Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv:2606. 07846v1 Announce Type: cross Abstract: LLM-agent workflows chain model calls and tool invocations, and spend most of their wall-clock time waiting on upstream operations before downstream ones can start.
arXiv:2509. 10534v3 Announce Type: replace-cross Abstract: The attention mechanism in a Transformer architecture matches key to query based on both content -- the what -- and position in a sequence -- the where.
arXiv:2507. 12612v4 Announce Type: replace-cross Abstract: Supervised fine-tuning performance for large language models depends strongly on how training budget is distributed across a heterogeneous set of tasks.
arXiv:2510. 12171v2 Announce Type: replace Abstract: Large Language Models have shown strong scientific reasoning ability, but their performance on materials science problems remains less studied.
arXiv:2511. 17855v5 Announce Type: replace Abstract: Robots must learn from both what people do and what they say, but either modality alone is often incomplete: physical corrections are grounded but ambiguous in intent, while language expresses high-level goals but lacks physical grounding.
arXiv:2509. 09151v2 Announce Type: replace-cross Abstract: Research in video understanding has advanced rapidly, driven by increasingly diverse datasets and more powerful model architectures.
arXiv:2603. 22473v2 Announce Type: replace-cross Abstract: Hybrid language models combine softmax attention with linear-time sequence mechanisms such as state-space or linear-attention layers, but the functional contribution of each component type remains insufficiently characterized.
arXiv:2605. 09823v3 Announce Type: replace-cross Abstract: Personal AI assistants are beginning to act as delegates with access to calendars, inboxes, and user preferences.
arXiv:2606. 07654v1 Announce Type: cross Abstract: Multi-vector visual document retrievers achieve strong fine-grained matching by representing each page with multiple vectors from deep Vision-Language Models (VLMs), but this design makes deployment expensive in both storage and computational overhead.
arXiv:2606. 08239v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have made substantial advancements in video understanding, yet the reliability of their responses remains underexplored.
arXiv:2604. 08304v3 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) extends large language models (LLMs) with external knowledge, but this access path also introduces security risks that existing work often conflates with inherent LLM flaws.
arXiv:2602. 05774v4 Announce Type: replace-cross Abstract: Speculative decoding accelerates inference for (M)LLMs, yet a training-decoding discrepancy persists: while existing methods optimize single greedy trajectories, decoding involves verifying and ranking multiple sampled draft paths.
arXiv:2606. 09204v1 Announce Type: new Abstract: We present a reproducible failure mode of safety training in RAG-based LLM recommendation -- the Injection Paradox -- in which prompt injections embedded in retrieved documents backfire against the attacker, suppressing the target brand below the injection-free baseline.
arXiv:2603. 18388v2 Announce Type: replace Abstract: Automatic prompt optimization (APO) has emerged as a powerful paradigm for improving LLM performance without manual prompt engineering.
arXiv:2606. 08790v1 Announce Type: new Abstract: Autonomous agents negotiate, purchase, deploy code, and move funds, but no neutral mechanism determines whether they met their delegated obligation, who is responsible when they did not, or which settlement action follows.
arXiv:2606. 07874v1 Announce Type: new Abstract: LLMs-as-judges are the only way to evaluate safety at scale.
arXiv:2606. 07602v1 Announce Type: cross Abstract: LLM-based LEGO assembly generation requires both semantic grounding and physical feasibility.
arXiv:2606. 08146v1 Announce Type: new Abstract: Fraud detection in payment, e-commerce, and telecommunications systems requires accuracy at the individual level, robustness under severe class imbalance, and ease of understanding for risk managers.
arXiv:2606. 08382v1 Announce Type: cross Abstract: Low-rank projection has emerged as a promising approach for compressing the KV cache by exploiting hidden-dimension redundancy.
arXiv:2605. 16928v2 Announce Type: replace-cross Abstract: Long-context inference in large language models is bottlenecked by the quadratic cost of full attention.