Knowledge catalogue
arXiv:2608.03893v1 Announce Type: new Abstract: Production deployments often swap between different-sized models in a family for cost-quality cascading, mid-conversation switching, and routing, and ea
arXiv:2608.03068v1 Announce Type: cross Abstract: Reinforcement learning (RL) has emerged as an effective method for enhancing the reasoning capabilities of large language models (LLMs). However, exis
arXiv:2608.03297v1 Announce Type: new Abstract: A standard claim in the literature on retrieval-augmented and memory-augmented language models is that shorter context is better when the relevant infor
arXiv:2608.03311v1 Announce Type: cross Abstract: Enterprise compliance management requires rapid adaptation to evolving regulatory frameworks (e.g., DORA, AI RMF, FedRAMP) and tight remediation SLAs.
arXiv:2608.03078v1 Announce Type: new Abstract: Multimodal large language models have demonstrated strong defect recognition capability in industrial anomaly detection. However, in lithography review,
arXiv:2608.03887v1 Announce Type: new Abstract: Fine-tuning a large language model on new data degrades what it previously learned. We present Omega-S, a drop-in penalty computed from the weight matri
arXiv:2608.03854v1 Announce Type: new Abstract: When decoder language models are used as classifiers, predicted class probabilities depend on implementation choices, including the prompt template, ver
arXiv:2608.02356v2 Announce Type: replace Abstract: Large language model agents increasingly solve complex tasks by composing reusable skills from a library. To address this, the key challenge is not
arXiv:2608.03420v1 Announce Type: new Abstract: Large language models have improved substantially on single-shot reasoning tasks, but their performance in sequential decision-making is less well under
arXiv:2608.03123v1 Announce Type: cross Abstract: Machine unlearning aims to eliminate the influence of sensitive data on a model. In the real world, unlearning requests arrive continually, which give
arXiv:2608.01014v1 Announce Type: new Abstract: Preference optimization improves mathematical reasoning in large language models (LLMs), but reliable chosen-rejected pairs usually require verified ans
Hank Green, a popular YouTuber and science communicator, said he is stepping back from production amid intense criticism over his use of AI. Green described his AI usage as 'not healthy,' but stressed
arXiv:2608.01418v1 Announce Type: cross Abstract: Autoregressive rollout generation is a major computational cost in reinforcement learning for large language models. Reusing each rollout batch for ad
arXiv:2608.00991v1 Announce Type: cross Abstract: This paper introduces SCHEDBench, a natural-language benchmark for evaluating combinatorial scheduling constraint faithfulness under surface-form vari
arXiv:2608.02181v1 Announce Type: new Abstract: Proximal Policy Optimization (PPO) for large language models typically trains its critic by mean-squared-error (MSE) regression on scalar value targets.
arXiv:2608.01285v1 Announce Type: new Abstract: The continued development of LLMs toward persistent and adaptive intelligence increasingly requires long-term memory mechanisms that preserve and reuse
arXiv:2608.00916v1 Announce Type: cross Abstract: Modern reranking recipes---billion-scale cross-encoders, mixture-of-experts (MoE) backbones, and distillation against strong teachers---have outpaced
arXiv:2607.29626v1 Announce Type: new Abstract: As LLMs evolve from code completion systems into autonomous scientific agents, evaluating their ability to conduct experiments has become increasingly i
arXiv:2607.29549v1 Announce Type: new Abstract: Large language models have demonstrated strong mathematical problem-solving capabilities, yet reliably verifying their candidate answers remains challen
arXiv:2607.28667v1 Announce Type: cross Abstract: Recent work has shown that classifying large language models (LLMs)' responses can be distinguished by modeling token embeddings as trajectories of a
arXiv:2607.28635v1 Announce Type: new Abstract: In Natural Language Processing (NLP), dealing with underrepresented topics is challenging, especially in unsupervised tasks where clustering might not a
arXiv:2607.28632v1 Announce Type: new Abstract: Major mathematical conjectures still depend heavily on expert intuition, so a unified method for the systematic generation and validation of conjectures
arXiv:2607.15776v2 Announce Type: replace Abstract: OWL ontologies provide a formal knowledge representation framework that enables semantic reasoning, and have been widely adopted across domains such
arXiv:2511.00847v5 Announce Type: replace-cross Abstract: The widespread adoption of Large Language Models (LLMs) through Application Programming Interfaces (APIs) induces a critical vulnerability: th
arXiv:2607.28814v1 Announce Type: cross Abstract: In Motivational Interviewing (MI), a client's sustain talk (arguments for the status quo) calls for the counselor to roll with resistance, a move that
arXiv:2607.28871v1 Announce Type: cross Abstract: When a repair agent runs a test and sees it pass, the result is treated as evidence about the reported defect. We measure how often that treatment is
arXiv:2604.04468v2 Announce Type: replace Abstract: Evaluating retail strategies before deployment is difficult, as outcomes are determined across multiple stages, from seller-side persuasion through
Been trying to find something that actually handles my workload well instead of just being 'fine.' Started on Qwen 2.5 7B, moved to Qwen 3 8B, and right now I'm using Nemotron 3 Ultra (the big 550B on
arXiv:2607.27705v1 Announce Type: cross Abstract: Large language models can contribute useful ideas to mathematical research, yet long-horizon proof attempts remain difficult to coordinate, evaluate,
GPU utilization can read healthy while your queue backs up, and a new replica takes minutes to warm. Here's how to pick autoscaling metrics, tune scale-up/down windows, and budget for cold starts on d
