Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv:2602. 13376v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) are increasingly used in document processing pipelines to convert flowchart images into structured code (e.
arXiv:2607. 07725v1 Announce Type: cross Abstract: Genomic prediction models often fail to transfer across institutions because sequencing panels differ across sites, creating structural feature missingness at deployment.
arXiv:2607. 07964v1 Announce Type: new Abstract: Post-training quantization (PTQ) is a widely adopted technique for compressing large language models (LLMs) without retraining.
arXiv:2604. 26962v3 Announce Type: replace-cross Abstract: Education is one of the most promising real-world applications for Large Language Models (LLMs).
arXiv:2607. 08605v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have emerged as a promising technique for mechanistic interpretability by learning a set of sparse latent features in large models, each of which encodes a distinct concept.
arXiv:2607. 08046v1 Announce Type: cross Abstract: Large language models fine-tuned for forecasting can be accurate yet poorly calibrated, and their chain-of-thought (CoT) reasoning may not faithfully reflect the evidence behind a forecast.
arXiv:2607. 07761v1 Announce Type: new Abstract: Large language models (LLMs) have emerged as important tools in healthcare, showing growing potential for clinical reasoning and patient care.
arXiv:2607. 08400v1 Announce Type: cross Abstract: LLM agents reach users through resellers, who may rebrand a developer's agent or substitute a cheaper model.
arXiv:2604. 07102v2 Announce Type: replace-cross Abstract: Activation-based steering enables inference-time personalization of large language models, but its effects in educational applications are not well understood.
arXiv:2607. 08170v1 Announce Type: new Abstract: Zero-shot model size interpolation aims to create new models of intermediate target sizes by combining existing models without additional training.
arXiv:2607. 08754v1 Announce Type: cross Abstract: Low-rank factorization is widely used to compress neural networks, but modern models are often not naturally amenable to aggressive factorization without significant accuracy loss.
arXiv:2607. 08409v1 Announce Type: cross Abstract: LLM-based ASR adapted to regulated domains such as banking is bottlenecked by privacy: real speech is costly and legally constrained to collect, making synthetic text-to-speech (TTS) an attractive substitute.
arXiv:2607. 08027v1 Announce Type: cross Abstract: This paper proposes an improved structured pruning method for large language models (LLMs) that addresses key challenges in adapting Adaptive Feature Retention (AFR), an unstructured pruning technique, to structured pruning.
arXiv:2605. 19665v2 Announce Type: replace-cross Abstract: Pairwise human preference prediction is central to evaluating code-generation systems, where quality often depends on task-specific trade-offs beyond functional correctness.
arXiv:2607. 08057v1 Announce Type: cross Abstract: Despite the rapid advancements of large language models (LLMs), LLM serving systems remain memory-intensive and costly.
arXiv:2605. 10886v3 Announce Type: replace-cross Abstract: Recent GPU generations deliver significantly higher FLOPs using lower-precision arithmetic, such as FP8.
arXiv:2510. 12857v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are now widely deployed in user-facing applications, reaching hundreds of millions of users worldwide.
Efficient serving of diffusion large language models (dLLMs) is hindered by convergence heterogeneity: when batching multiple requests, different sequences converge at different rates, causing faster requests to stall behind slower stragglers and introducing compute bubbles and tail latency. We present BlockServe, a continuous batching framework that integrates block-grained scheduling -- immediately evicting completed requests at block boundaries -- with mixed-state execution that extends dual cache and parallel decoding to heterogeneous batches via gather-scatter indexing.
Large Language Model (LLM) agents have shown promise in multi-step planning tasks, but existing approaches like LATS (Language Agent Tree Search) and ReAct rely heavily on LLM inference during planning, leading to high computational costs and stochastic behavior. We present \textbf{GATS} (Graph-Augmented Tree Search), a planning framework that combines systematic UCB1-based tree search with a layered world model to eliminate LLM calls during inference while achieving superior planning performance.
Large autoregressive language models exhibit a self-correction blind spot: they reliably fix identical errors when attributed to an external source yet fail to fix the same errors in their own outputs. Prior work has documented this phenomenon empirically, through controlled error injection, error-depth decompositions, RL-based verifier-corrector training, and intrinsic self-verification, but offers no formal model of why generating a token suppresses the ability to detect its error, no quantitative activation condition for correction markers, and no convergence guarantee for reinforcement-learning-based self-correction.