitude but rotate apart in direction.