arXiv:2607.27405v1 Announce Type: new Abstract: Both expressions of uncertainty and inferences are ubiquitous in natural language, and valid inferences over natural-language expressions of uncertainty
arXiv:2508.02092v3 Announce Type: replace-cross Abstract: Large language models represent significant investments in computation, data, and engineering expertise, making them extraordinarily valuable
I’m one of the builders of LOLM, a hybrid Transformer–SSM model and agent system from Qira. The model separates surface token processing from persistent latent-state tracking. An NFET controller can s
Disclaimer, this was kinda written with AI (Gemma 4 again) but it also did really well here, it outputted what I wanted, when I asked it to refine stuff or improve on certain areas it did that without
arXiv:2607.27797v1 Announce Type: new Abstract: Predictive process monitoring (PPM) leverages event logs to forecast the future of running process instances, for instance, predicting the next activity
arXiv:2601.16651v3 Announce Type: replace Abstract: Gradient-based methods for instance-based explanation for large language models (LLMs) are hindered by the immense dimensionality of model gradients
arXiv:2607.28418v1 Announce Type: cross Abstract: Pruning is a promising approach for improving the efficiency of LLMs. Existing static structured pruning methods are hardware-friendly and can deliver
arXiv:2607.26828v1 Announce Type: new Abstract: Large language models increasingly support scientific and algorithmic discovery through inference-time search over evaluated candidates. Existing adapti
arXiv:2602.09472v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) enable non-experts to specify open-world multi-robot tasks, but the generated plans are often kinematically infea
arXiv:2607.25451v1 Announce Type: new Abstract: Language models are almost always quantized before they are deployed, and a growing line of work asks whether quantization also lowers their privacy ris
arXiv:2607.25308v1 Announce Type: cross Abstract: Training large language models (LLMs) to act in long-horizon games is a promising step toward generalist decision-making, yet reinforcement learning w
arXiv:2601.03595v2 Announce Type: replace Abstract: Large Reasoning Models (LRMs) exhibit human-like cognitive reasoning strategies (eg backtracking, cross-verification) during the reasoning process,
arXiv:2607.25820v1 Announce Type: new Abstract: Food image segmentation plays a vital role in health-related applications such as nutrition tracking and personalized health monitoring. However, existi
arXiv:2607.24788v1 Announce Type: new Abstract: As Large Language Models scale to increasingly long contexts, the memory I/O and computational overhead of the Key-Value (KV) cache during decoding emer
arXiv:2607.25199v1 Announce Type: cross Abstract: Automated code generation is becoming an important tool in quantitative finance, where large language models can generate option pricing implementatio
arXiv:2607.25877v1 Announce Type: new Abstract: This paper investigates how multi-agent systems (MAS)-based on large language models (LLMs) can support actuarial risk modelling, with a particular focu
arXiv:2607.24803v1 Announce Type: cross Abstract: Scientific claims often spread on social media faster than they can be verified, while posts rarely link to the original scholarly sources. To tackle
arXiv:2607.25152v1 Announce Type: new Abstract: Long-running autonomous agents plan, act, and judge their own completion without human intervention. When an agent grades its own work, self-evaluation
arXiv:2607.24343v1 Announce Type: cross Abstract: Language-model agents act through structured tool calls whose arguments carry different risks. Untrusted content may safely influence an email body bu
arXiv:2607.24743v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) hold immense potential to revolutionize clinical practice, yet deploying them in the medical domain is fundam
arXiv:2607.23386v1 Announce Type: new Abstract: We document a failure class in frontier large language models -- exception chain collapse -- observed in eligibility evaluation under nested conditional
arXiv:2607.23394v1 Announce Type: new Abstract: Recent work shows that fine-tuning language models on even a small amount of poisoned data can install targeted misbehavior, and ostensibly benign data
arXiv:2607.22552v1 Announce Type: new Abstract: The automatic translation of mathematical expressions in scientific literature into executable symbolic code (a process we refer to as Formula Formaliza
arXiv:2607.22925v1 Announce Type: cross Abstract: A key question for AI safety is whether a language model expresses all of its reasoning in its output tokens. We demonstrate a concrete failure mode w
arXiv:2509.02594v3 Announce Type: replace-cross Abstract: Evaluating large language models (LLMs) on their ability to generate high-quality, accurate, situationally aware answers to clinical questions
Largest empirical study of AI penetration in academic publishing ever conducted—51%-by-2025 is the most authoritative quantitative marker yet of how thoroughly LLMs have reshaped scientific writing, a
arXiv:2607.23075v1 Announce Type: cross Abstract: Detecting fake-order fraud at scale remains a critical challenge for large online-to-offline (O2O) service platforms, as existing approaches often rel
arXiv:2607.24392v1 Announce Type: cross Abstract: Jailbreak defenses are essential for protecting large language models (LLMs), but they can also introduce secondary costs that weaken model utility. W
arXiv:2607.21624v1 Announce Type: cross Abstract: Transformer-based models have enabled unprecedented capabilities across language, vision, and multimodal tasks. On-device fine-tuning of transformer m
arXiv:2607.22389v1 Announce Type: cross Abstract: With the rapid adoption of long-context large language models (LLMs), the continuously growing KV cache during decoding has become the critical memory